| Title: | Unified statistal Modeling of Omics Data |
|---|---|
| Description: | This package unifies access to Statistal Modeling of Omics Data. Across linear modeling engines (lm, lme, lmer, limma, and wilcoxon). Across coding systems (treatment, difference, deviation, etc). Across model formulae (with/without intercept, random effect, interaction or nesting). Across omics platforms (microarray, rnaseq, msproteomics, affinity proteomics, metabolomics). Across projection methods (pca, pls, sma, lda, spls, opls). Across clustering methods (hclust, pam, cmeans). It provides a fast enrichment analysis implementation. And an intuitive contrastogram visualisation to summarize contrast effects in complex designs. |
| Authors: | Aditya Bhagwat [aut, cre], Richard Cotton [aut], Shahina Hayat [aut], Laure Cougnaud [ctb], Witold Szymanski [ctb], Vanessa Beutgen [ctb], Willem Ligtenberg [sad], Hinrich Goehlmann [sad], Karsten Suhre [sad], Johannes Graumann [aut, sad, rth] |
| Maintainer: | Aditya Bhagwat <[email protected]> |
| License: | GPL-3 |
| Version: | 1.13.21 |
| Built: | 2024-07-17 19:36:21 UTC |
| Source: | https://github.com/bioc/autonomics |
Extract coefficient features
.extract_p_features( object, coefs, p = 0.05, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_fdr_features( object, coefs, fdr = 0.05, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_effectsize_features( object, coefs, effectsize = 1, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_sign_features( object, coefs, sign, fit = fits(object)[1], combiner = "|", verbose = TRUE ) .extract_n_features( object, coefs, combiner = "|", n, fit = fits(object)[1], verbose = TRUE ) extract_coef_features( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit), combiner = "|", p = 1, fdr = 1, effectsize = 0, sign = c(-1, +1), n = 4, verbose = TRUE ).extract_p_features( object, coefs, p = 0.05, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_fdr_features( object, coefs, fdr = 0.05, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_effectsize_features( object, coefs, effectsize = 1, fit = fits(object), combiner = "|", verbose = TRUE ) .extract_sign_features( object, coefs, sign, fit = fits(object)[1], combiner = "|", verbose = TRUE ) .extract_n_features( object, coefs, combiner = "|", n, fit = fits(object)[1], verbose = TRUE ) extract_coef_features( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit), combiner = "|", p = 1, fdr = 1, effectsize = 0, sign = c(-1, +1), n = 4, verbose = TRUE )
object |
SummarizedXExperiment |
coefs |
subset of coefs(object) |
p |
p threshold |
fit |
subset of fits(object) |
combiner |
'|' or '&': how to combine multiple fits/coefs |
verbose |
TRUE or FALSE |
fdr |
fdr threshold |
effectsize |
effectsize threshold |
sign |
effect sign |
n |
number of top features (Inf means all) |
SummarizedExperiment
# Read and Fit file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() fdt(object) %<>% add_adjusted_pvalues('fdr') # Single coef object0 <- object object %<>% .extract_p_features( coefs = 't1-t0', p = 0.05) object %<>% .extract_fdr_features( coefs = 't1-t0', fdr = 0.05) object %<>% .extract_effectsize_features(coefs = 't1-t0', effectsize = 1) object %<>% .extract_sign_features( coefs = 't1-t0', sign = -1) object %<>% .extract_n_features( coefs = 't1-t0', n = 1) object <- object0 object %<>% extract_coef_features( coefs = 't1-t0', p = 0.05, fdr = 0.05, effectsize = 1, sign = -1, n = 1) # Multiple coefs object <- object0 object %<>% .extract_p_features( coefs = c('t1-t0', 't2-t0'), p = 0.05) object %<>% .extract_fdr_features( coefs = c('t1-t0', 't2-t0'), fdr = 0.01) object %<>% .extract_effectsize_features(coefs = c('t1-t0', 't2-t0'), effectsize = 1) object %<>% .extract_sign_features( coefs = c('t1-t0', 't2-t0'), sign = -1) object %<>% .extract_n_features( coefs = c('t1-t0', 't2-t0'), n = 1) object <- object0 object %<>% extract_coef_features( coefs = c('t1-t0', 't2-t0'), p = 0.05, fdr = 0.01, effectsize = 1, sign = -1, n = 1)# Read and Fit file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() fdt(object) %<>% add_adjusted_pvalues('fdr') # Single coef object0 <- object object %<>% .extract_p_features( coefs = 't1-t0', p = 0.05) object %<>% .extract_fdr_features( coefs = 't1-t0', fdr = 0.05) object %<>% .extract_effectsize_features(coefs = 't1-t0', effectsize = 1) object %<>% .extract_sign_features( coefs = 't1-t0', sign = -1) object %<>% .extract_n_features( coefs = 't1-t0', n = 1) object <- object0 object %<>% extract_coef_features( coefs = 't1-t0', p = 0.05, fdr = 0.05, effectsize = 1, sign = -1, n = 1) # Multiple coefs object <- object0 object %<>% .extract_p_features( coefs = c('t1-t0', 't2-t0'), p = 0.05) object %<>% .extract_fdr_features( coefs = c('t1-t0', 't2-t0'), fdr = 0.01) object %<>% .extract_effectsize_features(coefs = c('t1-t0', 't2-t0'), effectsize = 1) object %<>% .extract_sign_features( coefs = c('t1-t0', 't2-t0'), sign = -1) object %<>% .extract_n_features( coefs = c('t1-t0', 't2-t0'), n = 1) object <- object0 object %<>% extract_coef_features( coefs = c('t1-t0', 't2-t0'), p = 0.05, fdr = 0.01, effectsize = 1, sign = -1, n = 1)
Clean Merge
.merge(dt1, dt2, by).merge(dt1, dt2, by)
dt1 |
data.table |
dt2 |
data.table |
by |
string |
require(data.table) dt1 <- data.table(feature_id = c('PG1', 'PG2'), gene = c('G1', 'G2')) dt2 <- data.table(feature_id = c('PG1', 'PG2'), protein = c('P1', 'P2')) dt1 %<>% .merge(dt2, by = 'feature_id') dt1require(data.table) dt1 <- data.table(feature_id = c('PG1', 'PG2'), gene = c('G1', 'G2')) dt2 <- data.table(feature_id = c('PG1', 'PG2'), protein = c('P1', 'P2')) dt1 %<>% .merge(dt2, by = 'feature_id') dt1
Read compound discoverer files as-is
.read_compounddiscoverer( file, quantity = guess_compounddiscoverer_quantity(file), colname_format = NULL, mod_extract = NULL, verbose = TRUE ).read_compounddiscoverer( file, quantity = guess_compounddiscoverer_quantity(file), colname_format = NULL, mod_extract = NULL, verbose = TRUE )
file |
compoumd discoverer file |
quantity |
string |
colname_format |
function to reformat column names |
mod_extract |
function to extract MS modi from sample names |
verbose |
TRUE / FALSE |
data.table
Read diann
.read_diann_precursors(file, Lib.PG.Q = 0.01, verbose = TRUE) .read_diann_proteingroups(file, Lib.PG.Q = 0.01) read_diann_proteingroups( file, Lib.PG.Q = 0.01, simplify_snames = TRUE, contaminants = character(0), impute = FALSE, plot = FALSE, pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_diann(...).read_diann_precursors(file, Lib.PG.Q = 0.01, verbose = TRUE) .read_diann_proteingroups(file, Lib.PG.Q = 0.01) read_diann_proteingroups( file, Lib.PG.Q = 0.01, simplify_snames = TRUE, contaminants = character(0), impute = FALSE, plot = FALSE, pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_diann(...)
file |
'report.tsv' file |
Lib.PG.Q |
Lib.PG.Q cutoff |
verbose |
TRUE or FALSE |
simplify_snames |
TRUE or FALSE: simplify (drop common parts in) samplenames ? |
contaminants |
character vector: contaminant uniprots |
impute |
TRUE or FALSE: impute group-specific NA values? |
plot |
TRUE or FALSE |
pca |
TRUE or FALSE: run pca ? |
pls |
TRUE or FALSE: run pls ? |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar: string or NULL |
coefs |
model coefficients of interest: character vector or NULL |
contrasts |
coefficient contrasts of interest: character vector or NULL |
palette |
color palette: named string vector |
... |
used to maintain deprecated functions |
data.table or SummarizedExperiment
# Read file <- download_data('dilution.report.tsv') .read_diann_precursors(file) # precursors longdt .read_diann_proteingroups(file) # proteingroups longdt fdt(read_diann_proteingroups(file)) # proteingroups sumexp # Compare PR <- .read_diann_precursors(file) PG <- .read_diann_proteingroups(file) PG[intensity==top1] # matches : 24975 (85%) proteingroups PG[intensity!=top1] # doesnt match : 4531 (15%) proteingroups RUN <- 'IPT_HeLa_1_DIAstd_Slot1-40_1_9997' PR[uniprot=='Q96JP5;Q96JP5-2' & run == RUN, 1:6] # match: 8884 == 8884 PR[uniprot=='P36578' & run == RUN, 1:6] # no match: 650887 != 407978 PR[intensity != top1][feature_id == unique(feature_id)[1]][run == unique(run)[1]][1:2, 1:6] PR[intensity != top1][feature_id == unique(feature_id)[2]][run == unique(run)[1]][1:2, 1:6] PR[intensity != top1][feature_id == unique(feature_id)[3]][run == unique(run)[1]][1:3, 1:6]# Read file <- download_data('dilution.report.tsv') .read_diann_precursors(file) # precursors longdt .read_diann_proteingroups(file) # proteingroups longdt fdt(read_diann_proteingroups(file)) # proteingroups sumexp # Compare PR <- .read_diann_precursors(file) PG <- .read_diann_proteingroups(file) PG[intensity==top1] # matches : 24975 (85%) proteingroups PG[intensity!=top1] # doesnt match : 4531 (15%) proteingroups RUN <- 'IPT_HeLa_1_DIAstd_Slot1-40_1_9997' PR[uniprot=='Q96JP5;Q96JP5-2' & run == RUN, 1:6] # match: 8884 == 8884 PR[uniprot=='P36578' & run == RUN, 1:6] # no match: 650887 != 407978 PR[intensity != top1][feature_id == unique(feature_id)[1]][run == unique(run)[1]][1:2, 1:6] PR[intensity != top1][feature_id == unique(feature_id)[2]][run == unique(run)[1]][1:2, 1:6] PR[intensity != top1][feature_id == unique(feature_id)[3]][run == unique(run)[1]][1:3, 1:6]
Read proteingroups/phosphosites as-is
.read_maxquant_proteingroups( file, quantity = guess_maxquant_quantity(file), verbose = TRUE ) .read_maxquant_phosphosites( file, profile, quantity = guess_maxquant_quantity(file), verbose = TRUE ).read_maxquant_proteingroups( file, quantity = guess_maxquant_quantity(file), verbose = TRUE ) .read_maxquant_phosphosites( file, profile, quantity = guess_maxquant_quantity(file), verbose = TRUE )
file |
proteingroups / phosphosites file |
quantity |
string |
verbose |
TRUE / FALSE |
profile |
proteingroups file |
data.table
profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') prodt <- .read_maxquant_proteingroups(file = profile) fosdt <- .read_maxquant_phosphosites( file = fosfile, profile = profile)profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') prodt <- .read_maxquant_proteingroups(file = profile) fosdt <- .read_maxquant_phosphosites( file = fosfile, profile = profile)
Read metabolon xlsxfile
.read_metabolon( file, sheet = "OrigScale", fidvar = "BIOCHEMICAL", sidvar = "(CLIENT_IDENTIFIER|Client ID)", sfile = NULL, by.x = "sample_id", by.y = NULL, subgroupvar = "Group", verbose = TRUE ) read_metabolon( file, sheet = "OrigScale", fidvar = "BIOCHEMICAL", sidvar = "(CLIENT_IDENTIFIER|Client ID)", sfile = NULL, by.x = "sample_id", by.y = NULL, subgroupvar = "Group", fnamevar = "BIOCHEMICAL", kegg_pathways = FALSE, smiles = FALSE, impute = TRUE, plot = FALSE, pca = plot, pls = plot, label = "feature_id", fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ).read_metabolon( file, sheet = "OrigScale", fidvar = "BIOCHEMICAL", sidvar = "(CLIENT_IDENTIFIER|Client ID)", sfile = NULL, by.x = "sample_id", by.y = NULL, subgroupvar = "Group", verbose = TRUE ) read_metabolon( file, sheet = "OrigScale", fidvar = "BIOCHEMICAL", sidvar = "(CLIENT_IDENTIFIER|Client ID)", sfile = NULL, by.x = "sample_id", by.y = NULL, subgroupvar = "Group", fnamevar = "BIOCHEMICAL", kegg_pathways = FALSE, smiles = FALSE, impute = TRUE, plot = FALSE, pca = plot, pls = plot, label = "feature_id", fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE )
file |
metabolon xlsx file |
sheet |
excel sheet (number or string) |
fidvar |
featureid var |
sidvar |
samplid var |
sfile |
sample file |
by.x |
'file' mergeby column |
by.y |
'sfile' mergeby column |
subgroupvar |
subgroup var |
verbose |
TRUE or FALSE |
fnamevar |
featurename fvar |
kegg_pathways |
TRUE or FALSE: add kegg pathways? |
smiles |
TRUE or FALSE: add smiles? |
impute |
TRUE or FALSE: impute group-specific NA values? |
plot |
TRUE or FALSE |
pca |
TRUE or FALSE |
pls |
TRUE or FALSE |
label |
fvar |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar: string or NULL |
coefs |
model coefficients of interest: character vector or NULL |
contrasts |
coefficient contrasts of interest: character vector or NULL |
palette |
NULL or colorvector |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') read_metabolon(file, plot = TRUE, block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') read_metabolon(file, plot = TRUE, block = 'Subject')
Read omics data from rectangular file
.read_rectangles( file, sheet = 1, fid_rows, fid_cols, sid_rows, sid_cols, expr_rows, expr_cols, fvar_rows = NULL, fvar_cols = NULL, svar_rows = NULL, svar_cols = NULL, fdata_rows = NULL, fdata_cols = NULL, sdata_rows = NULL, sdata_cols = NULL, transpose = FALSE, verbose = TRUE ) read_rectangles( file, sheet = 1, fid_rows, fid_cols, sid_rows, sid_cols, expr_rows, expr_cols, fvar_rows = NULL, fvar_cols = NULL, svar_rows = NULL, svar_cols = NULL, fdata_rows = NULL, fdata_cols = NULL, sdata_rows = NULL, sdata_cols = NULL, transpose = FALSE, sfile = NULL, sfileby = NULL, subgroupvar = character(0), verbose = TRUE ).read_rectangles( file, sheet = 1, fid_rows, fid_cols, sid_rows, sid_cols, expr_rows, expr_cols, fvar_rows = NULL, fvar_cols = NULL, svar_rows = NULL, svar_cols = NULL, fdata_rows = NULL, fdata_cols = NULL, sdata_rows = NULL, sdata_cols = NULL, transpose = FALSE, verbose = TRUE ) read_rectangles( file, sheet = 1, fid_rows, fid_cols, sid_rows, sid_cols, expr_rows, expr_cols, fvar_rows = NULL, fvar_cols = NULL, svar_rows = NULL, svar_cols = NULL, fdata_rows = NULL, fdata_cols = NULL, sdata_rows = NULL, sdata_cols = NULL, transpose = FALSE, sfile = NULL, sfileby = NULL, subgroupvar = character(0), verbose = TRUE )
file |
string: name of text (txt, csv, tsv, adat) or excel (xls, xlsx) file |
sheet |
integer/string: only relevant for excel files |
fid_rows |
numeric vector: featureid rows |
fid_cols |
numeric vector: featureid cols |
sid_rows |
numeric vector: sampleid rows |
sid_cols |
numeric vector: sampleid cols |
expr_rows |
numeric vector: expr rows |
expr_cols |
numeric vector: expr cols |
fvar_rows |
numeric vector: fvar rows |
fvar_cols |
numeric vector: fvar cols |
svar_rows |
numeric vector: svar rows |
svar_cols |
numeric vector: svar cols |
fdata_rows |
numeric vector: fdata rows |
fdata_cols |
numeric vector: fdata cols |
sdata_rows |
numeric vector: sdata rows |
sdata_cols |
numeric vector: sdata cols |
transpose |
TRUE or FALSE (default) |
verbose |
TRUE (default) or FALSE |
sfile |
sample file |
sfileby |
sample file mergeby column |
subgroupvar |
subgroupvar in sfile |
SummarizedExperiment
# RNASEQ file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') read_rectangles( file, fid_rows = 2:25, fid_cols = 2, sid_rows = 1, sid_cols = 5:28, expr_rows = 2:25 , expr_cols = 5:28, fvar_rows = 1, fvar_cols = 1:4, fdata_rows = 2:25 , fdata_cols = 1:4, transpose = FALSE) # LCMSMS PROTEINGROUPS file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') read_rectangles( file, fid_rows = 2:21, fid_cols = 383, sid_rows = 1, sid_cols = seq(124, 316, by = 6), expr_rows = 2:21, expr_cols = seq(124, 316, by = 6), fvar_rows = 1, fvar_cols = c(2, 6, 7, 383), fdata_rows = 2:21, fdata_cols = c(2, 6, 7, 383), transpose = FALSE ) # SOMASCAN file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') read_rectangles(file, fid_rows = 30, fid_cols = 23:42, sid_rows = 42:108, sid_cols = 4, expr_rows = 42:108, expr_cols = 23:42, fvar_rows = 28:40, fvar_cols = 22, svar_rows = 41, svar_cols = 1:21, fdata_rows = 28:40, fdata_cols = 23:42, sdata_rows = 42:108, sdata_cols = 1:21, transpose = TRUE) # METABOLON file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') read_rectangles(file, sheet = 2, fid_rows = 11:30, fid_cols = 2, sid_rows = 4, sid_cols = 15:81, expr_rows = 11:30, expr_cols = 15:81, fvar_rows = 10, fvar_cols = 1:14, svar_rows = 1:10, svar_cols = 14, fdata_rows = 11:30, fdata_cols = 1:14, sdata_rows = 1:10, sdata_cols = 15:81, transpose = FALSE )# RNASEQ file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') read_rectangles( file, fid_rows = 2:25, fid_cols = 2, sid_rows = 1, sid_cols = 5:28, expr_rows = 2:25 , expr_cols = 5:28, fvar_rows = 1, fvar_cols = 1:4, fdata_rows = 2:25 , fdata_cols = 1:4, transpose = FALSE) # LCMSMS PROTEINGROUPS file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') read_rectangles( file, fid_rows = 2:21, fid_cols = 383, sid_rows = 1, sid_cols = seq(124, 316, by = 6), expr_rows = 2:21, expr_cols = seq(124, 316, by = 6), fvar_rows = 1, fvar_cols = c(2, 6, 7, 383), fdata_rows = 2:21, fdata_cols = c(2, 6, 7, 383), transpose = FALSE ) # SOMASCAN file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') read_rectangles(file, fid_rows = 30, fid_cols = 23:42, sid_rows = 42:108, sid_cols = 4, expr_rows = 42:108, expr_cols = 23:42, fvar_rows = 28:40, fvar_cols = 22, svar_rows = 41, svar_cols = 1:21, fdata_rows = 28:40, fdata_cols = 23:42, sdata_rows = 42:108, sdata_cols = 1:21, transpose = TRUE) # METABOLON file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') read_rectangles(file, sheet = 2, fid_rows = 11:30, fid_cols = 2, sid_rows = 4, sid_cols = 15:81, expr_rows = 11:30, expr_cols = 15:81, fvar_rows = 10, fvar_cols = 1:14, svar_rows = 1:10, svar_cols = 14, fdata_rows = 11:30, fdata_cols = 1:14, sdata_rows = 1:10, sdata_cols = 15:81, transpose = FALSE )
Read rnaseq counts/bams
.read_rnaseq_bams( dir, paired, genome, nthreads = detectCores(), sfile = NULL, by.y = NULL, ensdb = NULL, verbose = TRUE ) .read_rnaseq_counts( file, fid_col = 1, sfile = NULL, by.y = NULL, ensdb = NULL, verbose = TRUE ) read_rnaseq_bams( dir, paired, genome, nthreads = detectCores(), sfile = NULL, by.y = NULL, block = NULL, formula = ~subgroup, min_count = 10, pseudo = 0.5, ensdb = NULL, tpm = FALSE, cpm = TRUE, log2 = TRUE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, voom = cpm, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_rnaseq_counts( file, fid_col = 1, sfile = NULL, by.y = NULL, formula = ~subgroup, block = NULL, min_count = 10, pseudo = 0.5, tpm = FALSE, ensdb = NULL, cpm = !tpm, log2 = TRUE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, voom = cpm, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ).read_rnaseq_bams( dir, paired, genome, nthreads = detectCores(), sfile = NULL, by.y = NULL, ensdb = NULL, verbose = TRUE ) .read_rnaseq_counts( file, fid_col = 1, sfile = NULL, by.y = NULL, ensdb = NULL, verbose = TRUE ) read_rnaseq_bams( dir, paired, genome, nthreads = detectCores(), sfile = NULL, by.y = NULL, block = NULL, formula = ~subgroup, min_count = 10, pseudo = 0.5, ensdb = NULL, tpm = FALSE, cpm = TRUE, log2 = TRUE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, voom = cpm, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_rnaseq_counts( file, fid_col = 1, sfile = NULL, by.y = NULL, formula = ~subgroup, block = NULL, min_count = 10, pseudo = 0.5, tpm = FALSE, ensdb = NULL, cpm = !tpm, log2 = TRUE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, voom = cpm, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE )
dir |
read_rnaseq_bams: bam/sam dir |
paired |
read_rnaseq_bams: TRUE/FALSE : paired end reads ? |
genome |
read_rnaseq_bams: 'mm10', 'hg38', etc. or GTF file |
nthreads |
read_rnaseq_bams: nthreads used by Rsubread::featureCounts() |
sfile |
sample file |
by.y |
sample file mergeby column |
ensdb |
EnsDb with genesizes : e.g. AnnotationHub::AnnotationHub[['AH64923']] |
verbose |
TRUE or FALSE: message? |
file |
count file |
fid_col |
featureid column (number or string) |
block |
model blockvar: string or NULL |
formula |
model formula |
min_count |
min feature count required in some samples |
pseudo |
pseudocount added to prevent -Inf log2 values |
tpm |
TRUE or FALSE : add tpm to assays ( counts / libsize / genelength ) ? |
cpm |
TRUE or FALSE: add cpm to assays ( counts / effectivelibsize ) ? |
log2 |
TRUE or FALSE: log2 transform ? |
plot |
TRUE or FALSE: plot? |
label |
fvar |
pca |
TRUE or FALSE: perform and plot pca? |
pls |
TRUE or FALSE: run pls ? |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
voom |
model weights to be computed? TRUE/FALSE |
coefs |
model coefficients of interest: string vector or NULL |
contrasts |
model coefficient contrasts of interest: string vector or NULL |
palette |
color palette : named string vector |
SummarizedExperiment
Aditya Bhagwat, Shahina Hayat
# read_rnaseq_bams if (requireNamespace('Rsubread')){ dir <- download_data('billing16.bam.zip') object <- read_rnaseq_bams(dir, paired = TRUE, genome = 'hg38') object <- read_rnaseq_bams(dir, paired = TRUE, genome = 'hg38', plot = TRUE) } # read_rnaseq_counts file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00') object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE) object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE, cpm = FALSE) object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE, cpm = FALSE, log2 = FALSE) object <- read_rnaseq_counts(file, plot = TRUE) # read_rnaseq_counts(tpm = TRUE) ## Not run: ah <- AnnotationHub::AnnotationHub() ensdb <- ah[['AH64923']] object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E02-E00', tpm = TRUE, ensdb = ensdb) ## End(Not run)# read_rnaseq_bams if (requireNamespace('Rsubread')){ dir <- download_data('billing16.bam.zip') object <- read_rnaseq_bams(dir, paired = TRUE, genome = 'hg38') object <- read_rnaseq_bams(dir, paired = TRUE, genome = 'hg38', plot = TRUE) } # read_rnaseq_counts file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00') object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE) object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE, cpm = FALSE) object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E15-E00', voom = FALSE, cpm = FALSE, log2 = FALSE) object <- read_rnaseq_counts(file, plot = TRUE) # read_rnaseq_counts(tpm = TRUE) ## Not run: ah <- AnnotationHub::AnnotationHub() ensdb <- ah[['AH64923']] object <- read_rnaseq_counts(file, fit = 'limma', coefs = 'E02-E00', tpm = TRUE, ensdb = ensdb) ## End(Not run)
Read somascan adatfile
.read_somascan( file, fidvar = "Target", sidvar = "SampleId", sfile = NULL, by.x = NULL, by.y = NULL, subgroupvar = "SampleGroup", verbose = TRUE ) read_somascan( file, fidvar = "Target", sidvar = "SampleId", sfile = NULL, by.x = NULL, by.y = NULL, subgroupvar = "SampleGroup", fname_var = "EntrezGeneSymbol", sample_type = "Sample", feature_type = "Protein", sample_quality = c("FLAG", "PASS"), feature_quality = c("FLAG", "PASS"), rm_na_svars = FALSE, rm_single_value_svars = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ).read_somascan( file, fidvar = "Target", sidvar = "SampleId", sfile = NULL, by.x = NULL, by.y = NULL, subgroupvar = "SampleGroup", verbose = TRUE ) read_somascan( file, fidvar = "Target", sidvar = "SampleId", sfile = NULL, by.x = NULL, by.y = NULL, subgroupvar = "SampleGroup", fname_var = "EntrezGeneSymbol", sample_type = "Sample", feature_type = "Protein", sample_quality = c("FLAG", "PASS"), feature_quality = c("FLAG", "PASS"), rm_na_svars = FALSE, rm_single_value_svars = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE )
file |
somascan (adat) file |
fidvar |
featureid var |
sidvar |
sampleid var |
sfile |
sample file |
by.x |
'file' mergeby column |
by.y |
'sfile' mergeby column |
subgroupvar |
subgroup var: string |
verbose |
TRUE or FALSE: message? |
fname_var |
featurename var: string |
sample_type |
subset of c('Sample','QC','Buffer','Calibrator') |
feature_type |
subset of c('Protein', 'Hybridization Control Elution','Rat Protein') |
sample_quality |
subset of c('PASS', 'FLAG', 'FAIL') |
feature_quality |
subset of c('PASS', 'FLAG', 'FAIL') |
rm_na_svars |
TRUE or FALSE: rm NA svars? |
rm_single_value_svars |
TRUE or FALSE: rm single value svars? |
plot |
TRUE or FALSE: plot ? |
label |
fvar |
pca |
TRUE or FALSE: run pca? |
pls |
TRUE or FALSE: run pls? |
fit |
model engine: 'limma', 'lm', 'lme(r)','wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar |
coefs |
model coefficients of interest: character vector or NULL |
contrasts |
coefficient contrasts of interest: character vector or NULL |
palette |
character vector or NULL |
Summarizedexperiment
file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') read_somascan(file, plot = TRUE, block = 'Subject')file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') read_somascan(file, plot = TRUE, block = 'Subject')
Abstract model fit
abstract_fit( object, sep = guess_fitsep(fdt(object)), fit = fits(object), coef = coefs(object, fit = fit), significancevar = "p", significance = 0.05 )abstract_fit( object, sep = guess_fitsep(fdt(object)), fit = fits(object), coef = coefs(object, fit = fit), significancevar = "p", significance = 0.05 )
object |
SummarizedExperiment |
sep |
string |
fit |
character vector |
coef |
character vector |
significancevar |
'p' or 'fdr' |
significance |
fraction : pvalue cutoff |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma', coef = 't3-t0') fdt(object) fdt(abstract_fit(object))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma', coef = 't3-t0') fdt(object) fdt(abstract_fit(object))
Add adjusted pvalues
add_adjusted_pvalues( featuredt, method, fit = fits(featuredt), coefs = default_coefs(featuredt, fit = fit), verbose = TRUE )add_adjusted_pvalues( featuredt, method, fit = fits(featuredt), coefs = default_coefs(featuredt, fit = fit), verbose = TRUE )
featuredt |
fdt(object) |
method |
'fdr', 'bonferroni', ... (see 'p.adjust.methods') |
fit |
'limma', 'lm', 'lme', 'lmer' |
coefs |
coefficient (string) |
verbose |
TRUE or FALSE |
SummarizedExperiment
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) %<>% extract(, 1:2) object %<>% fit_limma(coef = 'Adult-X30dpt') object %<>% extract(order(fdt(.)$`p~Adult-X30dpt~limma`), ) fdt(object) (fdt(object) %<>% add_adjusted_pvalues('fdr')) (fdt(object) %<>% add_adjusted_pvalues('fdr')) # smart enough not to add second column (fdt(object) %>% add_adjusted_pvalues('bonferroni'))file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) %<>% extract(, 1:2) object %<>% fit_limma(coef = 'Adult-X30dpt') object %<>% extract(order(fdt(.)$`p~Adult-X30dpt~limma`), ) fdt(object) (fdt(object) %<>% add_adjusted_pvalues('fdr')) (fdt(object) %<>% add_adjusted_pvalues('fdr')) # smart enough not to add second column (fdt(object) %>% add_adjusted_pvalues('bonferroni'))
Add assay means
add_assay_means(object, assay = assayNames(object)[1], bin = TRUE)add_assay_means(object, assay = assayNames(object)[1], bin = TRUE)
object |
SummarizedExperiment or NULL |
assay |
string |
bin |
TRUE or FALSE |
SummarizedExperiment
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) %<>% extract(, 1:2) fdt(object) object %<>% add_assay_means(SummarizedExperiment::assayNames(.)) fdt(object)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) %<>% extract(, 1:2) fdt(object) object %<>% add_assay_means(SummarizedExperiment::assayNames(.)) fdt(object)
Add facetvars
add_facetvars( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit) )add_facetvars( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit) )
object |
SummarizedExperiment |
fit |
string |
coefs |
string vector |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') fdt(object) fdt(add_facetvars(object))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') fdt(object) fdt(add_facetvars(object))
Add opentargets annotations
add_opentargets_by_uniprot( object, cols = c("genesymbol", "genename", "function"), verbose = TRUE )add_opentargets_by_uniprot( object, cols = c("genesymbol", "genename", "function"), verbose = TRUE )
object |
SummarizedExperiment |
cols |
character vector |
verbose |
TRUE or FALSE |
SummarizedExperiment
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% add_opentargets_by_uniprot()file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% add_opentargets_by_uniprot()
Add PhosphoSitePlus literature counts
add_psp( object, pspfile = file.path(R_user_dir("autonomics", "cache"), "phosphositeplus", "Phosphorylation_site_dataset.gz") )add_psp( object, pspfile = file.path(R_user_dir("autonomics", "cache"), "phosphositeplus", "Phosphorylation_site_dataset.gz") )
object |
SummarizedExperiment |
pspfile |
phosphositeplus file |
Go to www.phosphosite.org
Register and Login.
Download Phosphorylation_site_dataset.gz'.
Save into: file.path(R_user_dir('autonomics','cache'),'phosphositeplus')
SummarizedExperiment
fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_phosphosites(fosfile = fosfile, profile = profile) fdt(object) object %<>% add_psp() fdt(object)fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_phosphosites(fosfile = fosfile, profile = profile) fdt(object) object %<>% add_psp() fdt(object)
Add smiles
add_smiles(object)add_smiles(object)
object |
character/factor vector with pubchem ids |
character/factor vector
https://pubchemdocs.ncbi.nlm.nih.gov/pug-rest-tutorial
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) # add_smiles(object[1:10, ]) # seems downfile <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) # add_smiles(object[1:10, ]) # seems down
Alternative Enrichment Analysis
altenrich( object, pathwaydt, genevar = "gene", genesep = "[ ,;]", coef = default_coefs(object)[1], fit = fits(object)[1], significancevar = "p", significance = 0.05, effectsize = 0, n = 3, genes = FALSE, verbose = TRUE )altenrich( object, pathwaydt, genevar = "gene", genesep = "[ ,;]", coef = default_coefs(object)[1], fit = fits(object)[1], significancevar = "p", significance = 0.05, effectsize = 0, n = 3, genes = FALSE, verbose = TRUE )
object |
|
pathwaydt |
|
genevar |
|
genesep |
|
coef |
|
fit |
|
significancevar |
'p' or 'fdr' |
significance |
significance cutoff |
effectsize |
effectsize cutoff |
n |
no of detected genes required (for geneset to be examined) |
genes |
whether to record genes |
verbose |
whether to msg |
This is an alternative enrichent analysis implementation.
It is more modular: uses four times .enrichment(VERBOSE)? as backend.
But also four times slower than enrichment, so not recommended.
It is retaind for testing purposes.
This alternative enrichment implementation
[enrichment()]
Get/set analysis
analysis(object) ## S4 method for signature 'SummarizedExperiment' analysis(object) analysis(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,list' analysis(object) <- valueanalysis(object) ## S4 method for signature 'SummarizedExperiment' analysis(object) analysis(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,list' analysis(object) <- value
object |
SummarizedExperiment |
value |
list |
analysis details (get) or updated object (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) analysis(object)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) analysis(object)
Analyze
analyze( object, pca = TRUE, pls = TRUE, fit = "limma", formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, contrasts = NULL, coefs = colnames(create_design(object, formula = formula, drop = drop)), block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, plot = pca & !is.null(fit), label = "feature_id", palette = NULL, verbose = TRUE )analyze( object, pca = TRUE, pls = TRUE, fit = "limma", formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, contrasts = NULL, coefs = colnames(create_design(object, formula = formula, drop = drop)), block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, plot = pca & !is.null(fit), label = "feature_id", palette = NULL, verbose = TRUE )
object |
SummarizedExperiment |
pca |
TRUE / FALSE: perform pca ? |
pls |
TRUE / FALSE: perform pls ? |
fit |
linmod engine: 'limma', 'lm', 'lme(r)', 'lmer', 'wilcoxon' |
formula |
model formula |
drop |
TRUE / FALSE : drop varname in designmat ? |
codingfun |
factor coding function
|
contrasts |
model coefficient contrasts of interest: string vector or NULL |
coefs |
model coefficients of interest: string vector or NULL |
block |
model blockvar |
weightvar |
NULL or name of weight matrix in assays(object) |
plot |
TRUE / FALSE |
label |
fvar |
palette |
NULL or colorvector |
verbose |
TRUE / FALSE: message? |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% analyze()file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% analyze()
Annotate maxquant data.table
annotate_maxquant( dt, uniprothdrs, contaminanthdrs, maxquanthdrs, restapi = FALSE, verbose = TRUE )annotate_maxquant( dt, uniprothdrs, contaminanthdrs, maxquanthdrs, restapi = FALSE, verbose = TRUE )
dt |
|
uniprothdrs |
|
contaminanthdrs |
|
maxquanthdrs |
|
restapi |
|
verbose |
|
Uncollapse, annotate, curate, recollapse, name
data.table
# Fukuda 2020: contaminants + maxquanthdrs #----------------------------------------- file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') dt <- .read_maxquant_proteingroups(file) dt[, 1:2] uniprothdrs <- NULL contaminanthdrs <- read_contaminantdt() maxquanthdrs <- parse_maxquant_hdrs(dt$`Fasta headers`); dt$`Fasta headers` <- NULL dt %<>% annotate_maxquant(uniprothdrs, contaminanthdrs, maxquanthdrs) dt[ , 1:9] dt[ reverse== '+', 1:9] dt[contaminant== '+', 1:9] # Billing 2019: uniprothdrs + contaminants + maxquanthdrs #-------------------------------------------------------- profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') upfile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') prodt <- .read_maxquant_proteingroups(profile); prodt[, 1:2] fosdt <- .read_maxquant_phosphosites(fosfile, profile); fosdt[, 1:3] uniprothdrs <- read_uniprotdt(upfile) contaminanthdrs <- read_contaminantdt() maxquanthdrs <- parse_maxquant_hdrs(prodt$`Fasta headers`) annotate_maxquant(prodt, uniprothdrs, contaminanthdrs, maxquanthdrs)[, 1:8] annotate_maxquant(fosdt, uniprothdrs, contaminanthdrs, maxquanthdrs)[, 1:8]# Fukuda 2020: contaminants + maxquanthdrs #----------------------------------------- file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') dt <- .read_maxquant_proteingroups(file) dt[, 1:2] uniprothdrs <- NULL contaminanthdrs <- read_contaminantdt() maxquanthdrs <- parse_maxquant_hdrs(dt$`Fasta headers`); dt$`Fasta headers` <- NULL dt %<>% annotate_maxquant(uniprothdrs, contaminanthdrs, maxquanthdrs) dt[ , 1:9] dt[ reverse== '+', 1:9] dt[contaminant== '+', 1:9] # Billing 2019: uniprothdrs + contaminants + maxquanthdrs #-------------------------------------------------------- profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') upfile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') prodt <- .read_maxquant_proteingroups(profile); prodt[, 1:2] fosdt <- .read_maxquant_phosphosites(fosfile, profile); fosdt[, 1:3] uniprothdrs <- read_uniprotdt(upfile) contaminanthdrs <- read_contaminantdt() maxquanthdrs <- parse_maxquant_hdrs(prodt$`Fasta headers`) annotate_maxquant(prodt, uniprothdrs, contaminanthdrs, maxquanthdrs)[, 1:8] annotate_maxquant(fosdt, uniprothdrs, contaminanthdrs, maxquanthdrs)[, 1:8]
Annotate uniprot/ensp
annotate_uniprot_rest(x, columns = UNIPROTCOLS, verbose = TRUE)annotate_uniprot_rest(x, columns = UNIPROTCOLS, verbose = TRUE)
x |
character vector |
columns |
character vector |
verbose |
TRUE or FALSE |
data.table(dbid, uniprot, reviewed, protein, gene, canonical, isoform, fragment, existence, organism, full)
annotate_uniprot_rest( x = c('P00761', 'Q32MB2') ) annotate_uniprot_rest( x = c('ENSBTAP00000006074', 'ENSP00000377550') )annotate_uniprot_rest( x = c('P00761', 'Q32MB2') ) annotate_uniprot_rest( x = c('ENSBTAP00000006074', 'ENSP00000377550') )
Assert that x is a valid SummarizedExperiment
assert_is_valid_sumexp(x, .xname = get_name_in_parent(x))assert_is_valid_sumexp(x, .xname = get_name_in_parent(x))
x |
SummarizedExperiment |
.xname |
see get_name_in_parent |
TRUE or FALSE
# VALID file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x <- read_metabolon(file) assert_is_valid_sumexp(x) # NOT VALID rownames(SummarizedExperiment::colData(x)) <- NULL # assert_is_valid_sumexp(x)# VALID file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x <- read_metabolon(file) assert_is_valid_sumexp(x) # NOT VALID rownames(SummarizedExperiment::colData(x)) <- NULL # assert_is_valid_sumexp(x)
Data used in examples/vignette/tests/longtests
AUTONOMICS_DATASETSAUTONOMICS_DATASETS
An object of class character of length 19.
AUTONOMICS_DATASETSAUTONOMICS_DATASETS
Bin continuous variable
bin(object, ...) ## S3 method for class 'logical' bin(object, ...) ## S3 method for class 'character' bin(object, ...) ## S3 method for class 'factor' bin(object, ...) ## S3 method for class 'numeric' bin(object, probs = c(0, 0.33, 0.66, 1), ...) ## S3 method for class 'SummarizedExperiment' bin(object, fvar, probs = c(0, 0.33, 0.66, 1), ...)bin(object, ...) ## S3 method for class 'logical' bin(object, ...) ## S3 method for class 'character' bin(object, ...) ## S3 method for class 'factor' bin(object, ...) ## S3 method for class 'numeric' bin(object, probs = c(0, 0.33, 0.66, 1), ...) ## S3 method for class 'SummarizedExperiment' bin(object, fvar, probs = c(0, 0.33, 0.66, 1), ...)
object |
numeric or SummarizedExperiment |
... |
(S3 dispatch) |
probs |
numeric |
fvar |
string or NULL |
factor vector
# Numeric vector object <- rnorm(10, 5, 1) bin(object) # SummarizedExperiment file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') fdt(object <- read_maxquant_proteingroups(file)) fdt(bin(object, 'pepcounts'))# Numeric vector object <- rnorm(10, 5, 1) bin(object) # SummarizedExperiment file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') fdt(object <- read_maxquant_proteingroups(file)) fdt(bin(object, 'pepcounts'))
Biplot
biplot( object, method = biplot_methods(object)[1], by = biplot_by(object, method)[1], dims = biplot_dims(object, method, by)[1:2], color = "subgroup", shape = NULL, size = NULL, alpha = NULL, group = NULL, linetype = NULL, label = NULL, feature_label = "feature_id", fixed = list(shape = 15, size = 3), nx = 0, ny = 0, colorpalette = make_svar_palette(object, color), alphapalette = make_alpha_palette(object, alpha), title = paste0(method, guess_fitsep(fdt(object)), by), theme = ggplot2::theme(plot.title = element_text(hjust = 0.5), panel.grid = element_blank()) )biplot( object, method = biplot_methods(object)[1], by = biplot_by(object, method)[1], dims = biplot_dims(object, method, by)[1:2], color = "subgroup", shape = NULL, size = NULL, alpha = NULL, group = NULL, linetype = NULL, label = NULL, feature_label = "feature_id", fixed = list(shape = 15, size = 3), nx = 0, ny = 0, colorpalette = make_svar_palette(object, color), alphapalette = make_alpha_palette(object, alpha), title = paste0(method, guess_fitsep(fdt(object)), by), theme = ggplot2::theme(plot.title = element_text(hjust = 0.5), panel.grid = element_blank()) )
object |
SummarizedExperiment |
method |
'pca', 'pls', 'lda', 'spls', 'opls', 'sma' |
by |
svar |
dims |
numeric vector: e.g. 1:2 |
color |
svar |
shape |
svar |
size |
svar |
alpha |
svar |
group |
svar |
linetype |
svar |
label |
svar |
feature_label |
fvar |
fixed |
fixed plot aesthetics |
nx |
number of x features to plot |
ny |
number of y features to plot |
colorpalette |
character vector |
alphapalette |
character vector |
title |
string |
theme |
ggplot2::theme output |
ggplot object
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca(ndim = 4) object %<>% pls(ndim = 4) biplot(object) biplot(object, nx = 1) biplot(object, dims = 3:4, nx = 1) biplot(object, method = 'pls') biplot(object, method = 'pls', dims = 3:4) biplot(object, method = 'pls', dims = 3:4, group = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca(ndim = 4) object %<>% pls(ndim = 4) biplot(object) biplot(object, nx = 1) biplot(object, dims = 3:4, nx = 1) biplot(object, method = 'pls') biplot(object, method = 'pls', dims = 3:4) biplot(object, method = 'pls', dims = 3:4, group = 'Subject')
Biplot batch corrections
biplot_corrections( object, method = "pca", by = "sample_id", color = "subgroup", covariates = character(0), varcols = ceiling(sqrt(1 + length(covariates))), plot = TRUE )biplot_corrections( object, method = "pca", by = "sample_id", color = "subgroup", covariates = character(0), varcols = ceiling(sqrt(1 + length(covariates))), plot = TRUE )
object |
SummarizedExperiment |
method |
'pca', 'pls', 'lda', or 'sma' |
by |
svar |
color |
variable mapped to color (symbol) |
covariates |
covariates to be batch-corrected |
varcols |
number of covariate columns |
plot |
TRUE/FALSE: plot? |
grid object
biplot_covariates
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, pca = TRUE, plot = FALSE) biplot_corrections(object, color = 'subgroup', covariates = c('Sex', 'Diabetes', 'Subject', 'Time'))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, pca = TRUE, plot = FALSE) biplot_corrections(object, color = 'subgroup', covariates = c('Sex', 'Diabetes', 'Subject', 'Time'))
Biplot covariates
biplot_covariates( object, method = "pca", by = "sample_id", block = NULL, covariates = "subgroup", ndim = 6, dimcols = 1, varcols = length(covariates), plot = TRUE )biplot_covariates( object, method = "pca", by = "sample_id", block = NULL, covariates = "subgroup", ndim = 6, dimcols = 1, varcols = length(covariates), plot = TRUE )
object |
SummarizedExperiment |
method |
'pca', 'pls', 'lda', or 'sma' |
by |
svar |
block |
svar |
covariates |
covariates: mapped to color or batch-corrected |
ndim |
number of dimensions to plot |
dimcols |
number of dimension columns |
varcols |
number of covariate columns |
plot |
TRUE or FALSE: whether to plot |
ggplot object
biplot_corrections
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, pca = TRUE) biplot_covariates(object, covariates = 'subgroup', ndim = 12, dimcols = 3) biplot_covariates(object, covariates = c('Sex', 'Diabetes', 'Subject', 'Time')) biplot_covariates(object, covariates = c('Sex', 'Diabetes', 'Subject', 'Time'), ndim = 2) biplot_covariates(object, covariates = c('subgroup'), dimcols = 3)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, pca = TRUE) biplot_covariates(object, covariates = 'subgroup', ndim = 12, dimcols = 3) biplot_covariates(object, covariates = c('Sex', 'Diabetes', 'Subject', 'Time')) biplot_covariates(object, covariates = c('Sex', 'Diabetes', 'Subject', 'Time'), ndim = 2) biplot_covariates(object, covariates = c('subgroup'), dimcols = 3)
Put block in lme-compatible format
block2lme(block, ...) ## S3 method for class 'list' block2lme(block, verbose = TRUE, ...) ## S3 method for class 'formula' block2lme(block, verbose = TRUE, ...) ## S3 method for class 'character' block2lme(block, verbose = TRUE, ...) formula2lmer(formula, block) formula2lm(formula, block) block_vars(formula)block2lme(block, ...) ## S3 method for class 'list' block2lme(block, verbose = TRUE, ...) ## S3 method for class 'formula' block2lme(block, verbose = TRUE, ...) ## S3 method for class 'character' block2lme(block, verbose = TRUE, ...) formula2lmer(formula, block) formula2lm(formula, block) block_vars(formula)
block |
block: charactervector or formula |
... |
required for s3 dispatch |
verbose |
TRUE or FALSE |
formula |
formula |
# lme: ensure lme-compatiblae block specification block2lme( block = list(subject = ~1, batch = ~1)) block2lme( block = ~1|subject) block2lme( block = c('subject', 'batch')) # lm: integrate block into formula as random effect formula2lm( formula = ~ subgroup, block = c('subject', 'batch') ) # lmer: integrate block into formula as fixed effect formula2lmer( formula = ~ subgroup, block = c('subject', 'batch') ) formula2lmer( formula = ~ subgroup + (1|subject) + (1|batch ) )# lme: ensure lme-compatiblae block specification block2lme( block = list(subject = ~1, batch = ~1)) block2lme( block = ~1|subject) block2lme( block = c('subject', 'batch')) # lm: integrate block into formula as random effect formula2lm( formula = ~ subgroup, block = c('subject', 'batch') ) # lmer: integrate block into formula as fixed effect formula2lmer( formula = ~ subgroup, block = c('subject', 'batch') ) formula2lmer( formula = ~ subgroup + (1|subject) + (1|batch ) )
Center samples
center( object, selector = rep(TRUE, nrow(object)) == TRUE, fun = "median", verbose = TRUE )center( object, selector = rep(TRUE, nrow(object)) == TRUE, fun = "median", verbose = TRUE )
object |
SummarizedExperiment |
selector |
logical vector (length = nrow(object)) |
fun |
aggregation function (string) |
verbose |
TRUE/FALSE |
SummarizedExperiment
require(matrixStats) file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object)$housekeeping <- FALSE fdt(object)$housekeeping[order(rowVars(values(object)))[1:5]] <- TRUE values(object)[, object$subgroup=='Adult'] %<>% magrittr::add(5) plot_sample_densities(object) plot_sample_densities(center(object)) plot_sample_densities(center(object, housekeeping))require(matrixStats) file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object)$housekeeping <- FALSE fdt(object)$housekeeping[order(rowVars(values(object)))[1:5]] <- TRUE values(object)[, object$subgroup=='Adult'] %<>% magrittr::add(5) plot_sample_densities(object) plot_sample_densities(center(object)) plot_sample_densities(center(object, housekeeping))
Contrast Code Factor for General Linear Model
code(object, ...) ## S3 method for class 'factor' code(object, codingfun, verbose = TRUE, ...) ## S3 method for class 'data.table' code(object, codingfun, vars = names(object), verbose = TRUE, ...) contr.treatment.explicit(n) code_control(n) contr.diff(n) code_diff(n) code_diff_forward(n) code_deviation(n) code_deviation_first(n) code_helmert(n) code_helmert_forward(n)code(object, ...) ## S3 method for class 'factor' code(object, codingfun, verbose = TRUE, ...) ## S3 method for class 'data.table' code(object, codingfun, vars = names(object), verbose = TRUE, ...) contr.treatment.explicit(n) code_control(n) contr.diff(n) code_diff(n) code_diff_forward(n) code_deviation(n) code_deviation_first(n) code_helmert(n) code_helmert_forward(n)
object |
factor vector |
... |
used for s3 dispatch |
codingfun |
factor coding function
|
verbose |
TRUE or FALSE |
vars |
svars |
n |
character vector |
A General Linear Model contains:
* An Intercept Coefficient: expressing some form of sample average
* For each numeric variable: a slope coefficient
* For each k-leveled factor: (k-1) Contrast Coefficients.
The interpretation of (intercept and contrast) coefficients depends on the contrast coding function used.
Several contrast coding functions are available in 'stats' and 'codingMatrices'
But their (function and coefficient) namings are a bit confusing and unsystematic.
Instead, the functions below offer an intuitive interface (to the otherwise powerful stats/codingMatrices packages).
The names of these functions reflect the contrast coding used (treatment, backward, sum, or helmert contrasts).
They also reflect the intercept interpretation (either first factor's first level or grand mean).
They all produce intuitive coefficient names (e.g. 't1-t0' rather than just 't1').
They all have unit scaling (a coefficient of 1 means a backward of 1).
(explicitly coded) factor vector
# Coding functions x <- factor(paste0('t', 0:3)) xlevels <- levels(x) contr.treatment( xlevels) contr.treatment.explicit(xlevels) contr.diff( xlevels) code_control( xlevels) code_diff( xlevels) code_diff_forward( xlevels) code_deviation( xlevels) code_deviation_first( xlevels) code_helmert( xlevels) code_helmert_forward( xlevels) # Code x %<>% code(contr.treatment) x %<>% code(contr.treatment.explicit) x %<>% code(contr.diff) x %<>% code(code_control) x %<>% code(code_diff) x %<>% code(code_diff_forward) x %<>% code(code_deviation) x %<>% code(code_deviation_first) x %<>% code(code_helmert) x %<>% code(code_helmert_forward) # Model file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(codingfun = contr.treatment) # default object %<>% fit_limma(codingfun = contr.treatment.explicit) object %<>% fit_limma(codingfun = contr.diff) object %<>% fit_limma(codingfun = code_control) object %<>% fit_limma(codingfun = code_diff) object %<>% fit_limma(codingfun = code_diff_forward) object %<>% fit_limma(codingfun = code_deviation) object %<>% fit_limma(codingfun = code_deviation_first) object %<>% fit_limma(codingfun = code_helmert) object %<>% fit_limma(codingfun = code_helmert_forward)# Coding functions x <- factor(paste0('t', 0:3)) xlevels <- levels(x) contr.treatment( xlevels) contr.treatment.explicit(xlevels) contr.diff( xlevels) code_control( xlevels) code_diff( xlevels) code_diff_forward( xlevels) code_deviation( xlevels) code_deviation_first( xlevels) code_helmert( xlevels) code_helmert_forward( xlevels) # Code x %<>% code(contr.treatment) x %<>% code(contr.treatment.explicit) x %<>% code(contr.diff) x %<>% code(code_control) x %<>% code(code_diff) x %<>% code(code_diff_forward) x %<>% code(code_deviation) x %<>% code(code_deviation_first) x %<>% code(code_helmert) x %<>% code(code_helmert_forward) # Model file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(codingfun = contr.treatment) # default object %<>% fit_limma(codingfun = contr.treatment.explicit) object %<>% fit_limma(codingfun = contr.diff) object %<>% fit_limma(codingfun = code_control) object %<>% fit_limma(codingfun = code_diff) object %<>% fit_limma(codingfun = code_diff_forward) object %<>% fit_limma(codingfun = code_deviation) object %<>% fit_limma(codingfun = code_deviation_first) object %<>% fit_limma(codingfun = code_helmert) object %<>% fit_limma(codingfun = code_helmert_forward)
Get coefs
coefs(object, ...) ## S3 method for class 'factor' coefs(object, ...) ## S3 method for class 'data.table' coefs(object, fit = fits(object), svars = NULL, ...) ## S3 method for class 'SummarizedExperiment' coefs(object, fit = fits(object), ...)coefs(object, ...) ## S3 method for class 'factor' coefs(object, ...) ## S3 method for class 'data.table' coefs(object, fit = fits(object), svars = NULL, ...) ## S3 method for class 'SummarizedExperiment' coefs(object, fit = fits(object), ...)
object |
factor, data.table, SummarizedExperiment |
... |
required for s3 dispatch |
fit |
'limma', 'lm', 'lme', 'lmer', 'wilcoxon' |
svars |
NULL or charactervector (svar for which to return coefs) |
character vector
# Factor x <- factor(c('A', 'B', 'C')) coefs(x) coefs(code(x, contr.treatment.explicit)) coefs(code(x, code_control)) # SummarizedExperiment file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') coefs(object)# Factor x <- factor(c('A', 'B', 'C')) coefs(x) coefs(code(x, contr.treatment.explicit)) coefs(code(x, code_control)) # SummarizedExperiment file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') coefs(object)
Collapsed entrezg to genesymbol
collapsed_entrezg_to_symbol(x, sep, orgdb)collapsed_entrezg_to_symbol(x, sep, orgdb)
x |
charactervector |
sep |
string |
orgdb |
OrgDb |
character vector
if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ x <- c('7448/3818/727', '5034/9601/64374') orgdb <- org.Hs.eg.db::org.Hs.eg.db collapsed_entrezg_to_symbol(x, sep = '/', orgdb = orgdb) }if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ x <- c('7448/3818/727', '5034/9601/64374') orgdb <- org.Hs.eg.db::org.Hs.eg.db collapsed_entrezg_to_symbol(x, sep = '/', orgdb = orgdb) }
compound discoverer quantity patterns
COMPOUNDDISCOVERER_PATTERNSCOMPOUNDDISCOVERER_PATTERNS
An object of class character of length 2.
COMPOUNDDISCOVERER_PATTERNSCOMPOUNDDISCOVERER_PATTERNS
Contaminants URL
CONTAMINANTSURLCONTAMINANTSURL
An object of class character of length 1.
CONTAMINANTSURLCONTAMINANTSURL
Row/Col contrasts
contrast_subgroup_cols(object, subgroupvar) contrast_subgroup_rows(object, subgroupvar)contrast_subgroup_cols(object, subgroupvar) contrast_subgroup_rows(object, subgroupvar)
object |
SummarizedExperiment |
subgroupvar |
subgroup svar |
matrix
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$subgroup <- paste0(object$Diabetes, '.', object$Time) subgroup_matrix(object, subgroupvar = 'subgroup') contrast_subgroup_cols(object, subgroupvar = 'subgroup') contrast_subgroup_rows(object, subgroupvar = 'subgroup')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$subgroup <- paste0(object$Diabetes, '.', object$Time) subgroup_matrix(object, subgroupvar = 'subgroup') contrast_subgroup_cols(object, subgroupvar = 'subgroup') contrast_subgroup_rows(object, subgroupvar = 'subgroup')
Count/Collapse in/outside intersection
count_in(x, ...) ## S3 method for class 'character' count_in(x, y, ...) ## S3 method for class 'factor' count_in(x, y, ...) ## S3 method for class 'list' count_in(x, y, ...) collapse_in(x, ...) ## S3 method for class 'character' collapse_in(x, y, sep, ...) ## S3 method for class 'factor' collapse_in(x, y, sep, ...) ## S3 method for class 'list' collapse_in(x, y, sep, ...) count_out(x, ...) ## S3 method for class 'character' count_out(x, y, ...) ## S3 method for class 'factor' count_out(x, y, ...) ## S3 method for class 'list' count_out(x, y, ...)count_in(x, ...) ## S3 method for class 'character' count_in(x, y, ...) ## S3 method for class 'factor' count_in(x, y, ...) ## S3 method for class 'list' count_in(x, y, ...) collapse_in(x, ...) ## S3 method for class 'character' collapse_in(x, y, sep, ...) ## S3 method for class 'factor' collapse_in(x, y, sep, ...) ## S3 method for class 'list' collapse_in(x, y, sep, ...) count_out(x, ...) ## S3 method for class 'character' count_out(x, y, ...) ## S3 method for class 'factor' count_out(x, y, ...) ## S3 method for class 'list' count_out(x, y, ...)
x |
character OR list |
... |
used for S3 dispatch |
y |
character |
sep |
string |
number OR numeric
# Sets contrast1 <- c('a', 'b', 'c', 'd') pathway <- c('c', 'd', 'e', 'f') contrast2 <- c('e', 'f', 'g', 'h') # Count outside count_out(contrast1, pathway) count_out(list(contrast1 = contrast1, contrast2 = contrast2), pathway) # Count inside count_in(contrast1, pathway) count_in(list(contrast1 = contrast1, contrast2 = contrast2), pathway) # Collapse inside collapse_in(contrast1, pathway, sep = ' ') collapse_in(list(contrast1 = contrast1, contrast2 = contrast2), pathway, sep = ' ')# Sets contrast1 <- c('a', 'b', 'c', 'd') pathway <- c('c', 'd', 'e', 'f') contrast2 <- c('e', 'f', 'g', 'h') # Count outside count_out(contrast1, pathway) count_out(list(contrast1 = contrast1, contrast2 = contrast2), pathway) # Count inside count_in(contrast1, pathway) count_in(list(contrast1 = contrast1, contrast2 = contrast2), pathway) # Collapse inside collapse_in(contrast1, pathway, sep = ' ') collapse_in(list(contrast1 = contrast1, contrast2 = contrast2), pathway, sep = ' ')
Get / Set counts matrix
counts(object) ## S4 method for signature 'SummarizedExperiment' counts(object) counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' counts(object) <- valuecounts(object) ## S4 method for signature 'SummarizedExperiment' counts(object) counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' counts(object) <- value
object |
SummarizedExperiment |
value |
count matrix (features x samples) |
count matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) counts(object)[1:3, 1:3] counts(object) <- values(object)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) counts(object)[1:3, 1:3] counts(object) <- values(object)
Convert between counts and cpm/tpm
counts2cpm(x, libsize = scaledlibsizes(x)) cpm2counts(x, libsize)counts2cpm(x, libsize = scaledlibsizes(x)) cpm2counts(x, libsize)
x |
count/cpm matrix |
libsize |
(scaled) libsize vector |
cpm/tpm/count matrix
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) libsize <- scaledlibsizes(counts(object)) tpm <- counts2tpm(counts(object), genesize = 1) cpm <- counts2cpm(counts(object), libsize) counts <- cpm2counts(cpm, libsize) sum(counts(object) - counts)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) libsize <- scaledlibsizes(counts(object)) tpm <- counts2tpm(counts(object), genesize = 1) cpm <- counts2cpm(counts(object), libsize) counts <- cpm2counts(cpm, libsize) sum(counts(object) - counts)
counts to tpm
counts2tpm(x, genesize)counts2tpm(x, genesize)
x |
count matrix |
genesize |
genesize vector (kilobase) |
tpm matrix
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) counts(object)[1:3, 1:3] counts2tpm(counts(object), genesize = 1)[1:3, 1:3]file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) counts(object)[1:3, 1:3] counts2tpm(counts(object), genesize = 1)[1:3, 1:3]
Get / Set cpm matrix
cpm(object) ## S4 method for signature 'SummarizedExperiment' cpm(object) cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' cpm(object) <- valuecpm(object) ## S4 method for signature 'SummarizedExperiment' cpm(object) cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' cpm(object) <- value
object |
SummarizedExperiment |
value |
cpm matrix (features x samples) |
cpm matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) cpm(object)[1:3, 1:3] cpm(object) <- values(object)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) cpm(object)[1:3, 1:3] cpm(object) <- values(object)
Create design matrix for statistical analysis
create_design(object, ...) ## S3 method for class 'SummarizedExperiment' create_design( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, verbose = TRUE, ... ) ## S3 method for class 'data.table' create_design( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, verbose = TRUE, ... )create_design(object, ...) ## S3 method for class 'SummarizedExperiment' create_design( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, verbose = TRUE, ... ) ## S3 method for class 'data.table' create_design( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, verbose = TRUE, ... )
object |
SummarizedExperiment or data.frame |
... |
required to s3ify |
formula |
formula with svars |
drop |
whether to drop predictor names |
codingfun |
factor coding function
|
verbose |
whether to message |
design matrix
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) unique(create_design(object)) unique(create_design(object, ~ Time)) unique(create_design(object, ~ Time, codingfun = contr.treatment.explicit)) unique(create_design(object, ~ Time, codingfun = contr.diff)) unique(create_design(object, ~ Time + Diabetes)) unique(create_design(object, ~ Time / Diabetes)) unique(create_design(object, ~ Time * Diabetes))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) unique(create_design(object)) unique(create_design(object, ~ Time)) unique(create_design(object, ~ Time, codingfun = contr.treatment.explicit)) unique(create_design(object, ~ Time, codingfun = contr.diff)) unique(create_design(object, ~ Time + Diabetes)) unique(create_design(object, ~ Time / Diabetes)) unique(create_design(object, ~ Time * Diabetes))
Download autonomics example data
DATADIR download_data( filename = NULL, localdir = file.path(DATADIR, split_extract_fixed(filename, ".", 1)), verbose = TRUE, force = FALSE )DATADIR download_data( filename = NULL, localdir = file.path(DATADIR, split_extract_fixed(filename, ".", 1)), verbose = TRUE, force = FALSE )
filename |
file name
|
||||||||||||||||||||||||||||||||||||
localdir |
local dir to save file to |
||||||||||||||||||||||||||||||||||||
verbose |
TRUE / FALSE |
||||||||||||||||||||||||||||||||||||
force |
TRUE / FALSE |
An object of class character of length 1.
local file path
# Show available datasets download_data() # atkin 2018 - hypoglycemia - pubmed 30525282 # download_data('atkin.somascan.adat') # somascan intensities # download_data('atkin.metabolon.xlsx') # metabolon intensities # billing16 - stemcell characterization - pubmed 26857143 # download_data('billing16.proteingroups.txt') # proteingroup ratios # download_data('billing16.somascan.adat') # somascan intensities # download_data('billing16.rnacounts.txt') # rnaseq counts # download_data('billing16.bam.zip') # rnaseq alignments # billing19 - stemcell differentiation - pubmed 31332097 # download_data('billing19.proteingroups.txt') # proteingroup ratios # download_data('billing19.phosphosites.txt') # phosphosite ratios # download_data('billing19.rnacounts.txt') # rnaseq counts # fukuda20 - heart regeneration - pubmed PXD016235 # download_data('fukuda20.proteingroups.txt') # proteingroup LFQ # halama18 - glutaminase inhibition - pubmed 30525282 # download_data('halama18.metabolon.xlsx') # metabolon intensities# Show available datasets download_data() # atkin 2018 - hypoglycemia - pubmed 30525282 # download_data('atkin.somascan.adat') # somascan intensities # download_data('atkin.metabolon.xlsx') # metabolon intensities # billing16 - stemcell characterization - pubmed 26857143 # download_data('billing16.proteingroups.txt') # proteingroup ratios # download_data('billing16.somascan.adat') # somascan intensities # download_data('billing16.rnacounts.txt') # rnaseq counts # download_data('billing16.bam.zip') # rnaseq alignments # billing19 - stemcell differentiation - pubmed 31332097 # download_data('billing19.proteingroups.txt') # proteingroup ratios # download_data('billing19.phosphosites.txt') # phosphosite ratios # download_data('billing19.rnacounts.txt') # rnaseq counts # fukuda20 - heart regeneration - pubmed PXD016235 # download_data('fukuda20.proteingroups.txt') # proteingroup LFQ # halama18 - glutaminase inhibition - pubmed 30525282 # download_data('halama18.metabolon.xlsx') # metabolon intensities
Get default coefs
default_coefs(object, ...) ## S3 method for class 'data.table' default_coefs(object, fit = fits(object), ...) ## S3 method for class 'SummarizedExperiment' default_coefs(object, fit = fits(object), ...)default_coefs(object, ...) ## S3 method for class 'data.table' default_coefs(object, fit = fits(object), ...) ## S3 method for class 'SummarizedExperiment' default_coefs(object, fit = fits(object), ...)
object |
data.table or SummarizedExperiment |
... |
S3 dispatch |
fit |
'limma', 'lm', 'lme', 'lmer', 'wilcoxon' |
character
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() default_coefs(object)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() default_coefs(object)
Default geom
default_geom(object, x, block = NULL)default_geom(object, x, block = NULL)
object |
SummarizedExperiment |
x |
svar |
block |
svar or NULL |
character vector
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$Age <- runif(min = 20, max = 60, n = ncol(object)) svars(object) default_geom(object, x = 'Age') default_geom(object, x = c('Age', 'Diabetes')) default_geom(object, x = c('Age', 'Diabetes'), block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$Age <- runif(min = 20, max = 60, n = ncol(object)) svars(object) default_geom(object, x = 'Age') default_geom(object, x = c('Age', 'Diabetes')) default_geom(object, x = c('Age', 'Diabetes'), block = 'Subject')
Default sfile
default_sfile(file)default_sfile(file)
file |
data file |
sample file
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') default_sfile(file)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') default_sfile(file)
Create default formula
default_subgroupvar(object) default_formula(object)default_subgroupvar(object) default_formula(object)
object |
SummarizedExperiment |
formula
# Abundances file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) default_formula(object) file <- download_data('billing16.proteingroups.txt') object <- read_maxquant_proteingroups(file) default_formula(object)# Abundances file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) default_formula(object) file <- download_data('billing16.proteingroups.txt') object <- read_maxquant_proteingroups(file) default_formula(object)
Demultiplex maxquant samplenames
demultiplex(x, verbose = FALSE)demultiplex(x, verbose = FALSE)
x |
character vector |
verbose |
TRUE or FALSE |
WT(L).KD(H).R1{H/L} -> KD_WT.R1
WT(1).KD(2).R1{1} -> WT.R1
WT.R1 -> WT.R1
character
# uniplexed / intensity / ratio demultiplex(c('KD.R1','OE.R1')) demultiplex(c('WT(L).KD(M).OE(H).R1{M}', 'WT(L).KD(M).OE(H).R1{H}')) demultiplex(c('WT(L).KD(M).OE(H).R1{M/L}','WT(L).KD(M).OE(H).R1{H/L}')) # run / replicate demultiplex(c('WT(L).OE(H).R1{L}', 'WT(L).OE(H).R1{H}')) # run demultiplex(c('WT.R1(L).OE.R1(H){L}', 'WT.R1(L).OE.R1(H){H}')) # repl # label / index demultiplex(c('WT(L).OE(H).R1{L}', 'WT(L).OE(H).R1{H}')) # label demultiplex(c('WT(1).OE(2).R1{1}', 'WT(1).OE(2).R1{2}')) # index # with unused channels demultiplex('WT(1).KD(2).OE(3).R1{6}')# uniplexed / intensity / ratio demultiplex(c('KD.R1','OE.R1')) demultiplex(c('WT(L).KD(M).OE(H).R1{M}', 'WT(L).KD(M).OE(H).R1{H}')) demultiplex(c('WT(L).KD(M).OE(H).R1{M/L}','WT(L).KD(M).OE(H).R1{H/L}')) # run / replicate demultiplex(c('WT(L).OE(H).R1{L}', 'WT(L).OE(H).R1{H}')) # run demultiplex(c('WT.R1(L).OE.R1(H){L}', 'WT.R1(L).OE.R1(H){H}')) # repl # label / index demultiplex(c('WT(L).OE(H).R1{L}', 'WT(L).OE(H).R1{H}')) # label demultiplex(c('WT(1).OE(2).R1{1}', 'WT(1).OE(2).R1{2}')) # index # with unused channels demultiplex('WT(1).KD(2).OE(3).R1{6}')
Drop quantity ('Reporter intensity').
Encode {channel} as suffix.
dequantify(x, quantity = guess_maxquant_quantity(x), verbose = FALSE)dequantify(x, quantity = guess_maxquant_quantity(x), verbose = FALSE)
x |
|
quantity |
|
verbose |
|
Ratio H/L WT(L).KD(H).R1 -> WT(L).KD(H).R1{H/L}
LFQ intensity WT.R1 -> WT.R1
Reporter intensity 0 WT(126).KD(127).R1 -> WT(1).KD(2).R1{1}
character
dequantify(c('Ratio H/L WT(L).KD(M).OE(H).R1', # Ratios 'Ratio M/L WT(L).KD(M).OE(H).R1')) dequantify(c('Ratio H/L normalized WT(L).KD(M).OE(H).R1', # Norm. Ratios 'Ratio M/L normalized WT(L).KD(M).OE(H).R1')) dequantify(c('LFQ intensity WT.R1', # LFQ intensity 'LFQ intensity KD.R1')) dequantify(c('Reporter intensity 1 WT(126).KD(127).R1', # Rep.intensities 'Reporter intensity 2 WT(126).KD(127).R1'))dequantify(c('Ratio H/L WT(L).KD(M).OE(H).R1', # Ratios 'Ratio M/L WT(L).KD(M).OE(H).R1')) dequantify(c('Ratio H/L normalized WT(L).KD(M).OE(H).R1', # Norm. Ratios 'Ratio M/L normalized WT(L).KD(M).OE(H).R1')) dequantify(c('LFQ intensity WT.R1', # LFQ intensity 'LFQ intensity KD.R1')) dequantify(c('Reporter intensity 1 WT(126).KD(127).R1', # Rep.intensities 'Reporter intensity 2 WT(126).KD(127).R1'))
Drop quantity.
dequantify_compounddiscoverer( x, quantity = guess_compounddiscoverer_quantity(x), verbose = FALSE )dequantify_compounddiscoverer( x, quantity = guess_compounddiscoverer_quantity(x), verbose = FALSE )
x |
|
quantity |
|
verbose |
|
Norm. Area: 20230908_F143_HILICNEG.raw (F11) -> 20230908_F143_HILICNEG.raw (F11)
Area: 20230908_F143_HILICNEG.raw (F11) -> 20230908_F143_HILICNEG.raw (F11)
character
dequantify_compounddiscoverer("Norm. Area: 20230908_F143_HILICNEG.raw (F11)") # Norm. Area dequantify_compounddiscoverer("Area: 20230908_F143_HILICNEG.raw (F11)") # Areadequantify_compounddiscoverer("Norm. Area: 20230908_F143_HILICNEG.raw (F11)") # Norm. Area dequantify_compounddiscoverer("Area: 20230908_F143_HILICNEG.raw (F11)") # Area
Downloads contaminants
download_contaminants(url = CONTAMINANTSURL, overwrite = FALSE)download_contaminants(url = CONTAMINANTSURL, overwrite = FALSE)
url |
contaminants file url (string) |
overwrite |
TRUE or FALSE: overwrite existiung download? |
filename (string)
download_contaminants() # download first time download_contaminants(overwrite = TRUE) # download each timedownload_contaminants() # download first time download_contaminants(overwrite = TRUE) # download each time
Download GTF file with feature annotations
download_gtf( organism, release = 100, gtffile = sprintf("%s/gtf/%s", R_user_dir("autonomics", "cache"), basename(make_gtf_url(organism, release) %>% substr(1, nchar(.) - 3))) )download_gtf( organism, release = 100, gtffile = sprintf("%s/gtf/%s", R_user_dir("autonomics", "cache"), basename(make_gtf_url(organism, release) %>% substr(1, nchar(.) - 3))) )
organism |
'Homo sapiens', 'Mus musculus' or 'Rattus norvegicus' |
release |
GTF release (number) |
gtffile |
string: path to local GTF file |
gtffile path
organism <- 'Homo sapiens' # download_gtf(organism)organism <- 'Homo sapiens' # download_gtf(organism)
Download mcclain21 data
download_mcclain21( counts_or_samples = "counts", localdir = file.path(DATADIR, "mcclain21"), force = FALSE )download_mcclain21( counts_or_samples = "counts", localdir = file.path(DATADIR, "mcclain21"), force = FALSE )
counts_or_samples |
'counts' or 'samples' |
localdir |
dirname |
force |
TRUE or FALSE |
Mc clain 2021: COVID19 transcriptomics:
download_mcclain21('counts') download_mcclain21('samples')download_mcclain21('counts') download_mcclain21('samples')
Download tcga example
download_tcga_example()download_tcga_example()
Convert between 'data.table' and 'matrix'
dt2mat(x) mat2dt(x, idvar)dt2mat(x) mat2dt(x, idvar)
x |
data.table / matrix |
idvar |
idvar string |
matrix / data.table
x <- data.table::data.table( gene = c('ENSG001', 'ENSG002', 'ENSG003'), sampleA = c(1787, 10, 432), sampleB = c(1143, 3, 268)) dt2mat(x) mat2dt(dt2mat(x), 'gene')x <- data.table::data.table( gene = c('ENSG001', 'ENSG002', 'ENSG003'), sampleA = c(1787, 10, 432), sampleB = c(1143, 3, 268)) dt2mat(x) mat2dt(dt2mat(x), 'gene')
Are selected genes enriched in pathway?
enrichment( object, pathwaydt, fit = fits(object)[1], coef = coefs(object, fit = fit)[1], var = abstractvar(object, fit = fit, coef = coef), levels = fdt(object)[[var]] %>% base::levels() %>% extract(-1), genevar = "gene", genesep = "[ ,;]", n = 3, verbose = TRUE, genes = FALSE )enrichment( object, pathwaydt, fit = fits(object)[1], coef = coefs(object, fit = fit)[1], var = abstractvar(object, fit = fit, coef = coef), levels = fdt(object)[[var]] %>% base::levels() %>% extract(-1), genevar = "gene", genesep = "[ ,;]", n = 3, verbose = TRUE, genes = FALSE )
object |
|
pathwaydt |
pathway |
fit |
string |
coef |
string |
var |
selection fvar |
levels |
selection levels |
genevar |
gene fvar |
genesep |
gene separator (string) |
n |
number |
verbose |
whether to msg |
genes |
whether to report genes |
Four enrichment analyses per geneset using the Fisher Exact Test (see four pvalues). Results are returned in a data.table
| in | : genes in pathway |
| in.det | : detected genes in pathway |
| in.sel | : up/downregulated genes in pathway |
| in.up(.genes) | : upregulated genes in pathway |
| in.down(.genes) | : downregulated genes in pathway |
| out | : genes outside pathway |
| det | : detected genes (in + out) |
| sel | : up/downregulated genes (in + out) |
| up | : upregulated genes (in + out) |
| down | : downregulated genes (in + out) |
| p.coef.upDET | : prob to randomly select this many (or more) upregulated genes (among detected genes) |
| p.coef.downDET | : prob to randomly select this many (or more) downregulated genes (among detected genes) |
| p.coef.selDET | : prob to randomly select this many (or more) up OR downregulated genes (among detected genes) |
| p.coef.selGEN | : prob to randomly select this many (or more) up OR downregulated genes (among genome genes) |
| p.detGEN | : prob to randomly select this many (or more) detected genes (among genome genes) |
# Read pathwaydt <- read_msigdt(collections = 'C5:GO:BP') file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file, fit = 'limma', coefs = 't1-t0') fvars(object) %<>% gsub('EntrezGeneSymbol', 'gene', .) object %<>% abstract_fit() var <- abstractvar(object) varlevels <- c('flat', 'down', 'up') enrichdt1 <- enrichment(object, pathwaydt, var = var) # 2:n factor enrichdt2 <- enrichment(object, pathwaydt, var = var, levels = varlevels) # 1:n factor enrichdt3 <- altenrich(object, pathwaydt) # alternative implementation cols <- intersect(names(enrichdt1), names(enrichdt3)) all(enrichdt1[, cols, with = FALSE] == enrichdt3[, cols, with = FALSE]) # identical# Read pathwaydt <- read_msigdt(collections = 'C5:GO:BP') file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file, fit = 'limma', coefs = 't1-t0') fvars(object) %<>% gsub('EntrezGeneSymbol', 'gene', .) object %<>% abstract_fit() var <- abstractvar(object) varlevels <- c('flat', 'down', 'up') enrichdt1 <- enrichment(object, pathwaydt, var = var) # 2:n factor enrichdt2 <- enrichment(object, pathwaydt, var = var, levels = varlevels) # 1:n factor enrichdt3 <- altenrich(object, pathwaydt) # alternative implementation cols <- intersect(names(enrichdt1), names(enrichdt3)) all(enrichdt1[, cols, with = FALSE] == enrichdt3[, cols, with = FALSE]) # identical
taxon/ens to organism
ens2org(x) taxon2org(x)ens2org(x) taxon2org(x)
x |
character vector |
character vector
taxon2org( x = c('9606', '9913') ) ens2org( x = c('ENSP00000377550', 'ENSBTAP00000038329') )taxon2org( x = c('9606', '9913') ) ens2org( x = c('ENSP00000377550', 'ENSBTAP00000038329') )
Entrezg to genesymbol
entrezg_to_symbol(x, orgdb)entrezg_to_symbol(x, orgdb)
x |
charactervector |
orgdb |
OrgDb |
character vector
if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ orgdb <- org.Hs.eg.db::org.Hs.eg.db entrezg_to_symbol(x = c('7448', '3818', '727'), orgdb) }if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ orgdb <- org.Hs.eg.db::org.Hs.eg.db entrezg_to_symbol(x = c('7448', '3818', '727'), orgdb) }
Explore transformations
explore_transformations( object, subgroupvar = "subgroup", transformations = c("quantnorm", "vsn", "zscore", "invnorm"), method = "pca", xdim = 1, ydim = 2, ... )explore_transformations( object, subgroupvar = "subgroup", transformations = c("quantnorm", "vsn", "zscore", "invnorm"), method = "pca", xdim = 1, ydim = 2, ... )
object |
SummarizedExperiment |
subgroupvar |
string |
transformations |
vector |
method |
'pca', 'pls', 'sma', or 'lda' |
xdim |
number (default 1) |
ydim |
number (default 2) |
... |
passed to plot_data |
grid object
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) object <- read_maxquant_proteingroups(file, subgroups = subgroups) explore_transformations(object, transformations = c('quantnorm', 'zscore', 'invnorm'))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) object <- read_maxquant_proteingroups(file, subgroups = subgroups) explore_transformations(object, transformations = c('quantnorm', 'zscore', 'invnorm'))
Extract rectangle from omics file, data.table, or matrix
extract_rectangle(x, ...) ## S3 method for class 'character' extract_rectangle( x, rows = seq_len(nrows(x, sheet = sheet)), cols = seq_len(ncols(x, sheet = sheet)), verbose = FALSE, transpose = FALSE, drop = FALSE, sheet = 1, ... ) ## S3 method for class 'data.table' extract_rectangle( x, rows = seq_len(nrow(x)), cols = seq_len(ncol(x)), transpose = FALSE, drop = FALSE, ... ) ## S3 method for class 'matrix' extract_rectangle( x, rows = seq_len(nrow(x)), cols = seq_len(ncol(x)), transpose = FALSE, drop = FALSE, ... )extract_rectangle(x, ...) ## S3 method for class 'character' extract_rectangle( x, rows = seq_len(nrows(x, sheet = sheet)), cols = seq_len(ncols(x, sheet = sheet)), verbose = FALSE, transpose = FALSE, drop = FALSE, sheet = 1, ... ) ## S3 method for class 'data.table' extract_rectangle( x, rows = seq_len(nrow(x)), cols = seq_len(ncol(x)), transpose = FALSE, drop = FALSE, ... ) ## S3 method for class 'matrix' extract_rectangle( x, rows = seq_len(nrow(x)), cols = seq_len(ncol(x)), transpose = FALSE, drop = FALSE, ... )
x |
omics datafile or datatable |
... |
allow for S3 method dispatch |
rows |
numeric vector |
cols |
numeric vector |
verbose |
logical |
transpose |
logical |
drop |
logical |
sheet |
numeric or string |
matrix
# FROM FILE: extract_rectangle.character #======================================= x <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') extract_rectangle(x, rows = 11:30, cols = 15:81, sheet = 2)[ 1:3, 1:3 ] # exprs extract_rectangle(x, rows = 11:30, cols = 2, sheet = 2)[ 1:3, ] # fids extract_rectangle(x, rows = 4, cols = 15:81, sheet = 2)[ , 1:3 ] # sids extract_rectangle(x, rows = 10:30, cols = 1:14, sheet = 2)[ 1:3, 1:3 ] # fdt extract_rectangle(x, rows = 1:10, cols = 14:81, sheet = 2, transpose = TRUE)[1:3, 1:3] # sdt # FROM MATRIX: extract_rectangle.matrix #====================================== x <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x %<>% extract_rectangle(sheet = 2) extract_rectangle(x, rows = 11:30, cols = 15:81, sheet = 2)[ 1:3, 1:3 ] # exprs extract_rectangle(x, rows = 11:30, cols = 2, sheet = 2)[ 1:3, ] # fids extract_rectangle(x, rows = 4, cols = 15:81, sheet = 2)[ , 1:3 ] # sids extract_rectangle(x, rows = 10:30, cols = 1:14, sheet = 2)[ 1:3, 1:3 ] # fdt extract_rectangle(x, rows = 1:10, cols = 14:81, sheet = 2, transpose = TRUE)[1:3, 1:3] # sdt# FROM FILE: extract_rectangle.character #======================================= x <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') extract_rectangle(x, rows = 11:30, cols = 15:81, sheet = 2)[ 1:3, 1:3 ] # exprs extract_rectangle(x, rows = 11:30, cols = 2, sheet = 2)[ 1:3, ] # fids extract_rectangle(x, rows = 4, cols = 15:81, sheet = 2)[ , 1:3 ] # sids extract_rectangle(x, rows = 10:30, cols = 1:14, sheet = 2)[ 1:3, 1:3 ] # fdt extract_rectangle(x, rows = 1:10, cols = 14:81, sheet = 2, transpose = TRUE)[1:3, 1:3] # sdt # FROM MATRIX: extract_rectangle.matrix #====================================== x <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x %<>% extract_rectangle(sheet = 2) extract_rectangle(x, rows = 11:30, cols = 15:81, sheet = 2)[ 1:3, 1:3 ] # exprs extract_rectangle(x, rows = 11:30, cols = 2, sheet = 2)[ 1:3, ] # fids extract_rectangle(x, rows = 4, cols = 15:81, sheet = 2)[ , 1:3 ] # sids extract_rectangle(x, rows = 10:30, cols = 1:14, sheet = 2)[ 1:3, 1:3 ] # fdt extract_rectangle(x, rows = 1:10, cols = 14:81, sheet = 2, transpose = TRUE)[1:3, 1:3] # sdt
Cluster features
fcluster( object, distmat = NULL, method = "cmeans", k = 2:10, verbose = TRUE, plot = TRUE, label = if ("gene" %in% fvars(object)) "gene" else "feature_id", alpha = 1, nrow = if (length(method) > 1) length(method) else NULL, ncol = NULL )fcluster( object, distmat = NULL, method = "cmeans", k = 2:10, verbose = TRUE, plot = TRUE, label = if ("gene" %in% fvars(object)) "gene" else "feature_id", alpha = 1, nrow = if (length(method) > 1) length(method) else NULL, ncol = NULL )
object |
SummarizedExperiment |
distmat |
distance matrix |
method |
'cmeans' |
k |
number of clusters |
verbose |
TRUE or FALSE |
plot |
TRUE or FALSE |
label |
fvar |
alpha |
fraction |
nrow |
number |
ncol |
number |
SummarizedExperiment
SummarizedExperiment
object <- twofactor_sumexp() distmat <- fdist(object) fcluster(object) # membership-based colors fcluster(object, distmat) # silhouette-based colors fcluster(object, distmat, method = c('cmeans', 'hclust', 'pamk')) # more methodsobject <- twofactor_sumexp() distmat <- fdist(object) fcluster(object) # membership-based colors fcluster(object, distmat) # silhouette-based colors fcluster(object, distmat, method = c('cmeans', 'hclust', 'pamk')) # more methods
Get/Set sample/feature data
fdata(object) sdata(object) fdt(object) sdt(object) ## S4 method for signature 'SummarizedExperiment' fdata(object) ## S4 method for signature 'SummarizedExperiment' sdata(object) ## S4 method for signature 'SummarizedExperiment' fdt(object) ## S4 method for signature 'SummarizedExperiment' sdt(object) fdata(object) <- value sdata(object) <- value fdt(object) <- value sdt(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.frame' fdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.frame' sdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,DataFrame' sdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.table' fdt(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.table' sdt(object) <- valuefdata(object) sdata(object) fdt(object) sdt(object) ## S4 method for signature 'SummarizedExperiment' fdata(object) ## S4 method for signature 'SummarizedExperiment' sdata(object) ## S4 method for signature 'SummarizedExperiment' fdt(object) ## S4 method for signature 'SummarizedExperiment' sdt(object) fdata(object) <- value sdata(object) <- value fdt(object) <- value sdt(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.frame' fdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.frame' sdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,DataFrame' sdata(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.table' fdt(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,data.table' sdt(object) <- value
object |
SummarizedExperiment |
value |
data.frame/data.table |
data.frame/data.table (get) or updated object (set)
# Read data file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) # sdt/fdt sdt(object)[1:3, ] fdt(object)[1:3, ] sdt(object) %<>% cbind(b=1) fdt(object) %<>% cbind(b=1) sdt(object) fdt(object) # sdata/fdata sdata(object)[1:3, ] fdata(object)[1:3, ] sdata(object) %<>% cbind(a=1) fdata(object) %<>% cbind(a=1) sdata(object)[1:3, ] fdata(object)[1:3, ]# Read data file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) # sdt/fdt sdt(object)[1:3, ] fdt(object)[1:3, ] sdt(object) %<>% cbind(b=1) fdt(object) %<>% cbind(b=1) sdt(object) fdt(object) # sdata/fdata sdata(object)[1:3, ] fdata(object)[1:3, ] sdata(object) %<>% cbind(a=1) fdata(object) %<>% cbind(a=1) sdata(object)[1:3, ] fdata(object)[1:3, ]
fdr to p
fdr2p(fdr)fdr2p(fdr)
fdr |
fdr values |
# Read/Fit file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() pcol <- pvar(fdt(object), fit = 'limma', coef = 't3-t0') object %<>% extract(order(fdt(.)[[pcol]]), ) object %<>% extract(1:10, ) fdt(object) %<>% extract(, 1) object %<>% fit_limma(coefs = 't3-t0') # fdr2p fdt(object)[[pcol]] fdt(object)[[pcol]] %>% p.adjust(method = 'fdr') fdt(object)[[pcol]] %>% p.adjust(method = 'fdr') %>% fdr2p()# Read/Fit file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() pcol <- pvar(fdt(object), fit = 'limma', coef = 't3-t0') object %<>% extract(order(fdt(.)[[pcol]]), ) object %<>% extract(1:10, ) fdt(object) %<>% extract(, 1) object %<>% fit_limma(coefs = 't3-t0') # fdr2p fdt(object)[[pcol]] fdt(object)[[pcol]] %>% p.adjust(method = 'fdr') fdt(object)[[pcol]] %>% p.adjust(method = 'fdr') %>% fdr2p()
Filter features with replicated expression in some subgroup
filter_exprs_replicated_in_some_subgroup( object, subgroupvar = "subgroup", assay = assayNames(object)[1], comparator = if (contains_ratios(object)) "!=" else ">", lod = 0, nsample = 2, nsubgroup = 1, verbose = TRUE )filter_exprs_replicated_in_some_subgroup( object, subgroupvar = "subgroup", assay = assayNames(object)[1], comparator = if (contains_ratios(object)) "!=" else ">", lod = 0, nsample = 2, nsubgroup = 1, verbose = TRUE )
object |
SummarizedExperiment |
subgroupvar |
subgroup svar |
assay |
string |
comparator |
'>' or '!=' |
lod |
number: limit of detection |
nsample |
number |
nsubgroup |
number |
verbose |
TRUE or FALSE |
Filtered SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% filter_exprs_replicated_in_some_subgroup() filter_exprs_replicated_in_some_subgroup(object, character(0)) filter_exprs_replicated_in_some_subgroup(object, NULL)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% filter_exprs_replicated_in_some_subgroup() filter_exprs_replicated_in_some_subgroup(object, character(0)) filter_exprs_replicated_in_some_subgroup(object, NULL)
Filter features on condition
filter_features(object, condition, verbose = TRUE)filter_features(object, condition, verbose = TRUE)
object |
SummarizedExperiment |
condition |
filter condition |
verbose |
logical |
filtered eSet
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) filter_features(object, SUPER_PATHWAY == 'Lipid')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) filter_features(object, SUPER_PATHWAY == 'Lipid')
Filter medoid sample
filter_medoid(object, by = NULL, verbose = FALSE)filter_medoid(object, by = NULL, verbose = FALSE)
object |
SummarizedExperiment |
by |
svar |
verbose |
whether to message |
SummarizedExperiment
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, plot = FALSE) object %<>% filter_medoid(by = 'subgroup', verbose=TRUE)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, plot = FALSE) object %<>% filter_medoid(by = 'subgroup', verbose=TRUE)
Filter samples on condition
filter_samples(object, condition, verbose = TRUE, record = TRUE)filter_samples(object, condition, verbose = TRUE, record = TRUE)
object |
SummarizedExperiment |
condition |
filter condition |
verbose |
TRUE/FALSE |
record |
TRUE/FALSE |
filtered SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) filter_samples(object, subgroup != 't0', verbose = TRUE)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) filter_samples(object, subgroup != 't0', verbose = TRUE)
Fit General Linear Model
fit( object, formula = default_formula(object), engine = "limma", drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun, verbose = FALSE), contrasts = NULL, coefs = if (is.null(contrasts)) contrast_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, engine), verbose = TRUE, plot = FALSE ) fit_limma( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, coefs = if (is.null(contrasts)) model_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "t"), ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, "limma"), verbose = TRUE, plot = FALSE ) .fit_limma( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, coefs = if (is.null(contrasts)) model_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, "limma"), verbose = TRUE, plot = FALSE ) fit_wilcoxon( object, formula = default_formula(object), drop = NULL, codingfun = contr.treatment.explicit, design = NULL, contrasts = NULL, coefs = NULL, block = NULL, weightvar = NULL, statvars = c("effect", "p"), sep = FITSEP, suffix = paste0(sep, "wilcoxon"), verbose = TRUE, plot = FALSE )fit( object, formula = default_formula(object), engine = "limma", drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun, verbose = FALSE), contrasts = NULL, coefs = if (is.null(contrasts)) contrast_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, engine), verbose = TRUE, plot = FALSE ) fit_limma( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, coefs = if (is.null(contrasts)) model_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "t"), ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, "limma"), verbose = TRUE, plot = FALSE ) .fit_limma( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = create_design(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, coefs = if (is.null(contrasts)) model_coefs(design = design) else NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, "limma"), verbose = TRUE, plot = FALSE ) fit_wilcoxon( object, formula = default_formula(object), drop = NULL, codingfun = contr.treatment.explicit, design = NULL, contrasts = NULL, coefs = NULL, block = NULL, weightvar = NULL, statvars = c("effect", "p"), sep = FITSEP, suffix = paste0(sep, "wilcoxon"), verbose = TRUE, plot = FALSE )
object |
SummarizedExperiment |
formula |
model formula |
engine |
'limma', 'lm', 'lme', 'lmer', or 'wilcoxon' |
drop |
TRUE or FALSE |
codingfun |
factor coding function
|
design |
design matrix |
contrasts |
NULL or character vector: coefficient contrasts to test |
coefs |
NULL or character vector: model coefs to test |
block |
block svar (or NULL) |
weightvar |
NULL or name of weight matrix in assays(object) |
statvars |
character vector: subset of c('effect', 'p', 'fdr', 't', 'se') |
ftest |
TRUE or FALSE |
sep |
string: pvar separator ("~" in "p~t2~limma") |
suffix |
string: pvar suffix ("limma" in "p~t2~limma") |
verbose |
whether to msg |
plot |
whether to plot |
Updated SummarizedExperiment
# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) # Standard fdt(object) %<>% extract(, 'feature_id') object %<>% fit_lm( ~ subgroup) # statistics default object %<>% fit_limma( ~ subgroup) # bioinformatics default summarize_fit(object) # Blocked fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject') # simple random effects object %<>% fit_lme( ~ subgroup, block = 'Subject') # powerful random effects object %<>% fit_lmer( ~ subgroup, block = 'Subject') # more powerful random effects summarize_fit(object) # Alternative coding: e.g. grand mean intercept fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = code_control) object %<>% fit_lme( ~ subgroup, block = 'Subject', codingfun = code_control) object %<>% fit_lmer( ~ subgroup, block = 'Subject', codingfun = code_control) summarize_fit(object) # Posthoc contrasts (only limma!) fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = code_control, coefs ='t1-t0') object %<>% fit_limma( ~ 0 + subgroup, block = 'Subject', contrasts = 't1-t0') # flexible, but only approximate # stat.ethz.ch/pipermail/bioconductor/2014-February/057682.html # Non-parametric: wilcoxon fdt(object) %<>% extract(, 'feature_id') object %<>% fit_wilcoxon( ~ subgroup) # unpaired object %<>% fit_wilcoxon( ~ subgroup, block = 'Subject') # paired # Custom separator fdt(object) %<>% extract(, 'feature_id') fdt( fit_lm( object, sep = '.')) fdt( fit_limma( object, block = 'Subject', sep = '.') ) fdt( fit_lme( object, block = 'Subject', sep = '.') ) fdt( fit_lmer( object, block = 'Subject', sep = '.') ) fdt( fit_wilcoxon(object, block = 'Subject', sep = '.') ) fdt( fit_wilcoxon(object, sep = '.') )# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) # Standard fdt(object) %<>% extract(, 'feature_id') object %<>% fit_lm( ~ subgroup) # statistics default object %<>% fit_limma( ~ subgroup) # bioinformatics default summarize_fit(object) # Blocked fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject') # simple random effects object %<>% fit_lme( ~ subgroup, block = 'Subject') # powerful random effects object %<>% fit_lmer( ~ subgroup, block = 'Subject') # more powerful random effects summarize_fit(object) # Alternative coding: e.g. grand mean intercept fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = code_control) object %<>% fit_lme( ~ subgroup, block = 'Subject', codingfun = code_control) object %<>% fit_lmer( ~ subgroup, block = 'Subject', codingfun = code_control) summarize_fit(object) # Posthoc contrasts (only limma!) fdt(object) %<>% extract(, 'feature_id') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = code_control, coefs ='t1-t0') object %<>% fit_limma( ~ 0 + subgroup, block = 'Subject', contrasts = 't1-t0') # flexible, but only approximate # stat.ethz.ch/pipermail/bioconductor/2014-February/057682.html # Non-parametric: wilcoxon fdt(object) %<>% extract(, 'feature_id') object %<>% fit_wilcoxon( ~ subgroup) # unpaired object %<>% fit_wilcoxon( ~ subgroup, block = 'Subject') # paired # Custom separator fdt(object) %<>% extract(, 'feature_id') fdt( fit_lm( object, sep = '.')) fdt( fit_limma( object, block = 'Subject', sep = '.') ) fdt( fit_lme( object, block = 'Subject', sep = '.') ) fdt( fit_lmer( object, block = 'Subject', sep = '.') ) fdt( fit_wilcoxon(object, block = 'Subject', sep = '.') ) fdt( fit_wilcoxon(object, sep = '.') )
Fit lm, lme, or lmer
fit_lmx( object, fit, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), block = NULL, opt = "optim", weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, fit), verbose = TRUE, plot = FALSE ) fit_lm( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lm"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE ) fit_lme( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, opt = "optim", statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lme"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE ) fit_lmer( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lmer"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE )fit_lmx( object, fit, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), block = NULL, opt = "optim", weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], ftest = if (is.null(coefs)) TRUE else FALSE, sep = FITSEP, suffix = paste0(sep, fit), verbose = TRUE, plot = FALSE ) fit_lm( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lm"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE ) fit_lme( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, opt = "optim", statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lme"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE ) fit_lmer( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit, design = NULL, block = NULL, weightvar = if ("weights" %in% assayNames(object)) "weights" else NULL, statvars = c("effect", "p", "se", "t")[1:2], sep = FITSEP, suffix = paste0(sep, "lmer"), coefs = model_coefs(object, formula = formula, drop = drop, codingfun = codingfun), contrasts = NULL, ftest = if (is.null(coefs)) TRUE else FALSE, verbose = TRUE, plot = FALSE )
object |
SummarizedExpriment |
fit |
'lm', 'lme', or 'lmer' |
formula |
formula |
drop |
TRUE or FALSE |
codingfun |
coding function |
coefs |
NULL or stringvector |
block |
NULL or svar |
opt |
optimizer used in fit_lme: 'optim' (more robust) or 'nlminb' |
weightvar |
NULL or svar |
statvars |
character vector: subset of c('effect', 'p', 'fdr', 't') |
ftest |
TRUE or FALSE |
sep |
string |
suffix |
string: pvar suffix ("lm" in "p~t2~lm") |
verbose |
TRUE or FALSE |
plot |
TRUE or FALSE |
design |
NULL |
contrasts |
unused. only to allow generic get(fitfun)(contrasts) |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fit_lm( object, formula = ~subgroup) fit_limma( object, formula = ~subgroup) fit_limma( object, formula = ~subgroup, block = 'Subject' ) fit_lme( object, formula = ~subgroup, block = 'Subject' ) fit_lmer( object, formula = ~subgroup, block = 'Subject' ) # fit_lme( object, formula = ~subgroup, block = ~1|Subject) # needs fine-tuning # fit_lmer( object, formula = ~subgroup + (1|Subject)) # needs fine-tuningfile <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fit_lm( object, formula = ~subgroup) fit_limma( object, formula = ~subgroup) fit_limma( object, formula = ~subgroup, block = 'Subject' ) fit_lme( object, formula = ~subgroup, block = 'Subject' ) fit_lmer( object, formula = ~subgroup, block = 'Subject' ) # fit_lme( object, formula = ~subgroup, block = ~1|Subject) # needs fine-tuning # fit_lmer( object, formula = ~subgroup + (1|Subject)) # needs fine-tuning
Fit/Plot survival
fit_survival( object, assay = assayNames(object)[1], percentile = 25, sep = FITSEP, samples = if (ncol(object) < 50) TRUE else FALSE, verbose = TRUE ) .plot_survival( object, assay = assayNames(object)[1], percentile = 25, title = paste0(assay, " ", percentile, "%"), subtitle = NULL, palette = c("#009999", "#ff5050") ) plot_survival( object, assay = assayNames(object)[1], percentile = percentiles(object), title = paste0(assay, " ", percentile, "%"), subtitle = NULL, palette = c("#009999", "#ff5050"), n = 4, ncol = 4, nrow = length(percentile), file = NULL, width = 7 * ncol, height = 7 * nrow )fit_survival( object, assay = assayNames(object)[1], percentile = 25, sep = FITSEP, samples = if (ncol(object) < 50) TRUE else FALSE, verbose = TRUE ) .plot_survival( object, assay = assayNames(object)[1], percentile = 25, title = paste0(assay, " ", percentile, "%"), subtitle = NULL, palette = c("#009999", "#ff5050") ) plot_survival( object, assay = assayNames(object)[1], percentile = percentiles(object), title = paste0(assay, " ", percentile, "%"), subtitle = NULL, palette = c("#009999", "#ff5050"), n = 4, ncol = 4, nrow = length(percentile), file = NULL, width = 7 * ncol, height = 7 * nrow )
object |
SummarizedExperiment |
assay |
string |
percentile |
percentage (not greater than 50) |
sep |
fvar string separator : e.g. '~' gives p~surv~LR50 |
samples |
TRUE or FALSE : record which samples in which stratum ? |
verbose |
TRUE or FALSE |
title |
string |
subtitle |
string |
palette |
color vector |
n |
number |
ncol |
number |
nrow |
number |
file |
filepath |
width |
number |
height |
number |
ggsurvplot
file <- download_tcga_example() if (!is.null(file) & requireNamespace('survminer')){ # Read object <- readRDS(file) object %<>% extract(, .$sample_type == 'T') object %<>% extract(c('UGT3A2', 'NSUN3', 'XRCC4', 'WNT10A'), ) # Fit fdt(object) fdt(fit_survival(object)) fdt(fit_survival(object, percentile = 50)) fdt(fit_survival(object, percentile = 50, sep = '.')) # Plot object %<>% fit_survival() plot_survival(object) p1 <- .plot_survival(object[1, ]) p2 <- .plot_survival(object[2, ]) }file <- download_tcga_example() if (!is.null(file) & requireNamespace('survminer')){ # Read object <- readRDS(file) object %<>% extract(, .$sample_type == 'T') object %<>% extract(c('UGT3A2', 'NSUN3', 'XRCC4', 'WNT10A'), ) # Fit fdt(object) fdt(fit_survival(object)) fdt(fit_survival(object, percentile = 50)) fdt(fit_survival(object, percentile = 50, sep = '.')) # Plot object %<>% fit_survival() plot_survival(object) p1 <- .plot_survival(object[1, ]) p2 <- .plot_survival(object[2, ]) }
fitcoefs
fitcoefs(object)fitcoefs(object)
object |
SummarizedExperiment |
string vector
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fitcoefs(object) fitcoefs(fit_limma(object))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fitcoefs(object) fitcoefs(fit_limma(object))
Get fit models
fits(object, ...) ## S3 method for class 'data.table' fits(object, ...) ## S3 method for class 'SummarizedExperiment' fits(object, ...)fits(object, ...) ## S3 method for class 'data.table' fits(object, ...) ## S3 method for class 'SummarizedExperiment' fits(object, ...)
object |
SummarizedExperiment or data.table |
... |
S3 dispatch |
character vector
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') fits(object)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') fits(object)
Fit results separator
FITSEP PPATTERNFITSEP PPATTERN
An object of class character of length 1.
An object of class character of length 1.
FITSEPFITSEP
Get fit vars/dt
fitvars(object) fitdt(object)fitvars(object) fitdt(object)
object |
SummarizedExperimenmt |
string vector
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fitvars(object) fitdt(object) fitvars(fit_limma(object)) fitdt(fit_limma(object))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) fitvars(object) fitdt(object) fitvars(fit_limma(object)) fitdt(fit_limma(object))
Fix excel genes
fix_xlgenes(x)fix_xlgenes(x)
x |
character |
character
x <- c('FAM46B', '15-Sep', '2-Mar', 'MARCHF6') x fix_xlgenes(x)x <- c('FAM46B', '15-Sep', '2-Mar', 'MARCHF6') x fix_xlgenes(x)
Get fvar levels
flevels(object, fvar)flevels(object, fvar)
object |
SummarizedExperiment |
fvar |
feature variable |
fvar values
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(flevels(object, 'feature_id'))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(flevels(object, 'feature_id'))
Get/Set feature names
fnames(object) ## S4 method for signature 'SummarizedExperiment' fnames(object) fnames(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' fnames(object) <- valuefnames(object) ## S4 method for signature 'SummarizedExperiment' fnames(object) fnames(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' fnames(object) <- value
object |
SummarizedExperiment, eSet, or EList |
value |
character vector with feature names |
feature name vector (get) or updated object (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fnames(object) %<>% paste0('protein_', .) objectfile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fnames(object) %<>% paste0('protein_', .) object
formula to string
formula2str(formula)formula2str(formula)
formula |
formula |
string
formula2str(~0+subgroup)formula2str(~0+subgroup)
Feature type
ftype( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), fit = fits(object)[1], codingfun = contr.treatment.explicit )ftype( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), fit = fits(object)[1], codingfun = contr.treatment.explicit )
object |
SummarizedExperiment |
formula |
model formula |
drop |
TRUE or FALSE |
fit |
'limma', 'lm', 'lme', 'wilcoxon' |
codingfun |
coding function |
SummarizedExperiment
file <- download_data('atkin.metabolon.xlsx') object <- read_metabolon(file) object %<>% fit_limma(block = 'Subject') object %<>% ftype() fdt(object)file <- download_data('atkin.metabolon.xlsx') object <- read_metabolon(file) object %<>% fit_limma(block = 'Subject') object %<>% ftype() fdt(object)
Get fvar values
fvalues(object, fvar)fvalues(object, fvar)
object |
SummarizedExperiment |
fvar |
feature variable |
fvar values
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(fvalues(object, 'feature_id')) fvalues(object, NULL)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(fvalues(object, 'feature_id')) fvalues(object, NULL)
Get/Set feature variables
fvars(object) ## S4 method for signature 'SummarizedExperiment' fvars(object) fvars(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' fvars(object) <- valuefvars(object) ## S4 method for signature 'SummarizedExperiment' fvars(object) fvars(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' fvars(object) <- value
object |
SummarizedExperiment |
value |
character vector with feature variables |
feature variables vector (get) or updated object (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fvars(object)[1] %<>% paste0('1') fvars(object)[1]file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fvars(object)[1] %<>% paste0('1') fvars(object)[1]
Get corresponding orgdb
genome_to_orgdb(genome)genome_to_orgdb(genome)
genome |
'hg38', 'hg19', 'mm10', or 'mm9' |
OrgDb
if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ class(genome_to_orgdb('hg38')) }if (requireNamespace('org.Hs.eg.db', quiet = TRUE)){ class(genome_to_orgdb('hg38')) }
group by level
group_by_level(x, ...) ## S3 method for class 'character' group_by_level(x, ...) ## S3 method for class 'factor' group_by_level(x, ...) ## S3 method for class 'data.table' group_by_level(x, var, idvar, ...)group_by_level(x, ...) ## S3 method for class 'character' group_by_level(x, ...) ## S3 method for class 'factor' group_by_level(x, ...) ## S3 method for class 'data.table' group_by_level(x, var, idvar, ...)
x |
named logical/character/factor |
... |
S3 dispatch |
var |
string |
idvar |
string |
unnamed character
t1 <- c( KLF5 = 'up', F11 = 'up', RIG = 'flat', ABT1 = 'down') dt <- data.table( gene = c( 'KL5', 'F11', 'RIG', 'ABT1' ), t1 = c( 'up', 'up', 'flat', 'down' ) ) group_by_level(t1) # character group_by_level(factor(t1)) # factor group_by_level(dt, 't1', 'gene') # data.tablet1 <- c( KLF5 = 'up', F11 = 'up', RIG = 'flat', ABT1 = 'down') dt <- data.table( gene = c( 'KL5', 'F11', 'RIG', 'ABT1' ), t1 = c( 'up', 'up', 'flat', 'down' ) ) group_by_level(t1) # character group_by_level(factor(t1)) # factor group_by_level(dt, 't1', 'gene') # data.table
Guess compound discoverer quantity from snames
guess_compounddiscoverer_quantity(x)guess_compounddiscoverer_quantity(x)
x |
character vector |
string: value from names(COMPOUNDDISCOVERER_PATTERNS)
## Not run: # file file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') guess_compounddiscoverer_quantity(file) ## End(Not run) # character vector x <- "Area: 20230908_F143_HILICNEG.raw (F11)" guess_compounddiscoverer_quantity(x) x <- "Norm. Area: 20230908_F143_HILICNEG.raw (F11)" guess_compounddiscoverer_quantity(x)## Not run: # file file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') guess_compounddiscoverer_quantity(file) ## End(Not run) # character vector x <- "Area: 20230908_F143_HILICNEG.raw (F11)" guess_compounddiscoverer_quantity(x) x <- "Norm. Area: 20230908_F143_HILICNEG.raw (F11)" guess_compounddiscoverer_quantity(x)
guess fitsep
guess_fitsep(object, ...) ## S3 method for class 'data.table' guess_fitsep(object, ...) ## S3 method for class 'SummarizedExperiment' guess_fitsep(object, ...)guess_fitsep(object, ...) ## S3 method for class 'data.table' guess_fitsep(object, ...) ## S3 method for class 'SummarizedExperiment' guess_fitsep(object, ...)
object |
data.table or SummarizedExperiment |
... |
S3 dispatch |
string
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% fit_limma() guess_fitsep(object)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% fit_limma() guess_fitsep(object)
Guess maxquant quantity from snames
guess_maxquant_quantity(x)guess_maxquant_quantity(x)
x |
character vector |
string: value from names(MAXQUANT_PATTERNS)
# file file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') guess_maxquant_quantity(file) # character vector x <- "Ratio M/L normalized STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x) x <- "Ratio M/L STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x) x <- "LFQ intensity E00.R1" guess_maxquant_quantity(x) x <- "Reporter intensity corrected 0 STD(0)E00(1)E01(2)_R1" guess_maxquant_quantity(x) x <- "Reporter intensity 0 STD(0)E00(1)E01(2)_R1" guess_maxquant_quantity(x) x <- "Intensity H STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x)# file file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') guess_maxquant_quantity(file) # character vector x <- "Ratio M/L normalized STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x) x <- "Ratio M/L STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x) x <- "LFQ intensity E00.R1" guess_maxquant_quantity(x) x <- "Reporter intensity corrected 0 STD(0)E00(1)E01(2)_R1" guess_maxquant_quantity(x) x <- "Reporter intensity 0 STD(0)E00(1)E01(2)_R1" guess_maxquant_quantity(x) x <- "Intensity H STD(L)_E00(M)_E01(H)_R1" guess_maxquant_quantity(x)
Guess separator
guess_sep(x, ...) ## S3 method for class 'numeric' guess_sep(x, ...) ## S3 method for class 'character' guess_sep(x, separators = c(".", "_"), verbose = FALSE, ...) ## S3 method for class 'factor' guess_sep(x, ...) ## S3 method for class 'SummarizedExperiment' guess_sep(x, var = "sample_id", separators = c(".", "_"), verbose = FALSE, ...)guess_sep(x, ...) ## S3 method for class 'numeric' guess_sep(x, ...) ## S3 method for class 'character' guess_sep(x, separators = c(".", "_"), verbose = FALSE, ...) ## S3 method for class 'factor' guess_sep(x, ...) ## S3 method for class 'SummarizedExperiment' guess_sep(x, var = "sample_id", separators = c(".", "_"), verbose = FALSE, ...)
x |
character vector or SummarizedExperiment |
... |
used for proper S3 method dispatch |
separators |
character vector: possible separators to look for |
verbose |
TRUE or FALSE |
var |
svar or fvar |
separator (string) or NULL (if no separator could be identified)
# charactervector guess_sep(c('PERM_NON.R1[H/L]', 'PERM_NON.R2[H/L]')) guess_sep(c('WT_untreated_1', 'WT_untreated_2')) guess_sep(c('group1', 'group2.R1')) # SummarizedExperiment file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) guess_sep(object)# charactervector guess_sep(c('PERM_NON.R1[H/L]', 'PERM_NON.R2[H/L]')) guess_sep(c('WT_untreated_1', 'WT_untreated_2')) guess_sep(c('group1', 'group2.R1')) # SummarizedExperiment file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) guess_sep(object)
Variable has multiple levels?
has_multiple_levels(x, ...) ## S3 method for class 'character' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'factor' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'numeric' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'data.table' has_multiple_levels( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y), ... ) ## S3 method for class 'SummarizedExperiment' has_multiple_levels( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y), ... )has_multiple_levels(x, ...) ## S3 method for class 'character' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'factor' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'numeric' has_multiple_levels(x, .xname = get_name_in_parent(x), ...) ## S3 method for class 'data.table' has_multiple_levels( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y), ... ) ## S3 method for class 'SummarizedExperiment' has_multiple_levels( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y), ... )
x |
vector, data.table or SummarizedExperiment |
... |
required for s3 dispatch |
.xname |
string |
y |
string |
.yname |
string |
TRUE or false
# numeric a <- numeric(); has_multiple_levels(a) a <- c(1, 1); has_multiple_levels(a) a <- c(1, 2); has_multiple_levels(a) # character a <- character(); has_multiple_levels(a) a <- c('A', 'A'); has_multiple_levels(a) a <- c('A', 'B'); has_multiple_levels(a) # factor a <- factor(); has_multiple_levels(a) a <- factor(c('A', 'A')); has_multiple_levels(a) a <- factor(c('A', 'B')); has_multiple_levels(a) # data.table dt <- data.table(a = factor()); has_multiple_levels(dt, 'b') dt <- data.table(a = factor()); has_multiple_levels(dt, 'a') dt <- data.table(a = factor()); has_multiple_levels(dt, 'a') dt <- data.table(a = factor(c('A', 'A'))); has_multiple_levels(dt, 'a') dt <- data.table(a = factor(c('A', 'B'))); has_multiple_levels(dt, 'a') # sumexp object <- matrix(1:9, nrow = 3) rownames(object) <- sprintf('f%d', 1:3) colnames(object) <- sprintf('s%d', 1:3) object <- list(exprs = object) object %<>% SummarizedExperiment::SummarizedExperiment() object$subgroup <- c('A', 'A', 'A'); has_multiple_levels(object, 'group') object$subgroup <- c('A', 'A', 'A'); has_multiple_levels(object, 'subgroup') object$subgroup <- c('A', 'B', 'A'); has_multiple_levels(object, 'subgroup')# numeric a <- numeric(); has_multiple_levels(a) a <- c(1, 1); has_multiple_levels(a) a <- c(1, 2); has_multiple_levels(a) # character a <- character(); has_multiple_levels(a) a <- c('A', 'A'); has_multiple_levels(a) a <- c('A', 'B'); has_multiple_levels(a) # factor a <- factor(); has_multiple_levels(a) a <- factor(c('A', 'A')); has_multiple_levels(a) a <- factor(c('A', 'B')); has_multiple_levels(a) # data.table dt <- data.table(a = factor()); has_multiple_levels(dt, 'b') dt <- data.table(a = factor()); has_multiple_levels(dt, 'a') dt <- data.table(a = factor()); has_multiple_levels(dt, 'a') dt <- data.table(a = factor(c('A', 'A'))); has_multiple_levels(dt, 'a') dt <- data.table(a = factor(c('A', 'B'))); has_multiple_levels(dt, 'a') # sumexp object <- matrix(1:9, nrow = 3) rownames(object) <- sprintf('f%d', 1:3) colnames(object) <- sprintf('s%d', 1:3) object <- list(exprs = object) object %<>% SummarizedExperiment::SummarizedExperiment() object$subgroup <- c('A', 'A', 'A'); has_multiple_levels(object, 'group') object$subgroup <- c('A', 'A', 'A'); has_multiple_levels(object, 'subgroup') object$subgroup <- c('A', 'B', 'A'); has_multiple_levels(object, 'subgroup')
hdl proteomewatch proteins
hdlproteins()hdlproteins()
string vector: HDLProteomeWatch protein entries
hdlproteins()hdlproteins()
Impute NA values
impute(object, ...) ## S3 method for class 'numeric' impute(object, shift = 2.5, width = 0.3, verbose = TRUE, plot = FALSE, ...) ## S3 method for class 'matrix' impute( object, shift = 2.5, width = 0.3, verbose = TRUE, plot = FALSE, n = min(9, ncol(object)), palette = make_colors(colnames(object)), ... ) ## S3 method for class 'SummarizedExperiment' impute( object, assay = assayNames(object)[1], by = "subgroup", shift = 2.5, width = 0.3, frac = 0.5, verbose = TRUE, plot = FALSE, palette = make_colors(colnames(object)), n = min(9, ncol(object)), ... )impute(object, ...) ## S3 method for class 'numeric' impute(object, shift = 2.5, width = 0.3, verbose = TRUE, plot = FALSE, ...) ## S3 method for class 'matrix' impute( object, shift = 2.5, width = 0.3, verbose = TRUE, plot = FALSE, n = min(9, ncol(object)), palette = make_colors(colnames(object)), ... ) ## S3 method for class 'SummarizedExperiment' impute( object, assay = assayNames(object)[1], by = "subgroup", shift = 2.5, width = 0.3, frac = 0.5, verbose = TRUE, plot = FALSE, palette = make_colors(colnames(object)), n = min(9, ncol(object)), ... )
object |
numeric vector, SumExp |
... |
required for s3 dispatch |
shift |
number: sd units |
width |
number: sd units |
verbose |
TRUE or FALSE |
plot |
TRUE or FALSE |
n |
number of samples to plot |
palette |
color vector |
assay |
string |
by |
svar |
frac |
fraction: fraction of available samples should be greater than this value for a subgroup to be called available |
Imputes NA values from N(mean - 2.5 sd, 0.3 sd)
numeric vector, matrix or SumExp
# Simple Design file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) impute(values(object)[, 1], plot = TRUE)[1:3] # vector impute(values(object), plot = TRUE)[1:3, 1:3] # matrix impute(object, plot = TRUE) # sumexp # Complex Design subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, subgroups = subgroups) impute(values(object)[1:3, 1 ]) # vector impute(values(object)[1:3, 1:5 ]) # matrix impute( object ) # sumexp# Simple Design file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) impute(values(object)[, 1], plot = TRUE)[1:3] # vector impute(values(object), plot = TRUE)[1:3, 1:3] # matrix impute(object, plot = TRUE) # sumexp # Complex Design subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, subgroups = subgroups) impute(values(object)[1:3, 1 ]) # vector impute(values(object)[1:3, 1:5 ]) # matrix impute( object ) # sumexp
Invert expressions , subgroups, and sample ids
invert_subgroups( object, subgroups = slevels(object, "subgroup"), sep = guess_sep(object, "subgroup") )invert_subgroups( object, subgroups = slevels(object, "subgroup"), sep = guess_sep(object, "subgroup") )
object |
SummarizedExperiment |
subgroups |
character vector: subgroup levels to be inversed |
sep |
string: collapsed string separator |
character vector or SummarizedExperiment
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) invert_subgroups(object)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) invert_subgroups(object)
Is collapsed subset
is_collapsed_subset(x, y, sep = ";")is_collapsed_subset(x, y, sep = ";")
x |
character vector |
y |
character vector |
sep |
string |
character vector
x <- c( 'H3BNX8;H3BRM5', 'G5E9Y3') y <- c('P20674;H3BNX8;H3BV69;H3BRM5', 'G5E9Y3;Q8WWN8;B4DIT1') is_collapsed_subset(x, y)x <- c( 'H3BNX8;H3BRM5', 'G5E9Y3') y <- c('P20674;H3BNX8;H3BV69;H3BRM5', 'G5E9Y3;Q8WWN8;B4DIT1') is_collapsed_subset(x, y)
Assert correlation matrix
is_correlation_matrix( x, .xname = get_name_in_parent(x), severity = getOption("assertive.severity", "stop") ) assert_correlation_matrix(x, .xname = get_name_in_parent(x))is_correlation_matrix( x, .xname = get_name_in_parent(x), severity = getOption("assertive.severity", "stop") ) assert_correlation_matrix(x, .xname = get_name_in_parent(x))
x |
correlation matrix |
.xname |
string |
severity |
'warning' or 'stop' |
TRUE or false
x <- matrix(c(1,0.7, 0.3, 1), nrow = 2) rownames(x) <- c('gene1', 'gene2') colnames(x) <- c('gene1', 'gene2') is_correlation_matrix(x) is_correlation_matrix({x[1,1] <- -2; x})x <- matrix(c(1,0.7, 0.3, 1), nrow = 2) rownames(x) <- c('gene1', 'gene2') colnames(x) <- c('gene1', 'gene2') is_correlation_matrix(x) is_correlation_matrix({x[1,1] <- -2; x})
Is diann, fragpipe, proteingroups, phosphosites file?
is_diann_report(x, .xname = get_name_in_parent(x)) is_fragpipe_tsv(x, .xname = get_name_in_parent(x)) is_maxquant_proteingroups(x, .xname = get_name_in_parent(x)) is_maxquant_phosphosites(x, .xname = get_name_in_parent(x)) is_compounddiscoverer_output(x, .xname = get_name_in_parent(x)) assert_diann_report(x, .xname = get_name_in_parent(x)) assert_fragpipe_tsv(x, .xname = get_name_in_parent(x)) assert_maxquant_proteingroups(x, .xname = get_name_in_parent(x)) assert_maxquant_phosphosites(x, .xname = get_name_in_parent(x)) assert_compounddiscoverer_output(x, .xname = get_name_in_parent(x))is_diann_report(x, .xname = get_name_in_parent(x)) is_fragpipe_tsv(x, .xname = get_name_in_parent(x)) is_maxquant_proteingroups(x, .xname = get_name_in_parent(x)) is_maxquant_phosphosites(x, .xname = get_name_in_parent(x)) is_compounddiscoverer_output(x, .xname = get_name_in_parent(x)) assert_diann_report(x, .xname = get_name_in_parent(x)) assert_fragpipe_tsv(x, .xname = get_name_in_parent(x)) assert_maxquant_proteingroups(x, .xname = get_name_in_parent(x)) assert_maxquant_phosphosites(x, .xname = get_name_in_parent(x)) assert_compounddiscoverer_output(x, .xname = get_name_in_parent(x))
x |
file |
.xname |
name of x |
file <- NULL is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- 3 is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- 'blabla.tsv' is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- download_data('multiorganism.combined_protein.tsv') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- download_data('dilution.report.tsv') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file)file <- NULL is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- 3 is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- 'blabla.tsv' is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- download_data('multiorganism.combined_protein.tsv') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- download_data('dilution.report.tsv') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file) file <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') is_diann_report(file) is_fragpipe_tsv(file) is_maxquant_proteingroups(file) is_maxquant_phosphosites(file)
Is fastadt
is_fastadt(x, .xname = get_name_in_parent(x)) assert_fastadt(x, .xname = get_name_in_parent(x))is_fastadt(x, .xname = get_name_in_parent(x)) assert_fastadt(x, .xname = get_name_in_parent(x))
x |
fasta data.table |
.xname |
string |
fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') x <- read_uniprotdt(fastafile) # is_fastadt(x) # slowfastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') x <- read_uniprotdt(fastafile) # is_fastadt(x) # slow
Is a file (and not a dir)
is_file(file)is_file(file)
file |
filepath |
This function distinguishies between dir and file. Others dont: is.file, fs::file_exists, assertive::is_existing_file
dir <- tempdir(); dir.create(dir, showWarnings = FALSE) file <- tempfile(); invisible(file.create(file)) is_file(dir) is_file(file)dir <- tempdir(); dir.create(dir, showWarnings = FALSE) file <- tempfile(); invisible(file.create(file)) is_file(dir) is_file(file)
Is fraction
is_fraction(x, .xname = get_name_in_parent(x)) assert_is_fraction(x, .xname = get_name_in_parent(x))is_fraction(x, .xname = get_name_in_parent(x)) assert_is_fraction(x, .xname = get_name_in_parent(x))
x |
number |
.xname |
string |
TRUE or false
is_fraction(0.1) # YES is_fraction(1) # YES is_fraction(1.2) # NO - more than 1 is_fraction(c(0.1, 0.2)) # NO - vectoris_fraction(0.1) # YES is_fraction(1) # YES is_fraction(1.2) # NO - more than 1 is_fraction(c(0.1, 0.2)) # NO - vector
Get/Set is_imputed
is_imputed(object) ## S4 method for signature 'SummarizedExperiment' is_imputed(object) is_imputed(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' is_imputed(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' is_imputed(object) <- valueis_imputed(object) ## S4 method for signature 'SummarizedExperiment' is_imputed(object) is_imputed(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' is_imputed(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' is_imputed(object) <- value
object |
SummarizedExperiment |
value |
matrix |
matrix (get) or updated object (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE) sum(is_imputed(object))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE) sum(is_imputed(object))
Is positive number
is_positive_number(x, .xname = get_name_in_parent(x)) assert_positive_number(x, .xname = get_name_in_parent(x)) is_weakly_positive_number(x, .xname = get_name_in_parent(x)) assert_weakly_positive_number(x, .xname = get_name_in_parent(x))is_positive_number(x, .xname = get_name_in_parent(x)) assert_positive_number(x, .xname = get_name_in_parent(x)) is_weakly_positive_number(x, .xname = get_name_in_parent(x)) assert_weakly_positive_number(x, .xname = get_name_in_parent(x))
x |
number |
.xname |
name of x |
TRUE or false
is_positive_number( 3) is_positive_number(-3) is_positive_number( 0) is_weakly_positive_number(0) assert_positive_number(3)is_positive_number( 3) is_positive_number(-3) is_positive_number( 0) is_weakly_positive_number(0) assert_positive_number(3)
Is scalar subset
is_scalar_subset( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) ) assert_scalar_subset( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) )is_scalar_subset( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) ) assert_scalar_subset( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) )
x |
scalar |
y |
SummarizedExperiment |
.xname |
name of x |
.yname |
name of y |
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) is_scalar_subset('subgroup', svars(object)) is_scalar_subset('subject', svars(object)) assert_scalar_subset('subgroup', svars(object))file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) is_scalar_subset('subgroup', svars(object)) is_scalar_subset('subject', svars(object)) assert_scalar_subset('subgroup', svars(object))
Is significant?
is_sig( object, fit = fits(object)[1], contrast = coefs(object), quantity = "fdr" )is_sig( object, fit = fits(object)[1], contrast = coefs(object), quantity = "fdr" )
object |
SummarizedExperiment |
fit |
subset of autonomics::TESTS |
contrast |
subset of colnames(metadata(object)[[fit]]) |
quantity |
value in dimnames(metadata(object)[[fit]])[3] |
matrix: -1 (downregulated), +1 (upregulatd), 0 (not fdr significant)
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% fit_lm() object %<>% fit_limma() issig <- is_sig(object, fit = c('lm','limma'), contrast = 'Adult-X30dpt') plot_contrast_venn(issig)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% fit_lm() object %<>% fit_limma() issig <- is_sig(object, fit = c('lm','limma'), contrast = 'Adult-X30dpt') plot_contrast_venn(issig)
Is valid formula
is_valid_formula( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) ) assert_valid_formula( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) )is_valid_formula( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) ) assert_valid_formula( x, y, .xname = get_name_in_parent(x), .yname = get_name_in_parent(y) )
x |
formula |
y |
SummarizedExperiment |
.xname |
string |
.yname |
string |
TRUE or false
object <- matrix(1:9, nrow = 3) rownames(object) <- sprintf('f%d', 1:3) colnames(object) <- sprintf('s%d', 1:3) object <- list(exprs = object) object %<>% SummarizedExperiment::SummarizedExperiment() object$group <- 'group0' object$subgroup <- c('A', 'B', 'C') svars(object) is_valid_formula( 'condition', object) # not formula is_valid_formula( ~condition, object) # not svar is_valid_formula( ~group, object) # not multilevel is_valid_formula( ~subgroup, object) # TRUE is_valid_formula( ~0+subgroup, object) # TRUE is_valid_formula( ~1, object) # TRUE assert_valid_formula( ~subgroup, object)object <- matrix(1:9, nrow = 3) rownames(object) <- sprintf('f%d', 1:3) colnames(object) <- sprintf('s%d', 1:3) object <- list(exprs = object) object %<>% SummarizedExperiment::SummarizedExperiment() object$group <- 'group0' object$subgroup <- c('A', 'B', 'C') svars(object) is_valid_formula( 'condition', object) # not formula is_valid_formula( ~condition, object) # not svar is_valid_formula( ~group, object) # not multilevel is_valid_formula( ~subgroup, object) # TRUE is_valid_formula( ~0+subgroup, object) # TRUE is_valid_formula( ~1, object) # TRUE assert_valid_formula( ~subgroup, object)
Keep fully connected blocks
keep_connected_blocks(object, block, verbose = TRUE)keep_connected_blocks(object, block, verbose = TRUE)
object |
SummarizedExperiment |
block |
svar |
verbose |
TRUE or FALSE |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_connected_blocks( block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_connected_blocks( block = 'Subject')
Keep features with n+ connected blocks
keep_connected_features(object, block, n = 2, verbose = TRUE)keep_connected_features(object, block, n = 2, verbose = TRUE)
object |
SummarizedExperiment |
block |
svar |
n |
number |
verbose |
TRUE or FALSE |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_connected_blocks( block = 'Subject') object %<>% keep_connected_features(block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_connected_blocks( block = 'Subject') object %<>% keep_connected_features(block = 'Subject')
Keep features replicated for each slevel
keep_replicated_features(object, formula = ~1, n = 3, verbose = TRUE)keep_replicated_features(object, formula = ~1, n = 3, verbose = TRUE)
object |
SummarizedExperiment |
formula |
formula |
n |
min replications required |
verbose |
TRUE or FALSE |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_replicated_features() object %<>% keep_replicated_features(~ subgroup)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% keep_replicated_features() object %<>% keep_replicated_features(~ subgroup)
Convert labels into indices
label2index(x)label2index(x)
x |
'character' |
label2index(x = 'Reporter intensity 0 WT(0).KD(1).OE(2).R1') label2index(x = 'Reporter intensity 1 WT(1).KD(2).OE(3).R1') label2index(x = 'Reporter intensity 0 WT(126).KD(127).OE(128).R1') label2index(x = 'Reporter intensity 1 WT(126).KD(127).OE(128).R1') label2index(x = 'Reporter intensity 1 Mix1')label2index(x = 'Reporter intensity 0 WT(0).KD(1).OE(2).R1') label2index(x = 'Reporter intensity 1 WT(1).KD(2).OE(3).R1') label2index(x = 'Reporter intensity 0 WT(126).KD(127).OE(128).R1') label2index(x = 'Reporter intensity 1 WT(126).KD(127).OE(128).R1') label2index(x = 'Reporter intensity 1 Mix1')
Linear Modeling Engines
LINMOD_ENGINESLINMOD_ENGINES
An object of class character of length 5.
LINMOD_ENGINESLINMOD_ENGINES
list.files for programming
list_files(dir, full.names)list_files(dir, full.names)
dir |
directory |
full.names |
TRUE or FALSE |
Adds a small layer on list.files. Returning NULL rather than character(0) when no files. Making it better suited for programming.
list to matrix
list2mat(x)list2mat(x)
x |
list |
matrix
x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) list2mat(x)x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) list2mat(x)
Get / Set log2counts matrix
log2counts(object) ## S4 method for signature 'SummarizedExperiment' log2counts(object) log2counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2counts(object) <- valuelog2counts(object) ## S4 method for signature 'SummarizedExperiment' log2counts(object) log2counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2counts(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2counts(object) <- value
object |
SummarizedExperiment |
value |
log2count matrix (features x samples) |
log2count matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2counts(object)[1:3, 1:3] log2counts(object) <- values(object)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2counts(object)[1:3, 1:3] log2counts(object) <- values(object)
Get / Set log2cpm matrix
log2cpm(object) ## S4 method for signature 'SummarizedExperiment' log2cpm(object) log2cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2cpm(object) <- valuelog2cpm(object) ## S4 method for signature 'SummarizedExperiment' log2cpm(object) log2cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2cpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2cpm(object) <- value
object |
SummarizedExperiment |
value |
log2cpm matrix (features x samples) |
log2cpm matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2cpm(object)[1:3, 1:3] log2cpm(object) <- values(object)file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2cpm(object)[1:3, 1:3] log2cpm(object) <- values(object)
Get/Set log2diffs
log2diffs(object) ## S4 method for signature 'SummarizedExperiment' log2diffs(object) log2diffs(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2diffs(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2diffs(object) <- valuelog2diffs(object) ## S4 method for signature 'SummarizedExperiment' log2diffs(object) log2diffs(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2diffs(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2diffs(object) <- value
object |
SummarizedExperiment |
value |
occupancy matrix (features x samples) |
occpuancy matrix (get) or updated object (set)
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2diffs(object)[1:3, 1:3]file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2diffs(object)[1:3, 1:3]
Get/Set log2proteins
log2proteins(object) ## S4 method for signature 'SummarizedExperiment' log2proteins(object) log2proteins(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2proteins(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2proteins(object) <- valuelog2proteins(object) ## S4 method for signature 'SummarizedExperiment' log2proteins(object) log2proteins(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2proteins(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2proteins(object) <- value
object |
SummarizedExperiment |
value |
occupancy matrix (features x samples) |
occpuancy matrix (get) or updated object (set)
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2proteins(object)[1:3, 1:3]file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2proteins(object)[1:3, 1:3]
Get/Set log2sites
log2sites(object) ## S4 method for signature 'SummarizedExperiment' log2sites(object) log2sites(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2sites(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2sites(object) <- valuelog2sites(object) ## S4 method for signature 'SummarizedExperiment' log2sites(object) log2sites(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2sites(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2sites(object) <- value
object |
SummarizedExperiment |
value |
occupancy matrix (features x samples) |
occpuancy matrix (get) or updated object (set)
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2sites(object)[1:3, 1:3]file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) log2sites(object)[1:3, 1:3]
Get / Set log2tpm matrix
log2tpm(object) ## S4 method for signature 'SummarizedExperiment' log2tpm(object) log2tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2tpm(object) <- valuelog2tpm(object) ## S4 method for signature 'SummarizedExperiment' log2tpm(object) log2tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' log2tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' log2tpm(object) <- value
object |
SummarizedExperiment |
value |
log2tpm matrix (features x samples) |
log2tpm matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2tpm(object) <- values(object) log2tpm(object)[1:3, 1:3]file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) log2tpm(object) <- values(object) log2tpm(object)[1:3, 1:3]
Transform values
log2transform( object, assay = assayNames(object)[1], pseudo = 0, verbose = FALSE ) exp2(object, verbose = FALSE) zscore(object, verbose = FALSE) sscale(mat, verbose = FALSE) fscale(mat, verbose = FALSE) quantnorm(object, verbose = FALSE) invnorm(object, verbose = FALSE) vsn(object, verbose = FALSE, delog = TRUE)log2transform( object, assay = assayNames(object)[1], pseudo = 0, verbose = FALSE ) exp2(object, verbose = FALSE) zscore(object, verbose = FALSE) sscale(mat, verbose = FALSE) fscale(mat, verbose = FALSE) quantnorm(object, verbose = FALSE) invnorm(object, verbose = FALSE) vsn(object, verbose = FALSE, delog = TRUE)
object |
SummarizedExperiment |
assay |
character vector : assays for which to perform transformation |
pseudo |
number : pseudo value to be added prior to transformation |
verbose |
TRUE or FALSE : whether to msg |
mat |
matrix |
delog |
TRUE or FALSE (vsn) |
Transformed sumexp
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %>% plot_sample_densities() invnorm(object) %>% plot_sample_densities() object %>% plot_sample_densities() quantnorm(object) %>% plot_sample_densities() object %>% plot_sample_densities() #vsn(object) %>% plot_sample_densities() # dataset too small object %>% plot_sample_densities() zscore(object) %>% plot_sample_densities() object %>% plot_sample_densities() exp2(object) %>% plot_sample_densities() log2transform(exp2(object)) %>% plot_sample_densities()file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %>% plot_sample_densities() invnorm(object) %>% plot_sample_densities() object %>% plot_sample_densities() quantnorm(object) %>% plot_sample_densities() object %>% plot_sample_densities() #vsn(object) %>% plot_sample_densities() # dataset too small object %>% plot_sample_densities() zscore(object) %>% plot_sample_densities() object %>% plot_sample_densities() exp2(object) %>% plot_sample_densities() log2transform(exp2(object)) %>% plot_sample_densities()
logical to factor
logical2factor(x, true = get_name_in_parent(x), false = paste0("not", true)) factor2logical(x)logical2factor(x, true = get_name_in_parent(x), false = paste0("not", true)) factor2logical(x)
x |
logical vector |
true |
string : truelevel |
false |
string : falselevel |
factor
t1up <- c( TRUE, FALSE, TRUE) t1 <- c('flat', 'down', 'up' ) %>% factor(., .) t1up logical2factor(t1up) factor2logical(t1)t1up <- c( TRUE, FALSE, TRUE) t1 <- c('flat', 'down', 'up' ) %>% factor(., .) t1up logical2factor(t1up) factor2logical(t1)
Make alpha palette
make_alpha_palette(object, alpha)make_alpha_palette(object, alpha)
object |
SummarizedExperiment |
alpha |
string |
character vector
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) make_alpha_palette(object, 'Time')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) make_alpha_palette(object, 'Time')
Make colors
make_colors( varlevels, sep = guess_sep(varlevels), show = FALSE, verbose = FALSE )make_colors( varlevels, sep = guess_sep(varlevels), show = FALSE, verbose = FALSE )
varlevels |
character vector |
sep |
string |
show |
TRUE or FALSE: whether to plot |
verbose |
TRUE or FALSE: whether to msg |
make_colors(c('A', 'B', 'C', 'D' ), show = TRUE) make_colors(c('A.1', 'B.1', 'A.2','B.2'), show = TRUE)make_colors(c('A', 'B', 'C', 'D' ), show = TRUE) make_colors(c('A.1', 'B.1', 'A.2','B.2'), show = TRUE)
Create volcano datatable
make_volcano_dt( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit)[1], shape = "imputed", size = NULL, alpha = NULL, label = "feature_id" )make_volcano_dt( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit)[1], shape = "imputed", size = NULL, alpha = NULL, label = "feature_id" )
object |
SummarizedExperiment |
fit |
'limma', 'lme', 'lm', 'wilcoxon' |
coefs |
character vector: coefs for which to plot volcanoes |
shape |
fvar or NULL |
size |
fvar or NULL |
alpha |
fvar or NULL |
label |
fvar or NULL |
data.table
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE, fit = 'limma') make_volcano_dt(object, fit = 'limma', coefs = 'Adult-X30dpt')file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE, fit = 'limma') make_volcano_dt(object, fit = 'limma', coefs = 'Adult-X30dpt')
Map fvalues
map_fvalues(object, fvalues, from = "uniprot", to = "feature_id", sep = ";")map_fvalues(object, fvalues, from = "uniprot", to = "feature_id", sep = ";")
object |
SummarizedExperiment |
fvalues |
uncollapsed string vector |
from |
string (fvar) |
to |
string (svar) |
sep |
collapse separator |
string vector
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) map_fvalues(object, c('Q6DHL5', 'Q6PFS7'), from = 'uniprot', to = 'feature_id', sep = ';')file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) fdt(object) map_fvalues(object, c('Q6DHL5', 'Q6PFS7'), from = 'uniprot', to = 'feature_id', sep = ';')
Convert matrix into SummarizedExperiment
matrix2sumexp(x, verbose = TRUE)matrix2sumexp(x, verbose = TRUE)
x |
matrix |
verbose |
TRUE/FALSE |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x <- values(read_metabolon(file)) object <- matrix2sumexp(x) object %<>% pca() biplot(object, color = 'subgroup')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') x <- values(read_metabolon(file)) object <- matrix2sumexp(x) object %<>% pca() biplot(object, color = 'subgroup')
maxquant quantity patterns
MAXQUANT_PATTERNSMAXQUANT_PATTERNS
An object of class character of length 7.
MAXQUANT_PATTERNSMAXQUANT_PATTERNS
Feature correlations/distances
mdsplot(distmat, title = NULL) fcor(object, verbose = TRUE) scor(object, verbose = TRUE) fdist(object, method = "cor") sdist(object, method = "cor")mdsplot(distmat, title = NULL) fcor(object, verbose = TRUE) scor(object, verbose = TRUE) fdist(object, method = "cor") sdist(object, method = "cor")
distmat |
distance matrix |
title |
NULL or string |
object |
SummarizedExperiment |
verbose |
TRUE or FALSE |
method |
'cor', 'euclidian', etc |
matrix
# Correlations object <- twofactor_sumexp() scor(object) %>% pheatmap::pheatmap() fcor(object) %>% pheatmap::pheatmap() # Distances sdist(object, 'cor') %>% mdsplot('samples: cor') sdist(object, 'euclidian') %>% mdsplot('samples: euclidian') fdist(object, 'cor') %>% mdsplot('features: cor') fdist(object, 'euclidian') %>% mdsplot('features: euclidian')# Correlations object <- twofactor_sumexp() scor(object) %>% pheatmap::pheatmap() fcor(object) %>% pheatmap::pheatmap() # Distances sdist(object, 'cor') %>% mdsplot('samples: cor') sdist(object, 'euclidian') %>% mdsplot('samples: euclidian') fdist(object, 'cor') %>% mdsplot('features: cor') fdist(object, 'euclidian') %>% mdsplot('features: euclidian')
merge compound discoverer files
merge_compounddiscoverer(x, quantity = NULL, verbose = TRUE)merge_compounddiscoverer(x, quantity = NULL, verbose = TRUE)
x |
'list' |
quantity |
''area', 'normalizedarea'' |
verbose |
'TRUE' or 'FALSE' |
'data.table'
Merge sample excel
merge_sample_excel( object, sfile, range = NULL, by.x = "sample_id", by.y = "sample_id" )merge_sample_excel( object, sfile, range = NULL, by.x = "sample_id", by.y = "sample_id" )
object |
SummarizedExperiment |
sfile |
sample file |
range |
string |
by.x |
string |
by.y |
string |
SummarizedExperiment
Merge sample / feature file
merge_sample_file( object, sfile = NULL, by.x = "sample_id", by.y = "sample_id", all.x = TRUE, select = NULL, stringsAsFactors = FALSE, verbose = TRUE ) merge_ffile( object, ffile = NULL, by.x = "feature_id", by.y = "feature_id", all.x = TRUE, select = NULL, stringsAsFactors = FALSE, verbose = TRUE )merge_sample_file( object, sfile = NULL, by.x = "sample_id", by.y = "sample_id", all.x = TRUE, select = NULL, stringsAsFactors = FALSE, verbose = TRUE ) merge_ffile( object, ffile = NULL, by.x = "feature_id", by.y = "feature_id", all.x = TRUE, select = NULL, stringsAsFactors = FALSE, verbose = TRUE )
object |
SummarizedExperiment |
sfile |
string : sample file path |
by.x |
string : object mergevar |
by.y |
string : file mergevvar |
all.x |
TRUE / FALSE : whether to keep samples / feature without annotation |
select |
character : [sf]file columns to select |
stringsAsFactors |
TRUE / FALSE |
verbose |
TRUE / FALSE |
ffile |
string : ffile path |
SummarizedExperiment
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- c('E00','E01', 'E02','E05','E15','E30', 'M00') subgroups %<>% paste0('_STD') object <- read_maxquant_proteingroups(file, subgroups = subgroups) sfile <- paste0(tempdir(),'/', basename(tools::file_path_sans_ext(file))) sfile %<>% paste0('.samples.txt') dt <- data.table(sample_id = object$sample_id, day = split_extract_fixed(object$subgroup, '_', 1)) data.table::fwrite(dt, sfile) sdt(object) sdt(merge_sample_file(object, sfile))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- c('E00','E01', 'E02','E05','E15','E30', 'M00') subgroups %<>% paste0('_STD') object <- read_maxquant_proteingroups(file, subgroups = subgroups) sfile <- paste0(tempdir(),'/', basename(tools::file_path_sans_ext(file))) sfile %<>% paste0('.samples.txt') dt <- data.table(sample_id = object$sample_id, day = split_extract_fixed(object$subgroup, '_', 1)) data.table::fwrite(dt, sfile) sdt(object) sdt(merge_sample_file(object, sfile))
Merge sample/feature dt
merge_sdata( object, dt, by.x = "sample_id", by.y = names(dt)[1], all.x = TRUE, verbose = TRUE ) merge_sdt( object, dt, by.x = "sample_id", by.y = "sample_id", all.x = TRUE, verbose = TRUE ) merge_fdata( object, dt, by.x = "feature_id", by.y = names(dt)[1], all.x = TRUE, verbose = TRUE ) merge_fdt( object, dt, by.x = "feature_id", by.y = "feature_id", all.x = TRUE, verbose = TRUE )merge_sdata( object, dt, by.x = "sample_id", by.y = names(dt)[1], all.x = TRUE, verbose = TRUE ) merge_sdt( object, dt, by.x = "sample_id", by.y = "sample_id", all.x = TRUE, verbose = TRUE ) merge_fdata( object, dt, by.x = "feature_id", by.y = names(dt)[1], all.x = TRUE, verbose = TRUE ) merge_fdt( object, dt, by.x = "feature_id", by.y = "feature_id", all.x = TRUE, verbose = TRUE )
object |
SummarizedExperiment |
dt |
data.frame, data.table, DataFrame |
by.x |
string : object mergevar |
by.y |
string : df mergevar |
all.x |
TRUE / FALSE : whether to keep samples / features without annotation |
verbose |
TRUE / FALSE : whether to msg |
SummarizedExperiment
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) sdt(object) sdt(merge_sdt(object, data.table(sample_id = object$sample_id, number = seq_along(object$sample_id))))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) sdt(object) sdt(merge_sdt(object, data.table(sample_id = object$sample_id, number = seq_along(object$sample_id))))
message dataframe using sprintf syntax. Use place holder '
message_df(format_string, x)message_df(format_string, x)
format_string |
sprintf style format string |
x |
data.frame |
nothing returned
x <- data.frame(feature_id = c('F001', 'F002'), symbol = c('FEAT1', 'FEAT2')) message_df('\t%s', x) x <- c(rep('PASS', 25), rep('FAIL', 25)) message_df(format_string = '%s', table(x))x <- data.frame(feature_id = c('F001', 'F002'), symbol = c('FEAT1', 'FEAT2')) message_df('\t%s', x) x <- c(rep('PASS', 25), rep('FAIL', 25)) message_df(format_string = '%s', table(x))
Get model variable
modelvar(object, ...) ## S3 method for class 'data.table' modelvar( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' modelvar( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) effectvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) tvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) pvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) fdrvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) abstractvar(object, ...) ## S3 method for class 'data.table' abstractvar( object, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' abstractvar( object, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) modelvec(object, ...) ## S3 method for class 'data.table' modelvec( object, quantity, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) ## S3 method for class 'SummarizedExperiment' modelvec( object, quantity, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) effectvec( object, fit = fits(object)[1], coef = default_coefs(object)[1], fvar = "feature_id" ) tvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) pvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) fdrvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) abstractvec(object, ...) ## S3 method for class 'data.table' abstractvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) ## S3 method for class 'SummarizedExperiment' abstractvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) modeldt(object, ...) ## S3 method for class 'data.table' modeldt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' modeldt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) effectdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) tdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) pdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) modelmat( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) modelmat( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) effectmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) effectsizemat( object, fit = fits(object), coef = default_coefs(object, fit = fit) ) tmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) pmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) fdrmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) modelfeatures(object, ...) ## S3 method for class 'data.table' modelfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectdirection = "<>", effectsize = 0, ... ) ## S3 method for class 'SummarizedExperiment' modelfeatures(object, ...) upfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectsize = 0 ) downfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectsize = 0 )modelvar(object, ...) ## S3 method for class 'data.table' modelvar( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' modelvar( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) effectvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) tvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) pvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) fdrvar(object, fit = fits(object), coef = default_coefs(object, fit = fit)) abstractvar(object, ...) ## S3 method for class 'data.table' abstractvar( object, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' abstractvar( object, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) modelvec(object, ...) ## S3 method for class 'data.table' modelvec( object, quantity, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) ## S3 method for class 'SummarizedExperiment' modelvec( object, quantity, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) effectvec( object, fit = fits(object)[1], coef = default_coefs(object)[1], fvar = "feature_id" ) tvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) pvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) fdrvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id" ) abstractvec(object, ...) ## S3 method for class 'data.table' abstractvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) ## S3 method for class 'SummarizedExperiment' abstractvec( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", ... ) modeldt(object, ...) ## S3 method for class 'data.table' modeldt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' modeldt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit), ... ) effectdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) tdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) pdt( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) modelmat( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) modelmat( object, quantity, fit = fits(object), coef = default_coefs(object, fit = fit) ) effectmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) effectsizemat( object, fit = fits(object), coef = default_coefs(object, fit = fit) ) tmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) pmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) fdrmat(object, fit = fits(object), coef = default_coefs(object, fit = fit)) modelfeatures(object, ...) ## S3 method for class 'data.table' modelfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectdirection = "<>", effectsize = 0, ... ) ## S3 method for class 'SummarizedExperiment' modelfeatures(object, ...) upfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectsize = 0 ) downfeatures( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], fvar = "feature_id", significancevar = "p", significance = 0.05, effectsize = 0 )
object |
data.table or SummarizedExperiment |
... |
S3 dispatch |
quantity |
'p', 'effect', 'fdr', 't', or 'se' |
fit |
string (vector) |
coef |
string (vector) |
fvar |
'feature_id' or other fvar for values (pvec) or names (upfeatures) |
significancevar |
'p' or 'fdr' |
significance |
p or fdr cutoff (fractional number) |
effectdirection |
'<>', '<' or '>' |
effectsize |
effectsize cutoff (positive number) |
string (tvar), matrix (tmat), numeric vector (tvec), character vector (tfeatures)
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(statvars = c('effect', 't', 'p')) object %<>% fit_lm( statvars = c('effect', 't', 'p')) effectvar(object) effectvec(object)[1:3] effectdt(object)[1:3, ] effectmat(object)[1:3, ] tvar(object) tvec(object)[1:3] tdt(object)[1:3, ] tmat(object)[1:3, ] pvar(object) pvec(object)[1:3] pdt(object)[1:3, ] pmat(object)[1:3, ] modelfeatures(object) downfeatures(object) upfeatures(object)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(statvars = c('effect', 't', 'p')) object %<>% fit_lm( statvars = c('effect', 't', 'p')) effectvar(object) effectvec(object)[1:3] effectdt(object)[1:3, ] effectmat(object)[1:3, ] tvar(object) tvec(object)[1:3] tdt(object)[1:3, ] tmat(object)[1:3, ] pvar(object) pvec(object)[1:3] pdt(object)[1:3, ] pmat(object)[1:3, ] modelfeatures(object) downfeatures(object) upfeatures(object)
Human/Mouse Msigdb Collections
MSIGCOLLECTIONSHUMAN MSIGCOLLECTIONSMOUSEMSIGCOLLECTIONSHUMAN MSIGCOLLECTIONSMOUSE
An object of class character of length 25.
An object of class character of length 13.
local msigdb dir
MSIGDIRMSIGDIR
An object of class character of length 1.
stri_split and extract
nfactors(x, sep = guess_sep(x)) split_extract_fixed(x, sep, i) split_extract_regex(x, sep, i) split_extract(x, i, sep = guess_sep(x))nfactors(x, sep = guess_sep(x)) split_extract_fixed(x, sep, i) split_extract_regex(x, sep, i) split_extract(x, i, sep = guess_sep(x))
x |
character vector |
sep |
string |
i |
integer |
character vector
# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) x <- object$sample_id[1:5] nfactors(x) # Split split_extract_fixed(x, '.', 1:2) split_extract_fixed(x, '.', seq_len(nfactors(x)-1)) split_extract_fixed(x, '.', nfactors(x)) split_extract_fixed(fdt(object)$PUBCHEM, ';', 1) # with NA values# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) x <- object$sample_id[1:5] nfactors(x) # Split split_extract_fixed(x, '.', 1:2) split_extract_fixed(x, '.', seq_len(nfactors(x)-1)) split_extract_fixed(x, '.', nfactors(x)) split_extract_fixed(fdt(object)$PUBCHEM, ';', 1) # with NA values
opentargets dir
OPENTARGETSDIROPENTARGETSDIR
An object of class character of length 1.
Order on p
order_on_p( object, fit = autonomics::fits(object), coefs = autonomics::coefs(object, fit = fit), combiner = "|", verbose = TRUE ) order_on_effect( object, fit = autonomics::fits(object), coefs = autonomics::coefs(object, fit = fit), combiner = "|", verbose = TRUE )order_on_p( object, fit = autonomics::fits(object), coefs = autonomics::coefs(object, fit = fit), combiner = "|", verbose = TRUE ) order_on_effect( object, fit = autonomics::fits(object), coefs = autonomics::coefs(object, fit = fit), combiner = "|", verbose = TRUE )
object |
SummarizedExperiment |
fit |
string vector: subset of 'fits(object)' |
coefs |
string vector: subset of 'coefs(object)' |
combiner |
'|' or '&' |
verbose |
TRUE or FALSE |
SummarizedExperiment
# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) order_on_p(object) order_on_p(fit_limma(object), coefs = c('t1-t0', 't2-t0', 't3-t0'))# Read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) order_on_p(object) order_on_p(fit_limma(object), coefs = c('t1-t0', 't2-t0', 't3-t0'))
Perform a dimension reduction. Store sample scores, feature loadings, and dimension variances.
pca( object, by = "sample_id", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, center_samples = TRUE, verbose = TRUE, plot = FALSE, ... ) pls( object, by = "subgroup", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = FALSE, plot = FALSE, ... ) sma( object, by = "sample_id", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = TRUE, plot = FALSE, ... ) lda( object, assay = assayNames(object)[1], by = "subgroup", ndim = 2, sep = FITSEP, minvar = 0, verbose = TRUE, plot = FALSE, ... ) spls( object, assay = assayNames(object)[1], by = "subgroup", ndim = 2, sep = FITSEP, minvar = 0, plot = FALSE, ... ) opls( object, by = "subgroup", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = FALSE, plot = FALSE, ... )pca( object, by = "sample_id", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, center_samples = TRUE, verbose = TRUE, plot = FALSE, ... ) pls( object, by = "subgroup", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = FALSE, plot = FALSE, ... ) sma( object, by = "sample_id", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = TRUE, plot = FALSE, ... ) lda( object, assay = assayNames(object)[1], by = "subgroup", ndim = 2, sep = FITSEP, minvar = 0, verbose = TRUE, plot = FALSE, ... ) spls( object, assay = assayNames(object)[1], by = "subgroup", ndim = 2, sep = FITSEP, minvar = 0, plot = FALSE, ... ) opls( object, by = "subgroup", assay = assayNames(object)[1], ndim = 2, sep = FITSEP, minvar = 0, verbose = FALSE, plot = FALSE, ... )
object |
SummarizedExperiment |
by |
svar or NULL |
assay |
string |
ndim |
number |
sep |
string |
minvar |
number |
center_samples |
TRUE/FALSE: center samples prior to pca ? |
verbose |
TRUE/FALSE: message ? |
plot |
TRUE/FALSE: plot ? |
... |
passed to biplot |
SummarizedExperiment
Aditya Bhagwat, Laure Cougnaud (LDA)
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) pca(object, plot = TRUE) # Principal Component Analysis pls(object, plot = TRUE) # Partial Least Squares lda(object, plot = TRUE) # Linear Discriminant Analysis sma(object, plot = TRUE) # Spectral Map Analysis spls(object, plot = TRUE) # Sparse PLS # opls(object, plot = TRUE) # OPLS # outcommented because it produces a file named FALSEfile <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) pca(object, plot = TRUE) # Principal Component Analysis pls(object, plot = TRUE) # Partial Least Squares lda(object, plot = TRUE) # Linear Discriminant Analysis sma(object, plot = TRUE) # Spectral Map Analysis spls(object, plot = TRUE) # Sparse PLS # opls(object, plot = TRUE) # OPLS # outcommented because it produces a file named FALSE
survival percentiles
percentiles(object)percentiles(object)
object |
SummarizedExperiment |
numeric vector
proteingroup to isoforms
pg_to_canonical(x, unique = TRUE) pg_to_isoforms(x, unique = TRUE)pg_to_canonical(x, unique = TRUE) pg_to_isoforms(x, unique = TRUE)
x |
proteingroups string vector |
unique |
whether to remove duplicates |
string vector
(x <- c('Q96JP5;Q96JP5-2', 'Q96JP5', 'Q96JP5-2;P86791')) pg_to_isoforms(x) pg_to_canonical(x) pg_to_isoforms( x, unique = FALSE) pg_to_canonical(x, unique = FALSE) # .pg_to_isoforms(x[1]) # unexported dot functions # .pg_to_canonical(x[1]) # operate on scalars(x <- c('Q96JP5;Q96JP5-2', 'Q96JP5', 'Q96JP5-2;P86791')) pg_to_isoforms(x) pg_to_canonical(x) pg_to_isoforms( x, unique = FALSE) pg_to_canonical(x, unique = FALSE) # .pg_to_isoforms(x[1]) # unexported dot functions # .pg_to_canonical(x[1]) # operate on scalars
Plot contrast venn
plot_contrast_venn(issig, colors = NULL)plot_contrast_venn(issig, colors = NULL)
issig |
matrix(nrow, ncontrast): -1 (down), +1 (up) |
colors |
NULL or colorvector |
nothing returned
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_wilcoxon(~ subgroup, block = 'Subject') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = contr.treatment.explicit) isfdr <- is_sig(object, contrast = 't3-t0', quantity = 'p', fit = fits(object)) plot_contrast_venn(isfdr)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_wilcoxon(~ subgroup, block = 'Subject') object %<>% fit_limma( ~ subgroup, block = 'Subject', codingfun = contr.treatment.explicit) isfdr <- is_sig(object, contrast = 't3-t0', quantity = 'p', fit = fits(object)) plot_contrast_venn(isfdr)
Plot contrastogram
plot_contrastogram( object, subgroupvar, formula = as.formula(paste0("~ 0 +", subgroupvar)), colors = make_colors(slevels(object, subgroupvar), guess_sep(object)), curve = 0.1 )plot_contrastogram( object, subgroupvar, formula = as.formula(paste0("~ 0 +", subgroupvar)), colors = make_colors(slevels(object, subgroupvar), guess_sep(object)), curve = 0.1 )
object |
SummarizedExperiment |
subgroupvar |
subgroup svar |
formula |
formula |
colors |
named color vector (names = subgroups) |
curve |
arrow curvature |
list returned by plotmat
if (requireNamespace('diagram', quietly = TRUE)){ file <- download_data('halama18.metabolon.xlsx') object <- read_metabolon(file) plot_contrastogram(object, subgroupvar = 'subgroup') }if (requireNamespace('diagram', quietly = TRUE)){ file <- download_data('halama18.metabolon.xlsx') object <- read_metabolon(file) plot_contrastogram(object, subgroupvar = 'subgroup') }
Plot data
plot_data( data, geom = geom_point, color = NULL, fill = NULL, linetype = NULL, ..., palette = NULL, fixed = list(), theme = list() )plot_data( data, geom = geom_point, color = NULL, fill = NULL, linetype = NULL, ..., palette = NULL, fixed = list(), theme = list() )
data |
data.frame' |
geom |
geom_point, etc. |
color |
variable mapped to color (symbol) |
fill |
variable mapped to fill (symbol) |
linetype |
variable mapped to linetype (symbol) |
... |
mapped aesthetics |
palette |
color palette (named character vector) |
fixed |
fixed aesthetics (list) |
theme |
list with ggplot theme specifications |
ggplot object
Aditya Bhagwat, Johannes Graumann
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() data <- sdt(object) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, color = subgroup) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, color = NULL) fixed <- list(shape = 15, size = 3) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, fixed = fixed)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() data <- sdt(object) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, color = subgroup) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, color = NULL) fixed <- list(shape = 15, size = 3) plot_data(data, x = `effect~sample_id~pca1`, y = `effect~sample_id~pca2`, fixed = fixed)
Plot sample/feature distributions
plot_densities( object, assay = assayNames(object)[1], group, fill, color = NULL, linetype = NULL, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free_y", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) ) plot_sample_densities( object, assay = assayNames(object)[1], group = "sample_id", fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", color = NULL, linetype = NULL, n = 100, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free_y", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) ) plot_feature_densities( object, assay = assayNames(object)[1], fill = "feature_id", group = fill, color = NULL, linetype = NULL, n = 9, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) )plot_densities( object, assay = assayNames(object)[1], group, fill, color = NULL, linetype = NULL, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free_y", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) ) plot_sample_densities( object, assay = assayNames(object)[1], group = "sample_id", fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", color = NULL, linetype = NULL, n = 100, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free_y", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) ) plot_feature_densities( object, assay = assayNames(object)[1], fill = "feature_id", group = fill, color = NULL, linetype = NULL, n = 9, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, palette = NULL, fixed = list(alpha = 0.8, na.rm = TRUE) )
object |
SummarizedExperiment |
assay |
string |
group |
svar (string) |
fill |
svar (string) |
color |
svar (string) |
linetype |
svar (string) |
facet |
svar (character vector) |
nrow |
number of facet rows |
ncol |
number of facet cols |
dir |
'h' (horizontal) or 'v' (vertical) |
scales |
'free', 'fixed', 'free_y' |
labeller |
e.g. label_value |
palette |
named character vector |
fixed |
fixed aesthetics |
n |
number |
ggplot object
plot_sample_violins,
plot_sample_boxplots
# Data file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% extract(, order(.$subgroup)) # Sample distributions plot_sample_densities(object) plot_sample_violins( object, facet = 'Time') plot_sample_boxplots(object) plot_exprs(object) plot_exprs(object, dim = 'samples', x = 'subgroup', facet = 'Time') # Feature distributions plot_feature_densities(object) plot_feature_violins( object) plot_feature_boxplots( object)# Data file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% extract(, order(.$subgroup)) # Sample distributions plot_sample_densities(object) plot_sample_violins( object, facet = 'Time') plot_sample_boxplots(object) plot_exprs(object) plot_exprs(object, dim = 'samples', x = 'subgroup', facet = 'Time') # Feature distributions plot_feature_densities(object) plot_feature_violins( object) plot_feature_boxplots( object)
Plot model
plot_design(object, codingfun = contr.treatment.explicit)plot_design(object, codingfun = contr.treatment.explicit)
object |
´SummarizedExperiment |
codingfun |
factor coding function
|
ggplot
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- paste0(c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00'), '_STD') object <- read_maxquant_proteingroups(file, subgroups = subgroups) object$subgroup %<>% substr(1,3) plot_design(object)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') subgroups <- paste0(c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00'), '_STD') object <- read_maxquant_proteingroups(file, subgroups = subgroups) object$subgroup %<>% substr(1,3) plot_design(object)
plot_sample_nas shows systematic and random missingness
(white), and full detection (bright color) at sample resolution.
Imputations are also shown (light color).
plot_detections(...) plot_summarized_detections(...) plot_sample_nas( object, by = "subgroup", fill = by, palette = make_svar_palette(object, fill), axis.text.y = element_blank() ) plot_subgroup_nas( object, by = "subgroup", fill = by, palette = NULL, na_imputes = TRUE )plot_detections(...) plot_summarized_detections(...) plot_sample_nas( object, by = "subgroup", fill = by, palette = make_svar_palette(object, fill), axis.text.y = element_blank() ) plot_subgroup_nas( object, by = "subgroup", fill = by, palette = NULL, na_imputes = TRUE )
... |
used to maintain deprecated functions |
object |
SummarizedExperiment |
by |
svar (string) |
fill |
svar (string) |
palette |
color vector (names = levels, values = colors) |
axis.text.y |
passed to ggplot2::theme |
na_imputes |
TRUE or FALSE |
plot_subgroup_nas shows systematic missingness at subgroup resolution.
Random missingness and full detection are shown together (bright color).
Imputations are also shown (light color).
ggplot object
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) plot_sample_nas(object) plot_sample_nas(impute(object)) plot_subgroup_nas(object) plot_subgroup_nas(impute(object)) subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, subgroups = subgroups) plot_subgroup_nas(object) plot_subgroup_nas(object, 'subgroup') plot_sample_nas(object) plot_sample_nas(object, 'subgroup')file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) plot_sample_nas(object) plot_sample_nas(impute(object)) plot_subgroup_nas(object) plot_subgroup_nas(impute(object)) subgroups <- sprintf('%s_STD', c('E00','E01','E02','E05','E15','E30','M00')) file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, subgroups = subgroups) plot_subgroup_nas(object) plot_subgroup_nas(object, 'subgroup') plot_sample_nas(object) plot_sample_nas(object, 'subgroup')
Plot exprs for coef
plot_exprs( object, dim = "both", assay = assayNames(object)[1], fit = fits(object)[1], coefs = default_coefs(object, fit = fit), block = NULL, x = default_x(object, dim), geom = default_geom(object, x = x, block = block), color = x, fill = x, shape = NULL, size = NULL, alpha = NULL, linetype = NULL, highlight = NULL, combiner = "|", p = 1, fdr = 1, facet = if (dim == "both") "feature_id" else NULL, n = 4, ncol = NULL, nrow = NULL, scales = "free_y", labeller = "label_value", pointsize = if (is.null(block)) 0 else 0.5, jitter = if (is.null(block)) 0.1 else 0, fillpalette = make_var_palette(object, fill), colorpalette = make_var_palette(object, color), hlevels = NULL, title = switch(dim, both = x, features = "Feature Boxplots", samples = "Sample Boxplots"), subtitle = if (!is.null(fit)) coefs else "", xlab = NULL, ylab = "value", theme = ggplot2::theme(plot.title = element_text(hjust = 0.5)), file = NULL, width = 7, height = 7, verbose = TRUE ) plot_sample_boxplots( object, fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", n = min(ncol(object), 16), ... ) plot_feature_boxplots(object, ...)plot_exprs( object, dim = "both", assay = assayNames(object)[1], fit = fits(object)[1], coefs = default_coefs(object, fit = fit), block = NULL, x = default_x(object, dim), geom = default_geom(object, x = x, block = block), color = x, fill = x, shape = NULL, size = NULL, alpha = NULL, linetype = NULL, highlight = NULL, combiner = "|", p = 1, fdr = 1, facet = if (dim == "both") "feature_id" else NULL, n = 4, ncol = NULL, nrow = NULL, scales = "free_y", labeller = "label_value", pointsize = if (is.null(block)) 0 else 0.5, jitter = if (is.null(block)) 0.1 else 0, fillpalette = make_var_palette(object, fill), colorpalette = make_var_palette(object, color), hlevels = NULL, title = switch(dim, both = x, features = "Feature Boxplots", samples = "Sample Boxplots"), subtitle = if (!is.null(fit)) coefs else "", xlab = NULL, ylab = "value", theme = ggplot2::theme(plot.title = element_text(hjust = 0.5)), file = NULL, width = 7, height = 7, verbose = TRUE ) plot_sample_boxplots( object, fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", n = min(ncol(object), 16), ... ) plot_feature_boxplots(object, ...)
object |
SummarizedExperiment |
dim |
'samples' (per-sample distribution across features), |
assay |
string: value in assayNames(object) |
fit |
'limma', 'lm', 'lme', 'lmer', 'wilcoxon' |
coefs |
subset of coefs(object) to consider in selecting top |
block |
group svar |
x |
x svar |
geom |
'boxplot' or 'point' |
color |
color svar: points, lines |
fill |
fill svar: boxplots |
shape |
shape svar |
size |
size svar |
alpha |
alpha svar |
linetype |
linetype svar |
highlight |
highlight svar |
combiner |
'&' or '|' |
p |
fraction: p cutoff |
fdr |
fraction: fdr cutoff |
facet |
string: fvar mapped to facet |
n |
number of samples (dim = 'samples') or features (dim = 'features' or 'both') to plot |
ncol |
number of cols in faceted plot (if dim = 'both') |
nrow |
number of rows in faceted plot (if dim = 'both) |
scales |
'free_y', 'free'x', 'fixed' |
labeller |
string or function |
pointsize |
number |
jitter |
jitter width (number) |
fillpalette |
named character vector: fill palette |
colorpalette |
named character vector: color palette |
hlevels |
xlevels for which to plot hlines |
title |
string |
subtitle |
string |
xlab |
string |
ylab |
string |
theme |
ggplot2::theme(...) or NULL |
file |
NULL or filepath |
width |
inches |
height |
inches |
verbose |
TRUE or FALSE |
... |
used to maintain depreceated functions |
ggplot object
plot_sample_densities,
plot_sample_violins
# Without limma file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) plot_exprs(object, block = 'Subject', title = 'Subgroup Boxplots') plot_exprs(object, dim = 'samples') plot_exprs(object, dim = 'features', block = 'sample_id') # With limma object %<>% fit_limma(block = 'Subject') plot_exprs(object, block = 'Subject') plot_exprs(object, block = 'Subject', coefs = c('t1-t0', 't2-t0', 't3-t0')) plot_exprs_per_coef(object, x = 'Time', block = 'Subject') # Points plot_exprs(object, geom = 'point', block = 'Subject') # Add highlights controlfeatures <- c('biotin','phosphate') fdt(object) %<>% cbind(control = .$feature_name %in% controlfeatures) plot_exprs(object, dim = 'samples', highlight = 'control') # Multiple pages plot_exprs(object, block = 'Subject', n = 4, nrow = 1, ncol = 2)# Without limma file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) plot_exprs(object, block = 'Subject', title = 'Subgroup Boxplots') plot_exprs(object, dim = 'samples') plot_exprs(object, dim = 'features', block = 'sample_id') # With limma object %<>% fit_limma(block = 'Subject') plot_exprs(object, block = 'Subject') plot_exprs(object, block = 'Subject', coefs = c('t1-t0', 't2-t0', 't3-t0')) plot_exprs_per_coef(object, x = 'Time', block = 'Subject') # Points plot_exprs(object, geom = 'point', block = 'Subject') # Add highlights controlfeatures <- c('biotin','phosphate') fdt(object) %<>% cbind(control = .$feature_name %in% controlfeatures) plot_exprs(object, dim = 'samples', highlight = 'control') # Multiple pages plot_exprs(object, block = 'Subject', n = 4, nrow = 1, ncol = 2)
Plot exprs per coef
plot_exprs_per_coef( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit), x = default_x(object), block = NULL, geom = default_geom(object, x, block = block), orderbyp = FALSE, title = x, subtitle = default_subtitle(fit, x, coefs), n = 1, nrow = 1, ncol = NULL, theme = ggplot2::theme(legend.position = "bottom", legend.title = element_blank(), plot.title = element_text(hjust = 0.5), plot.subtitle = element_text(hjust = 0.5)) )plot_exprs_per_coef( object, fit = fits(object)[1], coefs = default_coefs(object, fit = fit), x = default_x(object), block = NULL, geom = default_geom(object, x, block = block), orderbyp = FALSE, title = x, subtitle = default_subtitle(fit, x, coefs), n = 1, nrow = 1, ncol = NULL, theme = ggplot2::theme(legend.position = "bottom", legend.title = element_blank(), plot.title = element_text(hjust = 0.5), plot.subtitle = element_text(hjust = 0.5)) )
object |
SummarizedExperiment |
fit |
'limma', 'lm', 'lme', 'lmer', 'wilcoxon' |
coefs |
subset of coefs(object) to consider in selecting top |
x |
x svar |
block |
group svar |
geom |
'boxplot' or 'point' |
orderbyp |
TRUE or FALSE |
title |
string |
subtitle |
string |
n |
number |
nrow |
number of rows in faceted plot |
ncol |
number of cols in faceted plot |
theme |
ggplot2::theme(...) or NULL |
ggplot object
plot_sample_densities,
plot_sample_violins
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% pls(by = 'subgroup') object %<>% pls(by = 'Diabetes') object %<>% pls(by = 'Subject') plot_exprs_per_coef(object) plot_exprs_per_coef(object, orderbyp = TRUE) plot_exprs_per_coef(object, fit = 'pls1', block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% pls(by = 'subgroup') object %<>% pls(by = 'Diabetes') object %<>% pls(by = 'Subject') plot_exprs_per_coef(object) plot_exprs_per_coef(object, orderbyp = TRUE) plot_exprs_per_coef(object, fit = 'pls1', block = 'Subject')
Plot fit summary
plot_fit_summary(sumdt, nrow = NULL, ncol = NULL, order = FALSE)plot_fit_summary(sumdt, nrow = NULL, ncol = NULL, order = FALSE)
sumdt |
data.table |
nrow |
number |
ncol |
number |
order |
TRUE or FALSE |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_lm() object %<>% fit_limma(block = 'Subject') sumdt <- summarize_fit(object, coefs = c('t1-t0', 't2-t0', 't3-t0')) plot_fit_summary(sumdt)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_lm() object %<>% fit_limma(block = 'Subject') sumdt <- summarize_fit(object, coefs = c('t1-t0', 't2-t0', 't3-t0')) plot_fit_summary(sumdt)
Plot heatmap
plot_heatmap( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], effectsize = 0, p = 1, fdr = 0.05, n = 100, assay = assayNames(object)[1], cluster_features = FALSE, cluster_samples = FALSE, flabel = intersect(c("gene", "feature_id"), fvars(object))[1], group = "subgroup", verbose = TRUE )plot_heatmap( object, fit = fits(object)[1], coef = default_coefs(object, fit = fit)[1], effectsize = 0, p = 1, fdr = 0.05, n = 100, assay = assayNames(object)[1], cluster_features = FALSE, cluster_samples = FALSE, flabel = intersect(c("gene", "feature_id"), fvars(object))[1], group = "subgroup", verbose = TRUE )
object |
SummarizedExperiment |
fit |
'limma', 'lm', 'lme(r)', 'wilcoxon' |
coef |
string: one of coefs(object) |
effectsize |
number: effectsize filter |
p |
number: p filter |
fdr |
number: fdr filter |
n |
number: n filter |
assay |
string: one of assayNames(object) |
cluster_features |
TRUE or FALSE |
cluster_samples |
TRUE or FALSE |
flabel |
string: feature label |
group |
sample groupvar |
verbose |
TRUE or FALSE |
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, fit = 'limma') plot_heatmap(object)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, fit = 'limma') plot_heatmap(object)
Plot binary matrix
plot_matrix(mat)plot_matrix(mat)
mat |
matrix |
no return (base R plot)
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) mat <- sdt(object)[, .(replicate, subgroup)] mat$present <- 1 mat %<>% data.table::dcast(replicate ~ subgroup, value.var = 'present', fill = 0) mat %<>% dt2mat() plot_matrix(mat)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) mat <- sdt(object)[, .(replicate, subgroup)] mat$present <- 1 mat %<>% data.table::dcast(replicate ~ subgroup, value.var = 'present', fill = 0) mat %<>% dt2mat() plot_matrix(mat)
Plot features
plot_subgroup_points( object, subgroup = "subgroup", block = NULL, x = subgroup, color = subgroup, group = block, facet = "feature_id", nrow = NULL, scales = "free_y", ..., palette = NULL, fixed = list(na.rm = TRUE), theme = list(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) )plot_subgroup_points( object, subgroup = "subgroup", block = NULL, x = subgroup, color = subgroup, group = block, facet = "feature_id", nrow = NULL, scales = "free_y", ..., palette = NULL, fixed = list(na.rm = TRUE), theme = list(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) )
object |
SummarizedExperiment |
subgroup |
subgroup svar |
block |
block svar |
x |
svar mapped to x |
color |
svar mapped to color |
group |
svar mapped to group |
facet |
svar mapped to facets |
nrow |
number of rows |
scales |
'free_y' etc. |
... |
mapped aesthetics |
palette |
color palette (named character vector) |
fixed |
fixed aesthetics |
theme |
ggplot theme specifications |
ggplot object
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') idx <- order(fdata(object)$`p~t1-t0~limma`)[1:9] object %<>% extract(idx, ) plot_sample_boxplots( object) plot_feature_boxplots( object) plot_sample_boxplots(object, x = 'Time') plot_subgroup_points( object, subgroup = 'Time') plot_subgroup_points( object, subgroup = 'Time', block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') idx <- order(fdata(object)$`p~t1-t0~limma`)[1:9] object %<>% extract(idx, ) plot_sample_boxplots( object) plot_feature_boxplots( object) plot_sample_boxplots(object, x = 'Time') plot_subgroup_points( object, subgroup = 'Time') plot_subgroup_points( object, subgroup = 'Time', block = 'Subject')
Plot summary
plot_summary( object, fit = "limma", formula = default_formula(object), block = NULL, label = "feature_id", palette = make_svar_palette(object, svar = svar) )plot_summary( object, fit = "limma", formula = default_formula(object), block = NULL, label = "feature_id", palette = make_svar_palette(object, svar = svar) )
object |
SummarizedExperiment |
fit |
linmod engine : 'limma', 'lm', 'lme', 'lmer' or 'wilcoxon' |
formula |
model formula |
block |
NULL or svar |
label |
fvar |
palette |
NULL or colorvector |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() object %<>% pls(by = 'subgroup') object %<>% fit_limma() plot_summary(object, block = 'Subject')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() object %<>% pls(by = 'subgroup') object %<>% fit_limma() plot_summary(object, block = 'Subject')
Plot venn
plot_venn(x)plot_venn(x)
x |
list |
x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) plot_venn(x)x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) plot_venn(x)
Plot venn heatmap
plot_venn_heatmap(x)plot_venn_heatmap(x)
x |
list |
x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) plot_venn_heatmap(x)x <- list(roundfruit = c('apple', 'orange'), redfruit = c('apple', 'strawberry')) plot_venn_heatmap(x)
Plot sample/feature violins
plot_violins( object, assay = assayNames(object)[1], x, fill, color = NULL, group = NULL, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, palette = NULL, fixed = list(na.rm = TRUE) ) plot_feature_violins( object, assay = assayNames(object)[1], x = "feature_id", fill = "feature_id", color = NULL, n = 9, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, fixed = list(na.rm = TRUE) ) plot_sample_violins( object, assay = assayNames(object)[1], x = "sample_id", fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", color = NULL, n = 100, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, fixed = list(na.rm = TRUE) ) plot_subgroup_violins( object, assay = assayNames(object)[1], subgroup, x = "subgroup", fill = "subgroup", color = NULL, highlight = NULL, facet = "feature_id", fixed = list(na.rm = TRUE) )plot_violins( object, assay = assayNames(object)[1], x, fill, color = NULL, group = NULL, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, palette = NULL, fixed = list(na.rm = TRUE) ) plot_feature_violins( object, assay = assayNames(object)[1], x = "feature_id", fill = "feature_id", color = NULL, n = 9, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, fixed = list(na.rm = TRUE) ) plot_sample_violins( object, assay = assayNames(object)[1], x = "sample_id", fill = if ("subgroup" %in% svars(object)) "subgroup" else "sample_id", color = NULL, n = 100, facet = NULL, nrow = NULL, ncol = NULL, dir = "h", scales = "free", labeller = label_value, highlight = NULL, fixed = list(na.rm = TRUE) ) plot_subgroup_violins( object, assay = assayNames(object)[1], subgroup, x = "subgroup", fill = "subgroup", color = NULL, highlight = NULL, facet = "feature_id", fixed = list(na.rm = TRUE) )
object |
SummarizedExperiment |
assay |
string |
x |
svar (string) |
fill |
svar (string) |
color |
svar (string) |
group |
svar (string) |
facet |
svar (character vector) |
nrow |
NULL or number |
ncol |
NULL or number |
dir |
'h' or 'v' : are facets filled horizontally or vertically ? |
scales |
'free', 'free_x', 'free_y', or 'fixed' |
labeller |
label_both or label_value |
highlight |
fvar expressing which feature should be highlighted (string) |
palette |
named color vector (character vector) |
fixed |
fixed aesthetics |
n |
number |
subgroup |
subgroup svar |
ggplot object
# data file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% extract(, order(.$subgroup)) control_features <- c('biotin','phosphate') fdata(object) %<>% cbind(control = .$feature_name %in% control_features) # plot plot_violins(object[1:12, ], x = 'feature_id', fill = 'feature_id') plot_feature_violins(object[1:12, ]) plot_sample_violins(object[, 1:12], highlight = 'control') plot_subgroup_violins(object[1:4, ], subgroup = 'subgroup')# data file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% extract(, order(.$subgroup)) control_features <- c('biotin','phosphate') fdata(object) %<>% cbind(control = .$feature_name %in% control_features) # plot plot_violins(object[1:12, ], x = 'feature_id', fill = 'feature_id') plot_feature_violins(object[1:12, ]) plot_sample_violins(object[, 1:12], highlight = 'control') plot_subgroup_violins(object[1:4, ], subgroup = 'subgroup')
Plot volcano
plot_volcano( object, fit = fits(object)[1], coefs = setdiff(autonomics::coefs(object, fit = fit), "Intercept")[1], facet = if (is_scalar(fit)) "coef" else c("fit", "coef"), scales = "fixed", shape = if ("imputed" %in% fvars(object)) "imputed" else NULL, size = NULL, alpha = NULL, label = "feature_id", max.overlaps = 10, features = NULL, nrow = length(fit), p = 0.05, fdr = 0.05, xndown = NULL, xnup = NULL, title = NULL )plot_volcano( object, fit = fits(object)[1], coefs = setdiff(autonomics::coefs(object, fit = fit), "Intercept")[1], facet = if (is_scalar(fit)) "coef" else c("fit", "coef"), scales = "fixed", shape = if ("imputed" %in% fvars(object)) "imputed" else NULL, size = NULL, alpha = NULL, label = "feature_id", max.overlaps = 10, features = NULL, nrow = length(fit), p = 0.05, fdr = 0.05, xndown = NULL, xnup = NULL, title = NULL )
object |
SummarizedExperiment |
fit |
'limma', 'lme', 'lm', 'wilcoxon' |
coefs |
character vector |
facet |
character vector |
scales |
'free', 'fixed', etc. |
shape |
fvar (string) |
size |
fvar (string) |
alpha |
fvar (string) |
label |
fvar (string) |
max.overlaps |
number: passed to ggrepel |
features |
feature ids (character vector): features to encircle |
nrow |
number: no of rows in plot |
p |
number: p cutoff for labeling |
fdr |
number: fdr cutoff for labeling |
xndown |
x position of ndown labels |
xnup |
x position of nup labels |
title |
string or NULL |
ggplot object
# Regular Usage file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% fit_lm() plot_volcano(object, coefs = 't3-t0', fit = 'limma') # single contrast plot_volcano(object, coefs = c('t2-t0', 't3-t0'), fit = 'limma') # multip contrasts plot_volcano(object, coefs = c('t2-t0', 't3-t0'), fit = c('limma', 'lm')) # multip contrs & methods # When nothing passes FDR fdt(object) %<>% add_adjusted_pvalues('fdr', fit = 'limma',coefs = 't3-t0') object %<>% extract( fdrvec(object, fit = 'limma', coef = 't3-t0') > 0.05, ) plot_volcano(object, coefs = 't3-t0', fit = 'limma') # Additional mappings file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE) object %<>% fit_limma() plot_volcano(object) plot_volcano(object, label = 'gene') plot_volcano(object, label = 'gene', size = 'log2maxlfq') plot_volcano(object, label = 'gene', size = 'log2maxlfq', alpha = 'pepcounts') plot_volcano(object, label = 'gene', features = c('hmbsb'))# Regular Usage file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% fit_lm() plot_volcano(object, coefs = 't3-t0', fit = 'limma') # single contrast plot_volcano(object, coefs = c('t2-t0', 't3-t0'), fit = 'limma') # multip contrasts plot_volcano(object, coefs = c('t2-t0', 't3-t0'), fit = c('limma', 'lm')) # multip contrs & methods # When nothing passes FDR fdt(object) %<>% add_adjusted_pvalues('fdr', fit = 'limma',coefs = 't3-t0') object %<>% extract( fdrvec(object, fit = 'limma', coef = 't3-t0') > 0.05, ) plot_volcano(object, coefs = 't3-t0', fit = 'limma') # Additional mappings file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, impute = TRUE) object %<>% fit_limma() plot_volcano(object) plot_volcano(object, label = 'gene') plot_volcano(object, label = 'gene', size = 'log2maxlfq') plot_volcano(object, label = 'gene', size = 'log2maxlfq', alpha = 'pepcounts') plot_volcano(object, label = 'gene', features = c('hmbsb'))
diann precursor quantity
PRECURSOR_QUANTITYPRECURSOR_QUANTITY
An object of class character of length 1.
Preprocess RNAseq counts
preprocess_rnaseq_counts( object, formula = ~subgroup, block = NULL, min_count = 10, pseudo = 0.5, tpm = FALSE, cpm = TRUE, voom = TRUE, log2 = TRUE, verbose = TRUE, plot = TRUE )preprocess_rnaseq_counts( object, formula = ~subgroup, block = NULL, min_count = 10, pseudo = 0.5, tpm = FALSE, cpm = TRUE, voom = TRUE, log2 = TRUE, verbose = TRUE, plot = TRUE )
object |
SummarizedExperiment |
formula |
designmat formula |
block |
blocK svar |
min_count |
min count required in some samples |
pseudo |
added pseudocount to avoid log(x)=-Inf |
tpm |
TRUE or FALSE : tpm normalize? |
cpm |
TRUE or FALSE : cpm normalize? (counts per million (scaled) reads) |
voom |
TRUE or FALSE : voom weight? |
log2 |
TRUE or FALSE : log2 transform? |
verbose |
TRUE or FALSE : msg? |
plot |
TRUE or FALSE : plot? |
SummarizedExperiment
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- .read_rnaseq_counts(file) object$subgroup object %<>% preprocess_rnaseq_counts()file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- .read_rnaseq_counts(file) object$subgroup object %<>% preprocess_rnaseq_counts()
Pull columns in a dataframe to the front
pull_columns(df, first_cols, verbose = TRUE)pull_columns(df, first_cols, verbose = TRUE)
df |
data.frame |
first_cols |
character vector: columns to be pulled to the front |
verbose |
TRUE (default) or FALSE |
dataframe with re-ordered columns
df <- data.frame( symbol = c('A1BG', 'A2M'), id = c('1', '2'), name = c('alpha-1-B glycoprotein', 'alpha-2-macroglobulin'), type = c('proteincoding', 'proteincoding')) first_cols <- c('id', 'symbol', 'location', 'uniprot') pull_columns(df, first_cols)df <- data.frame( symbol = c('A1BG', 'A2M'), id = c('1', '2'), name = c('alpha-1-B glycoprotein', 'alpha-2-macroglobulin'), type = c('proteincoding', 'proteincoding')) first_cols <- c('id', 'symbol', 'location', 'uniprot') pull_columns(df, first_cols)
Read affymetrix microarray
read_affymetrix(celfiles)read_affymetrix(celfiles)
celfiles |
string vector: CEL file paths |
RangedSummarizedExperiment
# Downloading example dataset fails 600s limit - example outcommented. # url <- paste0('http://www.bioconductor.org/help/publications/2003/Chiaretti/chiaretti2/T33.tgz') # localdir <- file.path(tools::R_user_dir('autonomics', 'cache'), 'T33') # dir.create(localdir, showWarnings = FALSE) # localfile <- file.path(localdir, basename(url)) # if (!file.exists(localfile)){ download.file(url, destfile = localfile) # untar(localfile, exdir = path.expand(localdir)) } # localfile %<>% substr(1, nchar(.)-4) # if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages('BiocManager') # if (!requireNamespace("hgu95av2.db", quietly = TRUE)) BiocManager::install('hgu95av2.db') # read_affymetrix(celfiles = list.files(localfile, full.names = TRUE))# Downloading example dataset fails 600s limit - example outcommented. # url <- paste0('http://www.bioconductor.org/help/publications/2003/Chiaretti/chiaretti2/T33.tgz') # localdir <- file.path(tools::R_user_dir('autonomics', 'cache'), 'T33') # dir.create(localdir, showWarnings = FALSE) # localfile <- file.path(localdir, basename(url)) # if (!file.exists(localfile)){ download.file(url, destfile = localfile) # untar(localfile, exdir = path.expand(localdir)) } # localfile %<>% substr(1, nchar(.)-4) # if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages('BiocManager') # if (!requireNamespace("hgu95av2.db", quietly = TRUE)) BiocManager::install('hgu95av2.db') # read_affymetrix(celfiles = list.files(localfile, full.names = TRUE))
Read compound discoverer output
read_compounddiscoverer( dir = getwd(), files = list.files(path = dir, pattern = "(RP|HILIC).*\\.csv$", full.names = TRUE), colname_regex = "^(.*)\\d{8,8}_+(.*)_+((HILIC|RP)(NEG|POS))\\.raw.*$", colname_format = function(x) stringi::stri_replace_first_regex(x, colname_regex, "$1$2"), mod_extract = function(x) stringi::stri_subset_regex(x, colname_regex) %>% stringi::stri_replace_first_regex(colname_regex, "$3"), quantity = NULL, nonames = FALSE, exclude_sname_pattern = "(blank|QC|RS)", subgroups = NULL, logbase = 2, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE )read_compounddiscoverer( dir = getwd(), files = list.files(path = dir, pattern = "(RP|HILIC).*\\.csv$", full.names = TRUE), colname_regex = "^(.*)\\d{8,8}_+(.*)_+((HILIC|RP)(NEG|POS))\\.raw.*$", colname_format = function(x) stringi::stri_replace_first_regex(x, colname_regex, "$1$2"), mod_extract = function(x) stringi::stri_subset_regex(x, colname_regex) %>% stringi::stri_replace_first_regex(colname_regex, "$3"), quantity = NULL, nonames = FALSE, exclude_sname_pattern = "(blank|QC|RS)", subgroups = NULL, logbase = 2, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE )
dir |
compound discoverer output directory |
files |
compound discoverer output files |
colname_regex |
regular expression to parse sample names from column names |
colname_format |
function to reformat column names |
mod_extract |
function to extract MS modi from sample names |
quantity |
'area', 'normalizedarea' or NULL |
nonames |
TRUE or FALSE: retain compunds without Names? |
exclude_sname_pattern |
regular expression of sample names to exclude |
subgroups |
NULL or string vector : subgroups to retain |
logbase |
base for logarithmization of the data |
impute |
TRUE or FALSE: impute group-specific NA values? |
plot |
TRUE or FALSE: plot ? |
label |
fvar |
pca |
TRUE or FALSE: run pca ? |
pls |
TRUE or FALSE: run pls ? |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar: string or NULL |
coefs |
model coefficients of interest: character vector or NULL |
contrasts |
coefficient contrasts of interest: character vector or NULL |
palette |
color palette : named character vector |
verbose |
TRUE or FALSE : message ? |
SummarizedExperiment
Read contaminants
read_contaminants(file = download_contaminants())read_contaminants(file = download_contaminants())
file |
contaminant file |
data.table
file <- download_contaminants() dt <- read_contaminants(file)file <- download_contaminants() dt <- read_contaminants(file)
Read fragpipe
read_fragpipe( dir = getwd(), file = if (is_file(dir)) dir else file.path(dir, "combined_protein.tsv"), contaminants = FALSE, verbose = TRUE )read_fragpipe( dir = getwd(), file = if (is_file(dir)) dir else file.path(dir, "combined_protein.tsv"), contaminants = FALSE, verbose = TRUE )
dir |
directory with 'combined_protein.tsv' |
file |
'combined_protein.tsv' (full path) |
contaminants |
whether to include contaminants |
verbose |
whether to msg |
SummarizedExperiment
file <- download_data('multiorganism.combined_protein.tsv') object <- read_fragpipe(file = file) object fdt(object) sdt(object)file <- download_data('multiorganism.combined_protein.tsv') object <- read_fragpipe(file = file) object fdt(object) sdt(object)
Read maxquant phosphosites
read_maxquant_phosphosites( dir = getwd(), fosfile = if (is_file(dir)) dir else file.path(dir, "phospho (STY)Sites.txt"), profile = file.path(dirname(fosfile), "proteinGroups.txt"), fastafile = NULL, restapi = FALSE, quantity = NULL, subgroups = NULL, invert = character(0), contaminants = FALSE, reverse = FALSE, rm_missing_in_all_samples = TRUE, localization = 0.75, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_phosphosites(...)read_maxquant_phosphosites( dir = getwd(), fosfile = if (is_file(dir)) dir else file.path(dir, "phospho (STY)Sites.txt"), profile = file.path(dirname(fosfile), "proteinGroups.txt"), fastafile = NULL, restapi = FALSE, quantity = NULL, subgroups = NULL, invert = character(0), contaminants = FALSE, reverse = FALSE, rm_missing_in_all_samples = TRUE, localization = 0.75, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_phosphosites(...)
dir |
proteingroups directory |
fosfile |
phosphosites file |
profile |
proteingroups file |
fastafile |
uniprot fastafile |
restapi |
TRUE or FALSE : annotate non-fastadt uniprots using uniprot restapi |
quantity |
'normalizedratio', 'ratio', 'correctedreporterintensity', 'reporterintensity', 'maxlfq', 'labeledintensity', 'intensity' or NULL |
subgroups |
NULL or string vector : subgroups to retain |
invert |
string vector: subgroups which require inversion |
contaminants |
TRUE or FALSE: retain contaminants ? |
reverse |
TRUE or FALSE: include reverse hits |
rm_missing_in_all_samples |
TRUE or FALSE |
localization |
number: min localization probability (for phosphosites) |
impute |
TRUE or FALSE: impute group-specific NA values? |
plot |
TRUE or FALSE |
label |
fvar |
pca |
TRUE or FALSE: run pca ? |
pls |
TRUE or FALSE: run pls ? |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar: string or NULL |
coefs |
model coefficients of interest: string vector or NULL |
contrasts |
model coefficient contrasts of interest: string vector or NULL |
palette |
color palette: named string vector |
verbose |
TRUE or FALSE: message ? |
... |
maintain deprecated functions |
SummarizedExperiment
profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00')) pro <- read_maxquant_proteingroups(file = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites( fosfile = fosfile, profile = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites( fosfile = fosfile, profile = profile, fastafile = fastafile, subgroups = subgroups)profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00')) pro <- read_maxquant_proteingroups(file = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites( fosfile = fosfile, profile = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites( fosfile = fosfile, profile = profile, fastafile = fastafile, subgroups = subgroups)
Read maxquant proteingroups
read_maxquant_proteingroups( dir = getwd(), file = if (is_file(dir)) dir else file.path(dir, "proteinGroups.txt"), fastafile = NULL, restapi = FALSE, quantity = NULL, subgroups = NULL, invert = character(0), contaminants = FALSE, reverse = FALSE, rm_missing_in_all_samples = TRUE, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_proteingroups(...)read_maxquant_proteingroups( dir = getwd(), file = if (is_file(dir)) dir else file.path(dir, "proteinGroups.txt"), fastafile = NULL, restapi = FALSE, quantity = NULL, subgroups = NULL, invert = character(0), contaminants = FALSE, reverse = FALSE, rm_missing_in_all_samples = TRUE, impute = FALSE, plot = FALSE, label = "feature_id", pca = plot, pls = plot, fit = if (plot) "limma" else NULL, formula = ~subgroup, block = NULL, coefs = NULL, contrasts = NULL, palette = NULL, verbose = TRUE ) read_proteingroups(...)
dir |
proteingroups directory |
file |
proteingroups file |
fastafile |
uniprot fastafile |
restapi |
TRUE or FALSE : use uniprot restapi to annotate uniprots not in fastadt ? |
quantity |
'normalizedratio', 'ratio', 'correctedreporterintensity', 'reporterintensity', 'maxlfq', 'labeledintensity', 'intensity' or NULL |
subgroups |
NULL or string vector : subgroups to retain |
invert |
string vector : subgroups which require inversion |
contaminants |
TRUE or FALSE : retain contaminants ? |
reverse |
TRUE or FALSE : include reverse hits ? |
rm_missing_in_all_samples |
TRUE or FALSE |
impute |
TRUE or FALSE: impute group-specific NA values? |
plot |
TRUE or FALSE: plot ? |
label |
fvar |
pca |
TRUE or FALSE: run pca ? |
pls |
TRUE or FALSE: run pls ? |
fit |
model engine: 'limma', 'lm', 'lme(r)', 'wilcoxon' or NULL |
formula |
model formula |
block |
model blockvar: string or NULL |
coefs |
model coefficients of interest: character vector or NULL |
contrasts |
coefficient contrasts of interest: character vector or NULL |
palette |
color palette : named character vector |
verbose |
TRUE or FALSE : message ? |
... |
maintain deprecated functions |
SummarizedExperiment
# fukuda20 - LFQ file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') pro <- read_maxquant_proteingroups(file = file) # billing19 - Normalized Ratios file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00')) pro <- read_maxquant_proteingroups(file = file, subgroups = subgroups) pro <- read_maxquant_proteingroups(file = file, fastafile = fastafile, subgroups = subgroups)# fukuda20 - LFQ file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') pro <- read_maxquant_proteingroups(file = file) # billing19 - Normalized Ratios file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') subgroups <- sprintf('%s_STD', c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00')) pro <- read_maxquant_proteingroups(file = file, subgroups = subgroups) pro <- read_maxquant_proteingroups(file = file, fastafile = fastafile, subgroups = subgroups)
Read msigdb datatable
read_msigdt( file = list_files(MSIGDIR, full.names = TRUE)[1], collections = if (is.null(file)) NULL else switch(basename(file) %>% substr(nchar(.) - 4, nchar(.) - 3), Hs = c("C2:CP:REACTOME", "C5:GO:BP", "C5:GO:MF", "C5:GO:CC"), Mm = c("M2:CP:REACTOME", "M5:GO:BP", "M5:GO:MF", "M5:GO:CC")) )read_msigdt( file = list_files(MSIGDIR, full.names = TRUE)[1], collections = if (is.null(file)) NULL else switch(basename(file) %>% substr(nchar(.) - 4, nchar(.) - 3), Hs = c("C2:CP:REACTOME", "C5:GO:BP", "C5:GO:MF", "C5:GO:CC"), Mm = c("M2:CP:REACTOME", "M5:GO:BP", "M5:GO:MF", "M5:GO:CC")) )
file |
msigdb file: one of the files in dir(MSIGDB). |
collections |
subset of names(MSIGCOLLECTIONS) |
read_msigdt()read_msigdt()
Read olink file
read_olink(file, sample_excel = NULL, sample_tsv = NULL, by.y = "SampleID")read_olink(file, sample_excel = NULL, sample_tsv = NULL, by.y = "SampleID")
file |
olinkfile |
sample_excel |
sample excel |
sample_tsv |
sample tsv |
by.y |
sample tsv mergeby column |
SummarizedExperiment
# Example data npxdt <- data.table::data.table(OlinkAnalyze::npx_data1)[, c(1:11, 17)] sampledt <- data.table::data.table(OlinkAnalyze::npx_data1)[, c(1, 12:15)] sampledt %<>% extract(!grepl('CONTROL', SampleID)) sampledt %<>% unique() # Write to file file <- paste0(tempfile(), '.olink.csv') samplefile <- paste0(tempfile(), '.samples.xlsx') data.table::fwrite(npxdt, file) writexl::write_xlsx(sampledt, samplefile) # Read object <- read_olink(file, sample_excel = samplefile) biplot(pca(object), color = 'Time', group = 'Subject', shape = 'Treatment')# Example data npxdt <- data.table::data.table(OlinkAnalyze::npx_data1)[, c(1:11, 17)] sampledt <- data.table::data.table(OlinkAnalyze::npx_data1)[, c(1, 12:15)] sampledt %<>% extract(!grepl('CONTROL', SampleID)) sampledt %<>% unique() # Write to file file <- paste0(tempfile(), '.olink.csv') samplefile <- paste0(tempfile(), '.samples.xlsx') data.table::fwrite(npxdt, file) writexl::write_xlsx(sampledt, samplefile) # Read object <- read_olink(file, sample_excel = samplefile) biplot(pca(object), color = 'Time', group = 'Subject', shape = 'Treatment')
Read salmon
read_salmon(dir, sfile = NULL, by = NULL, ensdb = NULL)read_salmon(dir, sfile = NULL, by = NULL, ensdb = NULL)
dir |
salmon results rootdir |
sfile |
samplefile |
by |
samplefile column to merge by |
ensdb |
EnsDb object |
SummarizedExperiment
# dir <- '../bh/salmon_quants' # sfile <- '../bh/samplesheet.csv' # by <- 'salmonDir' # ah <- AnnotationHub::AnnotationHub() # ensdb <- ah[['AH98078']] # read_salmon(dir, sfile = sfile, by = 'salmonDir', ensdb = ensdb)# dir <- '../bh/salmon_quants' # sfile <- '../bh/samplesheet.csv' # by <- 'salmonDir' # ah <- AnnotationHub::AnnotationHub() # ensdb <- ah[['AH98078']] # read_salmon(dir, sfile = sfile, by = 'salmonDir', ensdb = ensdb)
Read fasta hdrs
read_uniprotdt(fastafile, fastafields = FASTAFIELDS, verbose = TRUE) parse_maxquant_hdrs(fastahdrs) read_contaminantdt(force = FALSE, verbose = TRUE)read_uniprotdt(fastafile, fastafields = FASTAFIELDS, verbose = TRUE) parse_maxquant_hdrs(fastahdrs) read_contaminantdt(force = FALSE, verbose = TRUE)
fastafile |
string (or charactervector) |
fastafields |
charactervector : which fastahdr fields to extract ? |
verbose |
bool |
fastahdrs |
character vector |
force |
whether to overwrite existing file |
data.table(uniprot, protein, gene, uniprot, reviewed, existence)
existence values are always those of the canonical isoform (no isoform-level resolution for this field)
# uniprot hdrs fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') read_uniprotdt(fastafile) # maxquant hdrs file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') dt <- .read_maxquant_proteingroups(file) parse_maxquant_hdrs(dt$`Fasta headers`) profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics' ) prodt <- .read_maxquant_proteingroups(profile) fosdt <- .read_maxquant_phosphosites(fosfile, profile) parse_maxquant_hdrs(prodt$`Fasta headers`) parse_maxquant_hdrs(fosdt$`Fasta headers`) # contaminant hdrs read_contaminantdt()# uniprot hdrs fastafile <- system.file('extdata/uniprot_hsa_20140515.fasta', package = 'autonomics') read_uniprotdt(fastafile) # maxquant hdrs file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') dt <- .read_maxquant_proteingroups(file) parse_maxquant_hdrs(dt$`Fasta headers`) profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics' ) prodt <- .read_maxquant_proteingroups(profile) fosdt <- .read_maxquant_phosphosites(fosfile, profile) parse_maxquant_hdrs(prodt$`Fasta headers`) parse_maxquant_hdrs(fosdt$`Fasta headers`) # contaminant hdrs read_contaminantdt()
Reset fit
reset_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), verbose = TRUE )reset_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), verbose = TRUE )
object |
SummarizedExperiment |
fit |
character vector |
coefs |
character vector |
verbose |
TRUE or FALSE |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') (object <- read_metabolon(file)) object %<>% reset_fit() object %<>% fit_limma() %>% reset_fit() object %<>% fit_limma() %>% fit_lm() %>% reset_fit() object %<>% fit_limma() %>% fit_lm() %>% reset_fit('limma')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') (object <- read_metabolon(file)) object %<>% reset_fit() object %<>% fit_limma() %>% reset_fit() object %<>% fit_limma() %>% fit_lm() %>% reset_fit() object %<>% fit_limma() %>% fit_lm() %>% reset_fit('limma')
Rm contaminants from DIA-NN SumExp
rm_diann_contaminants( object, contaminants = read_contaminants(), verbose = TRUE )rm_diann_contaminants( object, contaminants = read_contaminants(), verbose = TRUE )
object |
SummarizedExperiment |
contaminants |
uniprots (character vector) |
verbose |
TRUE or FALSE |
SummarizedExperiment
file <- download_data('dilution.report.tsv') object <- read_diann_proteingroups(file) object %<>% rm_diann_contaminants()file <- download_data('dilution.report.tsv') object <- read_diann_proteingroups(file) object %<>% rm_diann_contaminants()
Rm features missing in some samples
rm_missing_in_all_samples(object, verbose = TRUE) rm_missing_in_some_samples(object, verbose = TRUE)rm_missing_in_all_samples(object, verbose = TRUE) rm_missing_in_some_samples(object, verbose = TRUE)
object |
SummarizedExperiment |
verbose |
TRUE (default) or FALSE |
updated object
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) rm_missing_in_all_samples( object) rm_missing_in_some_samples(object)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) rm_missing_in_all_samples( object) rm_missing_in_some_samples(object)
rm unmatched/singleton samples
rm_unmatched_samples( object, subgroupvar = "subgroup", subgroupctr = slevels(object, subgroupvar)[1], block, verbose = TRUE ) rm_singleton_samples(object, subgroupvar = "subgroup", verbose = TRUE)rm_unmatched_samples( object, subgroupvar = "subgroup", subgroupctr = slevels(object, subgroupvar)[1], block, verbose = TRUE ) rm_singleton_samples(object, subgroupvar = "subgroup", verbose = TRUE)
object |
SummarizedExperiment |
subgroupvar |
subgroup variable (string) |
subgroupctr |
control subgroup (string) |
block |
block variable (string) |
verbose |
TRUE/FALSE |
SummarizedExperiment
file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file) object %<>% filter_samples(subgroup %in% c('t1', 't2'), verbose = TRUE) rm_singleton_samples(object, subgroupvar = 'Subject') rm_unmatched_samples(object, subgroupvar = 'subgroup', block = 'Subject')file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file) object %<>% filter_samples(subgroup %in% c('t1', 't2'), verbose = TRUE) rm_singleton_samples(object, subgroupvar = 'Subject') rm_unmatched_samples(object, subgroupvar = 'subgroup', block = 'Subject')
Get tmm-scaled libsizes
scaledlibsizes(counts)scaledlibsizes(counts)
counts |
counts matri |
scaled libsize vector
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) scaledlibsizes(counts(object))file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) scaledlibsizes(counts(object))
Extract scores/loadings
scoremat(object, method = "pca", by = biplot_by(object, method), dim = 1:2) scores(object, method = "pca", by = biplot_by(object, method), dim = 1) loadingmat(object, method = "pca", by = biplot_by(object, method), dim = 1:2) loadings(object, method = "pca", by = biplot_by(object, method), dim = 1)scoremat(object, method = "pca", by = biplot_by(object, method), dim = 1:2) scores(object, method = "pca", by = biplot_by(object, method), dim = 1) loadingmat(object, method = "pca", by = biplot_by(object, method), dim = 1:2) loadings(object, method = "pca", by = biplot_by(object, method), dim = 1)
object |
SummarizedExperiment |
method |
'pca', 'pls', etc. |
by |
svar (string) |
dim |
numeric vector |
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() scores(object)[1:2] loadings(object)[1:2] scoremat(object)[1:2, ] loadingmat(object)[1:2, ]file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% pca() scores(object)[1:2] loadings(object)[1:2] scoremat(object)[1:2, ] loadingmat(object)[1:2, ]
Get svar levels
slevels(object, svar) subgroup_levels(object)slevels(object, svar) subgroup_levels(object)
object |
SummarizedExperiment, eSet, or eList |
svar |
sample var (character) |
svar values (character)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) slevels(object, 'subgroup') subgroup_levels(object)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) slevels(object, 'subgroup') subgroup_levels(object)
Get/Set sample names
snames(object) ## S4 method for signature 'SummarizedExperiment' snames(object) snames(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' snames(object) <- valuesnames(object) ## S4 method for signature 'SummarizedExperiment' snames(object) snames(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' snames(object) <- value
object |
SummarizedExperiment |
value |
string vector with sample names |
sample names vector (get) or updated eSet (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(snames(object)) head(snames(object) %<>% paste0('SAMPLE_', .))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) head(snames(object)) head(snames(object) %<>% paste0('SAMPLE_', .))
Split samples by svar
split_samples(object, by = "subgroup") cbind_imputed(objlist) split_features(object, by)split_samples(object, by = "subgroup") cbind_imputed(objlist) split_features(object, by)
object |
SummarizedExperiment |
by |
svar to split by (string) |
objlist |
SummarizedExperiment list |
SummarizedExperiment list
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) objlist <- split_features(object, by = 'PLATFORM') objlist <- split_samples(object, 'Diabetes') objlist %<>% Map(impute, .) object <- cbind_imputed(objlist)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) objlist <- split_features(object, by = 'PLATFORM') objlist <- split_samples(object, 'Diabetes') objlist %<>% Map(impute, .) object <- cbind_imputed(objlist)
Does any string have a regex
stri_any_regex(str, pattern)stri_any_regex(str, pattern)
str |
string vector |
pattern |
string |
TRUE or FALSE
str <- c('s1 Spectral Count', 's1 Unique Spectral Count') patterns <- c('Spectral Count', '(?<!Unique) Spectral Count', 'Intensity') stringi::stri_detect_regex(str, pattern = patterns[1]) stringi::stri_detect_regex(str, pattern = patterns[2]) stringi::stri_detect_regex(str, pattern = patterns[3]) stri_any_regex( str, pattern = patterns)str <- c('s1 Spectral Count', 's1 Unique Spectral Count') patterns <- c('Spectral Count', '(?<!Unique) Spectral Count', 'Intensity') stringi::stri_detect_regex(str, pattern = patterns[1]) stringi::stri_detect_regex(str, pattern = patterns[2]) stringi::stri_detect_regex(str, pattern = patterns[3]) stri_any_regex( str, pattern = patterns)
Detect fixed patterns in collapsed strings
stri_detect_fixed_in_collapsed(x, patterns, sep)stri_detect_fixed_in_collapsed(x, patterns, sep)
x |
vector with collapsed strings |
patterns |
vector with fixed patterns (strings) |
sep |
collapse separator (string) or NULL (if uncollapsed) |
boolean vector
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) x <- fdt(object)$uniprot patterns <- c('A0A0R4IKT8', 'Q7T3G6') table(stri_detect_fixed_in_collapsed(x = x, patterns = patterns, sep = ';'))file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) x <- fdt(object)$uniprot patterns <- c('A0A0R4IKT8', 'Q7T3G6') table(stri_detect_fixed_in_collapsed(x = x, patterns = patterns, sep = ';'))
Arrange (subgroup)levels in matrix
subgroup_array(object, subgroupvar) subgroup_matrix(object, subgroupvar)subgroup_array(object, subgroupvar) subgroup_matrix(object, subgroupvar)
object |
SummarizedExperiment |
subgroupvar |
subgroup svar |
matrix
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$subgroup <- paste0(object$Diabetes, '.', object$subgroup) subgroup_matrix(object, 'subgroup')file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object$subgroup <- paste0(object$Diabetes, '.', object$subgroup) subgroup_matrix(object, 'subgroup')
Subtract baseline level within block
subtract_baseline( object, subgroupvar, subgroupctr = slevels(object, subgroupvar)[1], block = NULL, assaynames = setdiff(assayNames(object), c("weights", "pepcounts")), verbose = TRUE ) subtract_pairs( object, subgroupvar = "subgroup", subgroupctr = slevels(object, subgroupvar)[1], block, assaynames = assayNames(object)[1], verbose = TRUE ) subtract_differences(object, block, subgroupvar, verbose = TRUE)subtract_baseline( object, subgroupvar, subgroupctr = slevels(object, subgroupvar)[1], block = NULL, assaynames = setdiff(assayNames(object), c("weights", "pepcounts")), verbose = TRUE ) subtract_pairs( object, subgroupvar = "subgroup", subgroupctr = slevels(object, subgroupvar)[1], block, assaynames = assayNames(object)[1], verbose = TRUE ) subtract_differences(object, block, subgroupvar, verbose = TRUE)
object |
SummarizedExperiment |
subgroupvar |
subgroup svar |
subgroupctr |
control subgroup |
block |
block svar (within which subtraction is performed) |
assaynames |
which assays to subtract for |
verbose |
TRUE/FALSE |
subtract_baseline subtracts baseline levels within block, using the
medoid baseline sample if multiple exist.
subtract_pairs also subtracts baseline level within block.
It cannot handle multiple baseline samples, but has instead been optimized
for many blocks
subtract_differences subtracts differences between subsequent levels,
again within block
SummarizedExperiment
# read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object0 <- read_metabolon(file) pca(object0, plot = TRUE, color = 'Time') # subtract_baseline: takes medoid of baseline samples if multiple object <- subtract_baseline(object0, block = 'Subject', subgroupvar = 'Time') pca(object, plot = TRUE, color = 'Time') # subtract_pairs: optimized for many blocks object <- subtract_pairs(object0, block = 'Subject', subgroupvar = 'Time') pca(object, plot = TRUE, color = 'Time') # subtract_differences object <- subtract_differences(object0, block = 'Subject', subgroupvar = 'Time') values(object) %<>% na_to_zero() pca(object, plot = TRUE, color = 'Time')# read file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object0 <- read_metabolon(file) pca(object0, plot = TRUE, color = 'Time') # subtract_baseline: takes medoid of baseline samples if multiple object <- subtract_baseline(object0, block = 'Subject', subgroupvar = 'Time') pca(object, plot = TRUE, color = 'Time') # subtract_pairs: optimized for many blocks object <- subtract_pairs(object0, block = 'Subject', subgroupvar = 'Time') pca(object, plot = TRUE, color = 'Time') # subtract_differences object <- subtract_differences(object0, block = 'Subject', subgroupvar = 'Time') values(object) %<>% na_to_zero() pca(object, plot = TRUE, color = 'Time')
Write sumexp to tsv
sumexp_to_tsv(object, assay = assayNames(object)[1], file)sumexp_to_tsv(object, assay = assayNames(object)[1], file)
object |
SummarizedExperiment |
assay |
string |
file |
filename |
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, fit = 'limma') tsv <- file.path(tempdir(), 'fukuda20.proteingroups.tsv') sumexp_to_tsv(object, file = tsv)file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file, fit = 'limma') tsv <- file.path(tempdir(), 'fukuda20.proteingroups.tsv') sumexp_to_tsv(object, file = tsv)
SummarizedExperiment to data.table
sumexp_to_widedt( object, fvars = autonomics::fvars(object), assay = assayNames(object)[1] ) sumexp_to_longdt( object, fvars = intersect("feature_name", autonomics::fvars(object)), svars = intersect("subgroup", autonomics::svars(object)), assay = assayNames(object) %>% intersect(c(.[1], "is_imputed")) ) sumexp_to_subrep_dt(object, subgroup = subgroup)sumexp_to_widedt( object, fvars = autonomics::fvars(object), assay = assayNames(object)[1] ) sumexp_to_longdt( object, fvars = intersect("feature_name", autonomics::fvars(object)), svars = intersect("subgroup", autonomics::svars(object)), assay = assayNames(object) %>% intersect(c(.[1], "is_imputed")) ) sumexp_to_subrep_dt(object, subgroup = subgroup)
object |
sumexp |
fvars |
additional fvars to include in table |
assay |
matrix in assays(object) to be used |
svars |
additional svars to include in table |
subgroup |
subgroup (sym) |
sumexp_to_widedt: feature x sample
sumexp_to_subrep_dt: feature.subgroup x replicate
sumexp_to_longdt: feature.sample
data.table
# Atkin Hypoglycemia file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) sumexp_to_widedt(object) sumexp_to_longdt(object) sumexp_to_subrep_dt(object) # Fukuda file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) values(object) fdt(object) object %<>% impute() table(fdt(object)$imputed) sumexp_to_longdt(object) sumexp_to_widedt(object) sumexp_to_longdt(object)# Atkin Hypoglycemia file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) sumexp_to_widedt(object) sumexp_to_longdt(object) sumexp_to_subrep_dt(object) # Fukuda file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) values(object) fdt(object) object %<>% impute() table(fdt(object)$imputed) sumexp_to_longdt(object) sumexp_to_widedt(object) sumexp_to_longdt(object)
SummarizedExperiment list to long data.table
sumexplist_to_longdt( sumexplist, svars = intersect("subgroup", autonomics::svars(sumexplist[[1]])), fvars = intersect("gene", autonomics::fvars(sumexplist[[1]])), setvarname = "set" )sumexplist_to_longdt( sumexplist, svars = intersect("subgroup", autonomics::svars(sumexplist[[1]])), fvars = intersect("gene", autonomics::fvars(sumexplist[[1]])), setvarname = "set" )
sumexplist |
list of SummarizedExperiments |
svars |
character vector |
fvars |
character vector |
setvarname |
string |
data.table
subgroups <- paste0(c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00'), '_STD') rnafile <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') rna <- read_rnaseq_counts(rnafile) pro <- read_maxquant_proteingroups(file = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites(fosfile = fosfile, profile = profile, subgroups = subgroups) pro$subgroup %<>% stringi::stri_replace_first_fixed('_STD', '') fos$subgroup %<>% stringi::stri_replace_first_fixed('_STD', '') sumexplist <- list(rna = rna, pro = pro, fos = fos) dt <- sumexplist_to_longdt(sumexplist, setvarname = 'platform') dt %<>% extract(gene %in% c('TNMD', 'TSPAN6'))subgroups <- paste0(c('E00', 'E01', 'E02', 'E05', 'E15', 'E30', 'M00'), '_STD') rnafile <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') profile <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') fosfile <- system.file('extdata/billing19.phosphosites.txt', package = 'autonomics') rna <- read_rnaseq_counts(rnafile) pro <- read_maxquant_proteingroups(file = profile, subgroups = subgroups) fos <- read_maxquant_phosphosites(fosfile = fosfile, profile = profile, subgroups = subgroups) pro$subgroup %<>% stringi::stri_replace_first_fixed('_STD', '') fos$subgroup %<>% stringi::stri_replace_first_fixed('_STD', '') sumexplist <- list(rna = rna, pro = pro, fos = fos) dt <- sumexplist_to_longdt(sumexplist, setvarname = 'platform') dt %<>% extract(gene %in% c('TNMD', 'TSPAN6'))
Summarize fit
summarize_fit(object, ...) ## S3 method for class 'data.table' summarize_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' summarize_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), ... )summarize_fit(object, ...) ## S3 method for class 'data.table' summarize_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), ... ) ## S3 method for class 'SummarizedExperiment' summarize_fit( object, fit = fits(object), coefs = autonomics::coefs(object, fit = fit), ... )
object |
SummarizedExperiment or data.table |
... |
S3 dispatch |
fit |
'limma', 'lme', 'lm', 'lme', 'wilcoxon' or NULL |
coefs |
string vector |
data.table(contrast, nup, ndown)
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% fit_lm() summarize_fit(object, coefs = c('t1-t0', 't2-t0', 't3-t0'))file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma() object %<>% fit_lm() summarize_fit(object, coefs = c('t1-t0', 't2-t0', 't3-t0'))
Get/Set svar values
svalues(object, svar) subgroup_values(object) sampleid_values(object) svalues(object, svar) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' svalues(object, svar) <- valuesvalues(object, svar) subgroup_values(object) sampleid_values(object) svalues(object, svar) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' svalues(object, svar) <- value
object |
SummarizedExperiment |
svar |
sample var (character) |
value |
value vector |
character vector (get) or SummarizedExperiment (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) svalues(object, 'subgroup') subgroup_values(object)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) svalues(object, 'subgroup') subgroup_values(object)
Get/Set sample variables
svars(object) ## S4 method for signature 'SummarizedExperiment' svars(object) ## S4 method for signature 'MultiAssayExperiment' svars(object) svars(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' svars(object) <- value ## S4 replacement method for signature 'MultiAssayExperiment,character' svars(object) <- valuesvars(object) ## S4 method for signature 'SummarizedExperiment' svars(object) ## S4 method for signature 'MultiAssayExperiment' svars(object) svars(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,character' svars(object) <- value ## S4 replacement method for signature 'MultiAssayExperiment,character' svars(object) <- value
object |
SummarizedExperiment |
value |
string fector with variable names |
sample variable names (get) or updated SummarizedExperiment
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) svars(object)[1] (svars(object)[1] %<>% paste0('1'))file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) svars(object)[1] (svars(object)[1] %<>% paste0('1'))
Is systematic/random/full NA
systematic_nas(object, by = "subgroup", frac = 0.5) random_nas(object, by = "subgroup") no_nas(object)systematic_nas(object, by = "subgroup", frac = 0.5) random_nas(object, by = "subgroup") no_nas(object)
object |
SummarizedExperiment |
by |
svar (string) |
frac |
fraction |
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) table(systematic_nas(object)) # missing in some subgroups, present in others table(random_nas(object)) # missing in some samples, independent of subgroup table(no_nas(object)) # missing in no samplesfile <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) table(systematic_nas(object)) # missing in some subgroups, present in others table(random_nas(object)) # missing in some samples, independent of subgroup table(no_nas(object)) # missing in no samples
Tag features
tag_features( object, keyvar, sep, features, tagvar = get_name_in_parent(features), verbose = TRUE )tag_features( object, keyvar, sep, features, tagvar = get_name_in_parent(features), verbose = TRUE )
object |
SummarizedExperiment |
keyvar |
string : intersection fvar |
sep |
string : keyvar collapse separator |
features |
character vector : intersection set |
tagvar |
string : |
verbose |
TRUE or FALSE |
SummarizedExperiment
file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file) features <- AnnotationDbi::keys(org.Hs.eg.db::org.Hs.eg.db, keytype = 'SYMBOL') object %<>% tag_features(keyvar = 'EntrezGeneSymbol', sep = ' ', features) table(fdt(object)$features)file <- system.file('extdata/atkin.somascan.adat', package = 'autonomics') object <- read_somascan(file) features <- AnnotationDbi::keys(org.Hs.eg.db::org.Hs.eg.db, keytype = 'SYMBOL') object %<>% tag_features(keyvar = 'EntrezGeneSymbol', sep = ' ', features) table(fdt(object)$features)
Tag hdlproteins
tag_hdlproteins(object, verbose = TRUE)tag_hdlproteins(object, verbose = TRUE)
object |
SummarizedExperiment |
verbose |
TRUE or FALSE |
SummarizedExperiment
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% tag_hdlproteins() fdt(object)file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) object %<>% tag_hdlproteins() fdt(object)
Annotation Maps
TAXON_TO_ORGNAME ABBREV_TO_ORGNAME REVIEWED_TO_NUMBER EXISTENCE_TO_NUMBERTAXON_TO_ORGNAME ABBREV_TO_ORGNAME REVIEWED_TO_NUMBER EXISTENCE_TO_NUMBER
An object of class character of length 7.
An object of class character of length 4.
An object of class character of length 2.
An object of class numeric of length 4.
TAXON_TO_ORGNAME['9606'] ABBREV_TO_ORGNAME['HSA'] REVIEWED_TO_NUMBER['reviewed'] EXISTENCE_TO_NUMBER['Evidence at protein level']TAXON_TO_ORGNAME['9606'] ABBREV_TO_ORGNAME['HSA'] REVIEWED_TO_NUMBER['reviewed'] EXISTENCE_TO_NUMBER['Evidence at protein level']
Statistical models supported in autonomics
TESTSTESTS
An object of class character of length 5.
TESTSTESTS
Get / Set tpm matrix
tpm(object) ## S4 method for signature 'SummarizedExperiment' tpm(object) tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' tpm(object) <- valuetpm(object) ## S4 method for signature 'SummarizedExperiment' tpm(object) tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' tpm(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' tpm(object) <- value
object |
SummarizedExperiment |
value |
tpm matrix (features x samples) |
tpm matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, plot=FALSE) tpm(object) <- values(object) tpm(object)[1:3, 1:3]file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file, plot=FALSE) tpm(object) <- values(object) tpm(object)[1:3, 1:3]
twofactor sumexp
twofactor_sumexp()twofactor_sumexp()
SummarizedExperiment
Uncollapse data.table cols
uncollapse(dt, ..., sep = ";") recollapse(dt, by, sep = ";")uncollapse(dt, ..., sep = ";") recollapse(dt, by, sep = ";")
dt |
data.table |
... |
cols |
sep |
string |
by |
string |
(dt <- data.table::data.table( uniprot = 'Q9BQL6;Q96AC1;Q96AC1-3', protein = 'FERM1_HUMAN;FERM2_HUMAN', gene = 'FERMT1;FERMT2')) (dt %<>% uncollapse(protein, gene, sep = ';')) (dt %>% recollapse(by = 'uniprot'))(dt <- data.table::data.table( uniprot = 'Q9BQL6;Q96AC1;Q96AC1-3', protein = 'FERM1_HUMAN;FERM2_HUMAN', gene = 'FERMT1;FERMT2')) (dt %<>% uncollapse(protein, gene, sep = ';')) (dt %>% recollapse(by = 'uniprot'))
Get/Set value matrix
values(object) ## S4 method for signature 'SummarizedExperiment' values(object) values(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' values(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' values(object) <- valuevalues(object) ## S4 method for signature 'SummarizedExperiment' values(object) values(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' values(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' values(object) <- value
object |
SummarizedExperiment |
value |
ratio matrix (features x samples) |
value matrix (get) or updated object (set)
file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) values(object)[1:3, 1:3] values(object) <- 0 values(object)[1:3, 1:3]file <- system.file('extdata/billing19.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) values(object)[1:3, 1:3] values(object) <- 0 values(object)[1:3, 1:3]
Are varlevels unique
varlevels_dont_clash(object, ...) ## S3 method for class 'data.table' varlevels_dont_clash(object, vars = names(object), ...) ## S3 method for class 'SummarizedExperiment' varlevels_dont_clash(object, vars = svars(object), ...)varlevels_dont_clash(object, ...) ## S3 method for class 'data.table' varlevels_dont_clash(object, vars = names(object), ...) ## S3 method for class 'SummarizedExperiment' varlevels_dont_clash(object, vars = svars(object), ...)
object |
SummarizedExperiment or data.table |
... |
required for s3 dispatch |
vars |
character vector |
TRUE or FALSE
require(data.table) object1 <- data.table(expand.grid(genome = c('WT', 'MUT'), treat = c('control', 'drug'))) object2 <- data.table(expand.grid(mutant = c('YES', 'NO'), treated = c('YES', 'NO'))) varlevels_dont_clash(object1) varlevels_dont_clash(object2)require(data.table) object1 <- data.table(expand.grid(genome = c('WT', 'MUT'), treat = c('control', 'drug'))) object2 <- data.table(expand.grid(mutant = c('YES', 'NO'), treated = c('YES', 'NO'))) varlevels_dont_clash(object1) varlevels_dont_clash(object2)
Venn diagram full/consistent/random detects
venn_detects(object, by = "subgroup")venn_detects(object, by = "subgroup")
object |
SummarizedExperiment |
by |
svar (string) |
NULL
file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) venn_detects(object, 'subgroup')file <- system.file('extdata/fukuda20.proteingroups.txt', package = 'autonomics') object <- read_maxquant_proteingroups(file) venn_detects(object, 'subgroup')
Get/Set weight matrix
weights(object, ...) ## S4 method for signature 'SummarizedExperiment' weights(object) weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' weights(object) <- valueweights(object, ...) ## S4 method for signature 'SummarizedExperiment' weights(object) weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,matrix' weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,numeric' weights(object) <- value ## S4 replacement method for signature 'SummarizedExperiment,NULL' weights(object) <- value
object |
SummarizedExperiment |
... |
addtional params |
value |
ratio matrix (features x samples) |
weight matrix (get) or updated object (set)
file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) weights(object)[1:3, 1:2] weights(object) <- 1 weights(object)[1:3, 1:2]file <- system.file('extdata/billing19.rnacounts.txt', package = 'autonomics') object <- read_rnaseq_counts(file) weights(object)[1:3, 1:2] weights(object) <- 1 weights(object)[1:3, 1:2]
Write xl/ods
write_xl(object, xlfile, fitcoefs = autonomics::fitcoefs(object)) write_ods(object, odsfile, fitcoefs = autonomics::fitcoefs(object))write_xl(object, xlfile, fitcoefs = autonomics::fitcoefs(object)) write_ods(object, odsfile, fitcoefs = autonomics::fitcoefs(object))
object |
SummarizedExperiment |
xlfile |
file |
fitcoefs |
character vector |
odsfile |
file |
filepath
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') xlfile <- file.path(tempdir(), 'fukuda20.proteingroups.fdt.xlsx') odsfile <- file.path(tempdir(), 'fukuda20.proteingroups.fdt.ods') # write_xl(object, xlfile) # write_ods(object, odsfile)file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file, fit = 'limma') xlfile <- file.path(tempdir(), 'fukuda20.proteingroups.fdt.xlsx') odsfile <- file.path(tempdir(), 'fukuda20.proteingroups.fdt.ods') # write_xl(object, xlfile) # write_ods(object, odsfile)
Model based prediction
X( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit ) beta(object, fit = fits(object)[1])X( object, formula = default_formula(object), drop = varlevels_dont_clash(object, all.vars(formula)), codingfun = contr.treatment.explicit ) beta(object, fit = fits(object)[1])
object |
SummarizedExperiment or data.frame |
formula |
formula |
drop |
TRUE or FALSE |
codingfun |
function |
fit |
'limma', 'lm', 'lme', 'wilcoxon' |
beta matrix (nlevel x nfeature)
file <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(block = 'Subject') beta(object) # betas : nlevel x nfeature X(object) # design : nlevel x nlevel X(object) %*% beta(object) # response : nlevel x nfeaturefile <- system.file('extdata/atkin.metabolon.xlsx', package = 'autonomics') object <- read_metabolon(file) object %<>% fit_limma(block = 'Subject') beta(object) # betas : nlevel x nfeature X(object) # design : nlevel x nlevel X(object) %*% beta(object) # response : nlevel x nfeature
Change nondetect representation
zero_to_na(x, verbose = FALSE) nan_to_na(x, verbose = FALSE) na_to_zero(x, verbose = FALSE) inf_to_na(x, verbose = FALSE) minusinf_to_na(x, verbose = FALSE) na_to_string(x)zero_to_na(x, verbose = FALSE) nan_to_na(x, verbose = FALSE) na_to_zero(x, verbose = FALSE) inf_to_na(x, verbose = FALSE) minusinf_to_na(x, verbose = FALSE) na_to_string(x)
x |
matrix |
verbose |
logical(1) |
Updated matrix
matrix(c(0, 7), nrow=1) matrix(c(0, 7), nrow=1) %>% zero_to_na(verbose=TRUE) matrix(c(NA, 7), nrow=1) matrix(c(NA, 7), nrow=1) %>% na_to_zero(verbose=TRUE) matrix(c(NaN, 7), nrow=1) matrix(c(NaN, 7), nrow=1) %>% nan_to_na(verbose=TRUE) matrix(c(Inf, 7), nrow=1) matrix(c(Inf, 7), nrow=1) %>% inf_to_na(verbose=TRUE) matrix(c(-Inf, 7), nrow=1) matrix(c(-Inf, 7), nrow=1) %>% minusinf_to_na(verbose=TRUE)matrix(c(0, 7), nrow=1) matrix(c(0, 7), nrow=1) %>% zero_to_na(verbose=TRUE) matrix(c(NA, 7), nrow=1) matrix(c(NA, 7), nrow=1) %>% na_to_zero(verbose=TRUE) matrix(c(NaN, 7), nrow=1) matrix(c(NaN, 7), nrow=1) %>% nan_to_na(verbose=TRUE) matrix(c(Inf, 7), nrow=1) matrix(c(Inf, 7), nrow=1) %>% inf_to_na(verbose=TRUE) matrix(c(-Inf, 7), nrow=1) matrix(c(-Inf, 7), nrow=1) %>% minusinf_to_na(verbose=TRUE)