Package 'MetaProViz'

Description

Manually curated table for the amino acid alanine toshowcase pathways (wiki, reactome, etc.) and alanine IDs (chebi, hmdb, etc.) included in those pathways

Usage

alanine_pathways

Format

An object of class tbl_df (inherits from tbl, data.frame) with 204 rows and 5 columns.

Examples

data(alanine_pathways)
head(alanine_pathways)

Description

Biocrates kit feature information of the "MxP Quant 500 XL kit" that covers more than 1,000 metabolites with biochemical class information and the exported different metabolite IDs (HMDB, KEGG, etc.). information (INCHI, Key, etc.).

Usage

biocrates_features

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 1019 rows and 14 columns.

Examples

data(biocrates_features)
head(biocrates_features)

Description

Metabolomics workbench project PR001418, study ST002226 and ST002224 measured metabolites were assigned HMDB and KEGG IDs as well as one main metabolic pathway. metabolite trivial names. nitrogen supports renal cancer progression , Nature Communications 2022, doi:10.1038/s41467-022-35036-4

Usage

cellular_meta

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 199 rows and 5 columns.

Examples

data(cellular_meta)
head(cellular_meta)

Description

features

Usage

checkmatch_pk_to_data(
  data,
  input_pk,
  metadata_info = c(InputID = "HMDB", PriorID = "HMDB", grouping_variable = "term"),
  save_table = "csv",
  path = NULL
)

Arguments

Value

A list with three elements:

• data_summary — a data frame summarising matching results per input ID, including counts, conflicts, and recommended actions.

• GroupingVariable_summary — a detailed data frame showing matches grouped by the specified variable, with conflict annotations.

• data_long — a merged data frame of prior knowledge IDs and detected IDs in long format.

Examples

## Not run: 
data(cellular_meta)
DetectedIDs <- cellular_meta %>%
    dplyr::select("Metabolite", "HMDB") %>%
    tidyr::drop_na()
input_pathway <- translate_id(
    data = metsigdb_kegg(),
    metadata_info = c(
        InputID = "MetaboliteID",
        grouping_variable = "term"
    ),
    from = c("kegg"),
    to = c("hmdb")
)[["TranslatedDF"]] %>% tidyr::drop_na()
Res <- checkmatch_pk_to_data(
    data = DetectedIDs,
    input_pk = input_pathway,
    metadata_info = c(
        InputID = "HMDB",
        PriorID = "hmdb",
        grouping_variable = "term"
    )
)

## End(Not run)

Description

Uses enricher to run ORA on each of the metabolite cluster from any of the MCA functions using a pathway list

Usage

cluster_ora(
  data,
  metadata_info = c(ClusterColumn = "RG2_Significant", BackgroundColumn = "BG_method",
    PathwayTerm = "term", PathwayFeature = "Metabolite"),
  remove_background = TRUE,
  input_pathway,
  pathway_name = "",
  min_gssize = 10,
  max_gssize = 1000,
  save_table = "csv",
  path = NULL
)

Arguments

Value

Saves results as individual .csv files.

Examples

KEGG_Pathways <- metsigdb_kegg()
data(intracell_dma) # loads the object into your environment
DMAres <- intracell_dma %>%
    dplyr::filter(!is.na(KEGGCompound)) %>%
    tibble::column_to_rownames("KEGGCompound") %>%
    dplyr::select(-"Metabolite")
RES <- cluster_ora(
    data = DMAres,
    metadata_info = c(
        ClusterColumn = "Pathway",
        PathwayTerm = "term",
        PathwayFeature = "Metabolite"
    ),
    input_pathway = KEGG_Pathways,
    remove_background = FALSE
)

Description

Cluster terms in prior knowledge by set overlap

Usage

cluster_pk(
  data,
  metadata_info = c(metabolite_column = "MetaboliteID", pathway_column = "term"),
  similarity = c("jaccard", "overlap_coefficient", "correlation"),
  correlation_method = "pearson",
  input_format = c("long", "enrichment"),
  delimiter = "/",
  threshold = 0.5,
  plot_threshold = 0,
  clust = c("components", "community", "hierarchical"),
  hclust_method = "average",
  min = 2,
  plot_name = "ClusterGraph",
  max_nodes = 10000,
  min_degree = 1,
  node_size_column = NULL,
  show_density = FALSE,
  save_plot = "png",
  print_plot = FALSE,
  path = NULL
)

Arguments

Value

A list with:

Examples

# Create toy pathway data in long format
toy_pw <- data.frame(
    MetaboliteID = c("C1", "C2", "C3", "C1", "C2", "C4", "C3", "C4", "C5"),
    term = c("pA", "pA", "pA", "pB", "pB", "pB", "pC", "pC", "pC")
)

r <- cluster_pk(
    toy_pw,
    metadata_info = c(
        metabolite_column = "MetaboliteID",
        pathway_column = "term"
    ),
    input_format = "long",
    similarity = "jaccard",
    threshold = 0.1,
    clust = "community",
    min = 1,
    save_plot = NULL,
    print_plot = FALSE
)

Description

and Generate an UpSet Plot This function compares gene and/or metabolite features across multiple prior knowledge (PK) resources or, if a single resource is provided with a vector of column names in metadata_info, compares columns within that resource. In the multi-resource mode, each element in data represents a PK resource (either as a data frame or a recognized resource name) from which a set of features is extracted. A binary summary table is then constructed and used to create an UpSet plot. In the within-resource mode, a single data frame is provided (with data containing one element) and its metadata_info entry is a vector of column names to compare (e.g., binary indicators for different annotations). In this case, the function expects the data frame to have a grouping column named "Class" (or, alternatively, a column specified via the class_col attribute in metadata_info) that is used for grouping in the UpSet plot.

Usage

compare_pk(
  data,
  metadata_info = NULL,
  filter_by = c("both", "gene", "metabolite"),
  plot_name = "Overlap of Prior Knowledge Resources",
  name_col = "TrivialName",
  palette_type = "polychrome",
  save_plot = "svg",
  save_table = "csv",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

A list containing two elements:

• summary_table: A data frame representing either:

  • the binary summary matrix of feature presence/absence across multiple resources, or

  • the original data frame (augmented with binary columns and a None column) in within-resource mode.

• upset_plot: The UpSet plot object generated by the function.

Examples

## Not run: 
## Example 1: Within-Resource Comparison
## (Comparing Columns Within a Single data Frame)

# biocrates_features is a data frame with columns:
# "TrivialName", "CHEBI", "HMDB", "LIMID", and "Class".
# Here the "Class" column is used as the grouping variable
# in the UpSet plot.
data(biocrates_features)
data_single <- list(Biocft = biocrates_features)
metadata_info_single <- list(Biocft = c("CHEBI", "HMDB", "LIMID"))

res_single <-
compare_pk(
data = data_single, metadata_info = metadata_info_single,
plot_name = "Overlap of BioCrates Columns"
)

## Example 2: Custom data Frames with Custom Column Names

# Example with preloaded data frames and custom column names:
hallmarks_df <- data.frame(
feature = c("HMDB0001", "GENE1", "GENE2"),
stringsAsFactors = FALSE
)
gaude_df <- data.frame(
feature = c("GENE2", "GENE3"),
stringsAsFactors = FALSE
)
metalinks_df <- data.frame(
hmdb = c("HMDB0001", "HMDB0002"),
gene_symbol = c("GENE1", "GENE4"),
stringsAsFactors = FALSE
)
ramp_df <- data.frame(
class_source_id = c("HMDB0001", "HMDB0003"),
stringsAsFactors = FALSE
)
data <- list(
Hallmarks = hallmarks_df, Gaude = gaude_df,
MetalinksDB = metalinks_df, RAMP = ramp_df
)
metadata_info <- list(
Hallmarks = "feature", Gaude = "feature",
MetalinksDB = c("hmdb", "gene_symbol"),
RAMP = "class_source_id"
)
res <- compare_pk(
data = data, metadata_info = metadata_info,
filter_by = "metabolite"
)

## End(Not run)

Description

This function processes a data frame column by counting the number of entries within each cell. It considers both NA values and empty strings as zero entries, and categorizes each cell as "No ID", "Single ID", or "Multiple IDs" based on the count. A histogram is then generated to visualize the distribution of entry counts. scale_x_continuous

Usage

count_id(
  data,
  column,
  delimiter = ",\n    ",
  fill_colors = c(`No ID` = "#FB8072", `Single ID` = "#B3DE69", `Multiple IDs` =
    "#80B1D3"),
  binwidth = 1,
  title_prefix = NULL,
  save_plot = "svg",
  save_table = "csv",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

A list with two elements:

Examples

data(biocrates_features)
count_id(biocrates_features, "HMDB")

Description

Performs differential metabolite analysis to obtain Log2FC, p-value, adjusted p-value, and t-value when comparing two or multiple conditions.

Usage

dma(
  data,
  metadata_sample = NULL,
  metadata_info = c(Conditions = "Conditions", Numerator = NULL, Denominator = NULL),
  pval = "lmFit",
  padj = "fdr",
  metadata_feature = NULL,
  core = FALSE,
  vst = FALSE,
  shapiro = TRUE,
  bartlett = TRUE,
  transform = TRUE,
  save_plot = "svg",
  save_table = "csv",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List of lists. Depending on parameter settings, returns dma (data frame of each comparison), shapiro (includes data frame and plot), bartlett (includes data frame and histogram), vst (includes data frame and plot), and VolcanoPlot (plots of each comparison).

Examples

data(intracell_raw_se)
ResI <- dma(
    data = intracell_raw_se,
    metadata_info = c(
        Conditions = "Conditions", Numerator = NULL, Denominator = "HK2"
    )
)

data(intracell_raw)
Intra <- intracell_raw[-c(49:58), ] %>% tibble::column_to_rownames("Code")
ResI <- dma(
    data = Intra[, -c(1:3)],
    metadata_sample = Intra[, c(1:3)],
    metadata_info = c(
        Conditions = "Conditions", Numerator = NULL, Denominator = "HK2"
    )
)

Description

Manually curated list of aminoacids and aminoacid-related metabolites with corresponding metabolite identifiers (HMDB, KEGG, etc.) irrespective of chirality.

Usage

equivalent_features

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 34 rows and 7 columns.

Examples

data(equivalent_features)
head(equivalent_features)

Description

Find additional potential IDs for "kegg", "pubchem", "chebi", "hmdb"

Usage

equivalent_id(
  data,
  metadata_info = c(InputID = "MetaboliteID"),
  from = "hmdb",
  save_table = "csv",
  path = NULL
)

Arguments

Value

Input DF with additional column including potential additional IDs.

Examples

data(cellular_meta)
DetectedIDs <- cellular_meta %>% tidyr::drop_na()
Res <- equivalent_id(
    data = DetectedIDs,
    metadata_info = c(InputID = "HMDB"),
    from = "hmdb"
)

Description

gaude_pathways

Usage

gaude_pathways

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 1932 rows and 3 columns.

Examples

data(gaude_pathways)
head(gaude_pathways)

Description

Builds an exclusion table from hard-coded seed identifiers and translates them across ID systems (HMDB, KEGG, CHEBI, PUBCHEM).

Usage

get_exclusion_metabolites()

Value

A data frame with columns metabolite_id, class, and id_type.

Examples

## Not run: 
get_exclusion_metabolites()

## End(Not run)

Description

hallmarks

Usage

hallmarks

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 7322 rows and 2 columns.

Examples

data(hallmarks)
head(hallmarks)

Description

Metabolomics workbench project PR001418, study ST002224 where we performed differential metabolite analysis comparing intracellular metabolomics of 786-M1A versus HK2 cells. metabolite values used as input with row names being metabolitetrivial names. nitrogen supports renal cancer progression , Nature Communications 2022, doi:10.1038/s41467-022-35036-4

Usage

intracell_dma

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 179 rows and 14 columns.

Examples

data(intracell_dma)
head(intracell_dma)

Description

Metabolomics workbench project PR001418, study ST002224 where we exported integrated raw peak values of intracellular metabolomics of HK2 and ccRCC cell lines 786-O, 786-M1A and 786-M2A. -Conditions: Character vector indicating cell line identity - Analytical_Replicate: Integer replicate number for analytical replicates -Biological_Replicate: Integer replicate number for biological replicates - Additional numeric columns (183 in total) containing raw metabolite intensities nitrogen supports renal cancer progression, Nature Communications 2022, DOI:10.1038/s41467-022-35036-4.

Usage

intracell_raw

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 58 rows and 186 columns.

Examples

data(intracell_raw)
head(intracell_raw)

Description

Metabolomics workbench project PR001418, study ST002224 where we exported integrated raw peak values of intracellular metabolomics of HK2 and ccRCC cell lines 786-O, 786-M1A and 786-M2A converted into an se object. -Conditions: Character vector indicating cell line identity - Analytical_Replicate: Integer replicate number for analytical replicates -Biological_Replicate: Integer replicate number for biological replicates nitrogen supports renal cancer progression, Nature Communications 2022, DOI:10.1038/s41467-022-35036-4.

Usage

intracell_raw_se

Format

An object of class SummarizedExperiment with 182 rows and 58 columns.

Examples

data(intracell_raw_se)
head(intracell_raw_se)

Description

Gene to metabolite translation is based on mappings in Recon-3D (cosmosR).

Usage

make_gene_metab_set(
  input_pk,
  metadata_info = c(Target = "gene"),
  pk_name = NULL,
  save_table = "csv",
  path = NULL,
  exclude_metabolites = "all"
)

Arguments

Value

List of two data frames: "GeneMetabSet" and "MetabSet".

Examples

data(hallmarks)
make_gene_metab_set(hallmarks)

Description

Create Mapping Ambiguities between two ID types

Usage

mapping_ambiguity(
  data,
  from,
  to,
  grouping_variable = NULL,
  summary = FALSE,
  save_table = "csv",
  path = NULL
)

Arguments

Value

List with at least 4 DFs: 1-3) from-to-to: 1. MappingIssues, 2. MappingIssues summary, 3. Long summary (If summary=TRUE) & 4-6) to-to-from: 4. MappingIssues, 5. MappingIssues summary, 6. Long summary (If summary=TRUE) & 7) Combined summary table (If summary=TRUE)

Examples

## Not run: 
KEGG_Pathways <- metsigdb_kegg()
InputDF <- translate_id(
    data = KEGG_Pathways,
    metadata_info = c(
        InputID = "MetaboliteID",
        grouping_variable = "term"
    ),
    from = c("kegg"),
    to = c("pubchem")
)[["TranslatedDF"]]
Res <- mapping_ambiguity(
    data = InputDF,
    from = "MetaboliteID",
    to = "pubchem",
    grouping_variable = "term",
    summary = TRUE
)

## End(Not run)

Description

Performs metabolite clustering analysis and computes clusters based on regulatory rules between conditions.

Usage

mca_2cond(
  data_c1,
  data_c2,
  metadata_info_c1 = c(ValueCol = "Log2FC", StatCol = "p.adj", cutoff_stat = 0.05,
    ValueCutoff = 1),
  metadata_info_c2 = c(ValueCol = "Log2FC", StatCol = "p.adj", cutoff_stat = 0.05,
    ValueCutoff = 1),
  feature = "Metabolite",
  save_table = "csv",
  method_background = "C1&C2",
  path = NULL
)

Arguments

Value

List of two DFs: 1. summary of the cluster count and 2. the detailed information of each metabolites in the clusters.

Examples

data(intracell_raw)
Intra <- intracell_raw %>% tibble::column_to_rownames("Code")
Input <- dma(
    data = Intra[-c(49:58), -c(1:3)],
    metadata_sample = Intra[-c(49:58), c(1:3)],
    metadata_info = c(
        Conditions = "Conditions",
        Numerator = NULL,
        Denominator = "HK2"
    )
)

Res <- mca_2cond(
    data_c1 = Input[["dma"]][["786-O_vs_HK2"]],
    data_c2 = Input[["dma"]][["786-M1A_vs_HK2"]]
)

Description

Performs metabolite clustering analysis and computes clusters based on regulatory rules between intracellular and culture media metabolomics in core experiments.

Usage

mca_core(
  data_intra,
  data_core,
  metadata_info_intra = c(ValueCol = "Log2FC", StatCol = "p.adj", cutoff_stat = 0.05,
    ValueCutoff = 1),
  metadata_info_core = c(DirectionCol = "core", ValueCol = "Log2(Distance)", StatCol =
    "p.adj", cutoff_stat = 0.05, ValueCutoff = 1),
  feature = "Metabolite",
  save_table = "csv",
  method_background = "Intra&core",
  path = NULL
)

Arguments

Value

List of two DFs: 1. summary of the cluster count and 2. the detailed information of each metabolites in the clusters.

Examples

data(intracell_dma)

# Create mock CoRe DMA results with required columns
core_dma <- data.frame(
    Metabolite = intracell_dma$Metabolite[1:50],
    `Log2(Distance)` = runif(50, -2, 2),
    p.adj = runif(50, 0, 0.1),
    core = sample(c("Consumption", "Release"), 50, replace = TRUE),
    check.names = FALSE
)

Res <- mca_core(
    data_intra = as.data.frame(intracell_dma),
    data_core = core_dma,
    save_table = NULL
)

Description

Manually curated table defining the flow of information of the Conusuption-Release and Intracellular metabolomics biological regulatory clusters Regulatory labels from the different grouping methods. columns (RG1-RG3)

Usage

mca_core_rules

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 108 rows and 7 columns.

Examples

data(mca_core_rules)
head(mca_core_rules)

Description

Manually curated table defining the flow of information of the two condition biological regulatory clusters Regulatory labels from the different grouping methods. columns (RG1-RG3)

Usage

mca_twocond_rules

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 36 rows and 5 columns.

Examples

data(mca_twocond_rules)
head(mca_twocond_rules)

Description

Metabolomics workbench project PR001418, study ST002226 where we exported integrated raw peak values of intracellular metabolomics of HK2 and cccRCC cell lines 786-O, 786-M1A, 786-M2A, OS-RC-2, OS-LM1 and RFX-631. a numeric column for each measured metabolite (raw data) nitrogen supports renal cancer progression , Nature Communications 2022, doi:10.1038/s41467-022-35036-4

Usage

medium_raw

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 44 rows and 77 columns.

Examples

data(medium_raw)
head(medium_raw)

Description

Meta prior-knowledge

Usage

meta_pk(
  data,
  metadata_sample,
  metadata_info = NULL,
  save_table = "csv",
  path = NULL
)

Arguments

Value

DF with prior knowledge based on patient metadata

Examples

data(tissue_norm_se)
Res <- meta_pk(tissue_norm_se)

data(tissue_norm)
Tissue_Norm <- tissue_norm %>% tibble::column_to_rownames("Code")
Res <- meta_pk(
    data = Tissue_Norm[, -c(1:13)],
    metadata_sample = Tissue_Norm[, c(2, 4:5, 12:13)]
)

Description

Performs PCA analysis on input data and combines it with sample metadata to run ANOVA tests for identifying significant differences between groups.

Usage

metadata_analysis(
  data,
  metadata_sample = NULL,
  scaling = TRUE,
  percentage = 0.1,
  cutoff_stat = 0.05,
  cutoff_variance = 1,
  save_table = "csv",
  save_plot = "svg",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List of DFs: prcomp results, loadings, top-Bottom features, annova results, results summary

Examples

data(tissue_norm)
d <- tissue_norm[1:100, -c(2:14)] %>% tibble::column_to_rownames("Code")
d <- d[, vapply(d, function(x) length(unique(x)) > 1, logical(1))]
Res <- metadata_analysis(
    data = d,
    metadata_sample = tissue_norm[1:100, c(1, 5:6)] %>%
        tibble::column_to_rownames("Code"),
    save_plot = NULL,
    save_table = NULL,
    print_plot = FALSE
)

Description

MetaProViz (Metabolomics Processing, functional analysis and Visualization), a free open-source R-package that provides mechanistic hypotheses from metabolomics data by integrating prior knowledge from literature with metabolomics. MetaProViz offers an interactive framework consisting of five modules: Processing, differential analysis, prior knowledge access and refactoring, functional analysis and visualization of both intracellular and exometabolomics (consumption-release/core data).

Author(s)

Christina Schmidt <\email{[email protected]}> and Denes Turei <\email{[email protected]}> and Dimitrios Prymidis and Macabe Daley and Julio Saez-Rodriguez and Christian Frezza

See Also

Useful links:

• https://saezlab.github.io/MetaProViz

• Report bugs at https://github.com/saezlab/MetaProViz/issues

Description

Current config file path of MetaProViz

Usage

metaproviz_config_path(user = FALSE)

Arguments

Value

Character: path to the config file.

Examples

metaproviz_config_path()

Description

Load the package configuration from a config file

Usage

metaproviz_load_config(path = NULL, title = "default", user = FALSE, ...)

Arguments

Value

Invisibly returns the config as a list.

Examples

metaproviz_load_config()

Description

Browse the current MetaProViz log file

Usage

metaproviz_log()

Value

Returns NULL.

See Also

metaproviz_logfile

Examples

## Not run: 
metaproviz_log()
# then you can browse the log file, and exit with `q`

## End(Not run)

Description

Path to the current MetaProViz log file

Usage

metaproviz_logfile()

Value

Character: path to the current logfile, or NULL if no logfile is available.

See Also

metaproviz_log

Examples

metaproviz_logfile()
# [1] "path/metaproviz/metaproviz-log/metaproviz-20210309-1642.log"

Description

Restore the built-in default values of all config parameters of MetaProViz

Usage

metaproviz_reset_config(save = NULL, reset_all = FALSE)

Arguments

Value

The config as a list.

See Also

metaproviz_load_config, metaproviz_save_config

Examples

# restore the defaults and write them to the default config file:
metaproviz_reset_config()
metaproviz_save_config()

Description

Save the current package configuration

Usage

metaproviz_save_config(path = NULL, title = "default", local = FALSE)

Arguments

Value

Returns NULL.

Examples

# restore the defaults and write them to the default config file:
metaproviz_reset_config()
metaproviz_save_config()

Description

Sets the log level for the package logger

Usage

metaproviz_set_loglevel(level, target = "logfile")

Arguments

Value

Returns NULL.

Examples

metaproviz_set_loglevel(logger::FATAL, target = "console")

Description

Metabolite chemical classes from RaMP DB

Usage

metsigdb_chemicalclass(
  version = "2.5.4",
  save_table = "csv",
  path = NULL,
  exclude_metabolites = "all"
)

Arguments

Value

A data frame containing the Prior Knowledge.

Examples

ChemicalClass <- metsigdb_chemicalclass()

Description

KEGG pathways

Usage

metsigdb_kegg(exclude_metabolites = "all")

Arguments

Value

A data frame containing the KEGG pathways suitable for ORA.

Examples

metsigdb_kegg()

Description

Retrieves metabolite-cancer associations from MACDB via OmnipathR and summarizes them to unique metabolite-cancer associations (by term and Metabolite_PubchemID).

Usage

metsigdb_macdb(exclude_metabolites = "all")

Arguments

Value

A data frame with one row per unique metabolite-cancer association, collapsed metadata columns, and summary metrics (evidence_count, significance_count, association_score).

Description

Annotated metabolite-protein interactions from MetalinksDB

Usage

metsigdb_metalinks(
  types = NULL,
  cell_location = NULL,
  tissue_location = NULL,
  biospecimen_location = NULL,
  disease = NULL,
  pathway = NULL,
  hmdb_ids = NULL,
  uniprot_ids = NULL,
  save_table = "csv",
  path = NULL,
  exclude_metabolites = "all"
)

Arguments

Value

A data frame of metabolite-protein interactions from MetalinksDB.

Examples

metsigdb_metalinks()

Description

Queries the OmniPath resource through OmniPathR to obtail Reactome pathway level metabolite sets.

Usage

metsigdb_reactome(
  species = "Homo sapiens",
  pathway_ids = NULL,
  out_path = NULL,
  exclude_metabolites = "all"
)

Arguments

Value

A tibble in long format containing one row per metabolite for the Reactome pathways.

Examples

## Not run: 
df <- metsigdb_reactome()
head(df)

## End(Not run)

Description

Retrieves pathway to metabolite mappings from WikiPathways (via wikipathways_metabolites_sparql()) via OmnipathR and returns a long-format table with one metabolite identifier per row.

Usage

metsigdb_wikipathways(species = "Homo sapiens", exclude_metabolites = "all")

Arguments

Value

A tibble in long format with columns pathway_id, pathway_name, pathway_url, n_metabolites_in_pathway, and metabolite_id.

Description

Find metabolites with high variability across total pool samples

Usage

pool_estimation(
  data,
  metadata_sample = NULL,
  metadata_info = NULL,
  cutoff_cv = 30,
  save_plot = "svg",
  save_table = "csv",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List with two elements: DF (including input and output table) and Plot (including all plots generated)

Examples

data(intracell_raw_se)
Res <- pool_estimation(
    data = intracell_raw_se,
    metadata_info = c(PoolSamples = "Pool", Conditions = "Conditions")
)

data(intracell_raw)
Intra <- intracell_raw %>% tibble::column_to_rownames("Code")
Res <- pool_estimation(
    data = Intra[, -c(1:3)],
    metadata_sample = Intra[, c(1:3)],
    metadata_info = c(PoolSamples = "Pool", Conditions = "Conditions")
)

Description

Applies modular normalization including 80% filtering rule, total-ion count normalization, missing value imputation, and outlier detection using Hotelling's T2 test.

Usage

processing(
  data,
  metadata_sample = NULL,
  metadata_info = c(Conditions = "Conditions"),
  featurefilt = "Modified",
  cutoff_featurefilt = 0.8,
  tic = TRUE,
  mvi = TRUE,
  mvi_percentage = 50,
  hotellins_confidence = 0.99,
  core = FALSE,
  save_plot = "svg",
  save_table = "csv",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List with two elements: DF (all output tables generated) and Plot (all plots generated).

Examples

data(intracell_raw)
Intra <- intracell_raw %>% tibble::column_to_rownames("Code")
ResI <- processing(
    data = Intra[1:30, -c(1:3)],
    metadata_sample = Intra[1:30, c(1:3)],
    metadata_info = c(
        Conditions = "Conditions",
        Biological_Replicates = "Biological_Replicates"
    ),
    save_plot = NULL,
    save_table = NULL,
    print_plot = FALSE
)

Description

Merges the analytical replicates of an experiment

Usage

replicate_sum(
  data,
  metadata_sample = NULL,
  metadata_info = c(Conditions = "Conditions", Biological_Replicates =
    "Biological_Replicates", Analytical_Replicates = "Analytical_Replicates"),
  save_table = "csv",
  path = NULL
)

Arguments

Value

DF with the merged analytical replicates

Examples

data(intracell_raw_se)
Res <- replicate_sum(data = intracell_raw_se)

data(intracell_raw)
Intra <- intracell_raw %>% tibble::column_to_rownames("Code")
Res <- replicate_sum(
    data = Intra[-c(49:58), -c(1:3)],
    metadata_sample = Intra[-c(49:58), c(1:3)]
)

Description

Can be applied on the result of differential metabolite analysis (DMA), requires a pathway list (from databases).

Usage

standard_ora(
  data,
  metadata_info = c(pvalColumn = "p.adj", percentageColumn = "t.val", PathwayTerm =
    "term", PathwayFeature = "Metabolite"),
  cutoff_stat = 0.05,
  cutoff_percentage = 10,
  input_pathway,
  pathway_name = "",
  min_gssize = 10,
  max_gssize = 1000,
  save_table = "csv",
  path = NULL
)

Arguments

Value

Saves results as individual .csv files.

Examples

KEGG_Pathways <- metsigdb_kegg()
data(intracell_dma) # loads the object into your environment
DMAres <- intracell_dma %>%
    dplyr::filter(!is.na(KEGGCompound)) %>%
    tibble::column_to_rownames("KEGGCompound") %>%
    dplyr::select(-"Metabolite")
RES <- standard_ora(
    data = DMAres,
    input_pathway = KEGG_Pathways
)

Description

We performed differential metabolite analysis comparing ccRCC tissue versus adjacent normal tissue using median normalised data from the supplementary table 2 of Hakimi et. al.(="Tissue_Norm"). metabolite values used as input with row names being metabolite trivial names. doi:10.1016/j.ccell.2015.12.004

Usage

tissue_dma

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 570 rows and 17 columns.

Examples

data(tissue_dma)
head(tissue_dma)

Description

We performed differential metabolite analysis comparing ccRCC tissue versus adjacent normal tissue of the patient's subset of old patient's (age > 58 years) using median normalised data from the supplementary table 2 of Hakimi et. al.(="Tissue_Norm"). metabolite values used as input with row names being metabolite trivial names. doi:10.1016/j.ccell.2015.12.004

Usage

tissue_dma_old

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 570 rows and 17 columns.

Examples

data(tissue_dma_old)
head(tissue_dma_old)

Description

We performed differential metabolite analysis comparing ccRCC tissue versus adjacent normal tissue of the patient's subset of young patient's (age <42 years) using median normalised data from the supplementary table 2 of Hakimi et. al.(="Tissue_Norm"). metabolite values used as input with row names being metabolite trivial names. doi:10.1016/j.ccell.2015.12.004

Usage

tissue_dma_young

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 570 rows and 17 columns.

Examples

data(tissue_dma_young)
head(tissue_dma_young)

Description

In Hakimi et. al. metabolites were assigned to metabolite IDs, pathways, platform, mass and other fetaure metainformation. row names being metabolite trivial names. doi:10.1016/j.ccell.2015.12.004

Usage

tissue_meta

Format

An object of class tbl_df (inherits from tbl, data.frame) with 877 rows and 11 columns.

Examples

data(tissue_meta)
head(tissue_meta)

Description

This is median normalised data from the supplementary table 2 of Hakimi et al with metabolomic profiling on 138 matched clear cell renal cell carcinoma (ccRCC)/normal tissue pairs. measured metabolite (normalised data) doi:10.1016/j.ccell.2015.12.004

Usage

tissue_norm

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 276 rows and 584 columns.

Examples

data(tissue_norm)
head(tissue_norm)

Description

This is median normalised data from the supplementary table 2 of Hakimi et al with metabolomic profiling on 138 matched clear cell renal cell carcinoma (ccRCC)/normal tissue pairs. coldata include patient metadata (e.g. age, gender, sage, etc.) doi:10.1016/j.ccell.2015.12.004

Usage

tissue_norm_se

Format

An object of class SummarizedExperiment with 570 rows and 276 columns.

Examples

data(tissue_norm_se)
head(tissue_norm_se)

Description

The processed proteomics data was downloaded from the supplementary table 3 of Mora & Schmidt et. al., which used the study from Clark et. al. under Proteomics data Commons PDC000127. on their regulation regulation in renal cancer, Genome Medicine 2024, doi:10.1186/s13073-024-01415-3 Clark et. al, Integrated proteogenomic characterization of clear cell renal cell carcinoma, Cell 2019, doi:10.1016/j.cell.2019.10.007

Usage

tissue_tvn_proteomics

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 8769 rows and 10 columns.

Examples

data(tissue_tvn_proteomics)
head(tissue_tvn_proteomics)

Description

The processed transcriptomics data was downloaded from the supplementary table 3 of Mora & Schmidt et. al., which used the study from Clark et. al. under Proteomics data Commons PDC000127. on their regulation regulation in renal cancer, Genome Medicine 2024, doi:10.1186/s13073-024-01415-3 Clark et. al, Integrated proteogenomic characterization of clear cell renal cell carcinoma, Cell 2019, doi:10.1016/j.cell.2019.10.007

Usage

tissue_tvn_rnaseq

Format

An object of class spec_tbl_df (inherits from tbl_df, tbl, data.frame) with 29283 rows and 10 columns.

Examples

data(tissue_tvn_rnaseq)
head(tissue_tvn_rnaseq)

Description

Translate IDs to/from KEGG, PubChem, Chebi, HMDB

Usage

translate_id(
  data,
  metadata_info = c(InputID = "MetaboliteID", grouping_variable = "term"),
  from = "kegg",
  to = c("pubchem", "chebi", "hmdb", "cas"),
  summary = FALSE,
  save_table = "csv",
  path = NULL
)

Arguments

Value

List with at least three DFs: 1) Original data and the new column of translated ids spearated by comma. 2) Mapping information between Original ID to Translated ID. 3) Mapping summary between Original ID to Translated ID.

Examples

## Not run: 
KEGG_Pathways <- metsigdb_kegg()
Res <- translate_id(
    data = KEGG_Pathways,
    metadata_info = c(
        InputID = "MetaboliteID",
        grouping_variable = "term"
    ),
    from = c("kegg"),
    to = c("pubchem", "hmdb")
)

## End(Not run)

Description

Traverses pairwise RaMP mappings from OmnipathR::ramp_id_mapping_table() across selected metabolite ID types until no new IDs are found.

Usage

traverse_ids(
  data,
  id_types = c("HMDB", "KEGG", "CHEBI", "PUBCHEM"),
  delimiter = c(";", ","),
  save_table = "csv",
  path = NULL,
  verbose = FALSE
)

Arguments

Value

Named list with three data frames:

Examples

input_df <- data.frame(
    name = c(
        "Acetone ; Propanal ; acetone",
        "Acetaldehyde oxime ; HMDB01122",
        "acetate",
        "Urea"
    ),
    all_ids = c(
        "HMDB01659 ; HMDB03366 ; C00207",
        "HMDB03656 ; HMDB01122",
        "C00033",
        "C00086"
     ),
     HMDB = c(
        "HMDB01659; HMDB03366",
        "HMDB03656; HMDB01122",
        NA,
        NA
     ),
     KEGG = c(
        "C00207",
        NA,
        "C00033",
        "C00086"
     ),
     CHEBI = NA,
     stringsAsFactors = FALSE
)

res <- traverse_ids(input_df)

df_translated <- res$ExpandedDF
head(df_translated)

Description

Graph visualization for clustered terms

Usage

viz_graph(
  similarity_matrix,
  clusters,
  plot_threshold = 0.5,
  plot_name = "ClusterGraph",
  max_nodes = NULL,
  min_degree = NULL,
  node_sizes = NULL,
  show_density = FALSE,
  save_plot = "svg",
  print_plot = TRUE,
  path = NULL,
  plot_width = 3000,
  plot_height = 2000,
  plot_unit = "px"
)

Arguments

Value

Graph plot as a ggplot object.

Examples

# Create toy similarity matrix and clusters
sim <- matrix(
    c(1, 0.8, 0.3, 0.1,
      0.8, 1, 0.2, 0.1,
      0.3, 0.2, 1, 0.7,
      0.1, 0.1, 0.7, 1),
    nrow = 4,
    dimnames = list(
        c("Pathway_A", "Pathway_B", "Pathway_C", "Pathway_D"),
        c("Pathway_A", "Pathway_B", "Pathway_C", "Pathway_D")
    )
)
clusters <- c(
    Pathway_A = "1", Pathway_B = "1",
    Pathway_C = "2", Pathway_D = "2"
)
viz_graph(
    sim, clusters,
    plot_threshold = 0.2,
    save_plot = NULL,
    print_plot = FALSE
)

Description

Heatmap visualization

Usage

viz_heatmap(
  data,
  metadata_info = NULL,
  metadata_sample = NULL,
  metadata_feature = NULL,
  plot_name = "",
  scale = "row",
  save_plot = "svg",
  enforce_featurenames = FALSE,
  enforce_samplenames = FALSE,
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List with two elements: Plot and Plot_Sized

Examples

data(intracell_raw_se)
Res <- viz_heatmap(data = intracell_raw_se)

data(intracell_raw)
Intra <- intracell_raw %>% tibble::column_to_rownames("Code")
Res <- viz_heatmap(data = Intra[, -c(1:3)])

Description

PCA plot visualization

Usage

viz_pca(
  data,
  metadata_info = NULL,
  metadata_sample = NULL,
  color_palette = NULL,
  scale_color = "discrete",
  shape_palette = NULL,
  show_loadings = FALSE,
  scaling = TRUE,
  pcx = 1,
  pcy = 2,
  theme = NULL,
  plot_name = "",
  save_plot = "svg",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List with two elements: Plot and Plot_Sized

Examples

data(intracell_raw_se)
Res <- viz_pca(intracell_raw_se)

data(intracell_raw)
Intra <- intracell_raw[, -c(2:4)] %>% tibble::column_to_rownames("Code")
Res <- viz_pca(Intra)

Description

Bar, Box or Violin plot in Superplot style visualization

Usage

viz_superplot(
  data,
  metadata_sample = NULL,
  metadata_info = c(Conditions = "Conditions", Superplot = NULL),
  plot_type = "Box",
  plot_name = "",
  plot_conditions = NULL,
  stat_comparison = NULL,
  pval = NULL,
  padj = NULL,
  xlab = NULL,
  ylab = NULL,
  theme = NULL,
  color_palette = NULL,
  color_palette_dot = NULL,
  save_plot = "svg",
  print_plot = TRUE,
  path = NULL
)

Arguments

Value

List with two elements: Plot and Plot_Sized

Examples

data(intracell_raw_se)
# only plot the first 2 metabolites
Res <- viz_superplot(data = intracell_raw_se[1:2, , drop = FALSE])

data(intracell_raw)
Intra <- intracell_raw[, c(1:6)] %>% tibble::column_to_rownames("Code")
Res <- viz_superplot(
    data = Intra[, -c(1:3)],
    metadata_sample = Intra[, c(1:3)]
)

Description

Volcano plot

Usage

viz_volcano(
  plot_types = "Standard",
  data,
  metadata_info = NULL,
  metadata_feature = NULL,
  data2 = NULL,
  y = "p.adj",
  x = "Log2FC",
  xlab = NULL,
  ylab = NULL,
  cutoff_x = 0.5,
  cutoff_y = 0.05,
  connectors = FALSE,
  select_label = "",
  plot_name = "",
  subtitle = "",
  name_comparison = c(data = "Cond1", data2 = "Cond2"),
  color_palette = NULL,
  shape_palette = NULL,
  theme = NULL,
  save_plot = "svg",
  path = NULL,
  feature = "Metabolites",
  print_plot = TRUE
)

Arguments

Value

List with two elements: Plot and Plot_Sized

Examples

data(intracell_dma)
Intra <- intracell_dma %>% tibble::column_to_rownames("Metabolite")
Res <- viz_volcano(data = Intra)