Package 'GenomicPlot'

Description

This is a helper function for performing one-way ANOVA analysis and post hoc Tukey's Honest Significant Differences tests

Usage

aov_TukeyHSD(df, xc = "Group", yc = "Intensity", op = NULL, verbose = FALSE)

Arguments

Value

a list of two elements, the first is the p-value of ANOVA test and the second is a matrix of the output of TukeyHSD tests

Note

used in plot_locus

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rnorm(20, mean = 2, sd = 1), rnorm(30, mean = 3, sd = 1))
)

out <- aov_TukeyHSD(stat_df, xc = "Feature")
out

Description

Make sure the coordinates of GRanges are within the boundaries of chromosomes, and trim anything that goes beyond. Also, remove entries whose seqname is not in the seqname of a query GRanges.

Usage

check_constraints(gr, genome, queryRle = NULL)

Arguments

Value

a GRanges object

Author(s)

Shuye Pu

Examples

subject <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 400, 2e+8)),
    strand = c("+", "+", "-", "-")
)

g <- check_constraints(gr = subject, genome = "hg19")
identical(g, subject)

subject1 <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 400, 28)),
    strand = c("+", "+", "-", "-")
)

g1 <- check_constraints(gr = subject1, genome = "hg19")
identical(g1, subject1)

Description

This is a helper function for creating custom TxDb object from a GTF/GFF file. Mitochondrial chromosome is excluded.

Usage

custom_TxDb_from_GTF(gtfFile, genome = "hg19")

Arguments

Value

a TxDb object defined in the GenomicFeatures package.

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")

Description

Plot violin plot with boxplot components for data with one or two factors, p-value significance levels are displayed, "***" = 0.001, "**" = 0.01, "*" = 0.05.

Usage

draw_boxplot_by_factor(
  stat_df,
  xc = "Feature",
  yc = "Intensity",
  fc = xc,
  comp = list(c(1, 2)),
  stats = "wilcox.test",
  Xlab = xc,
  Ylab = yc,
  nf = 1
)

Arguments

Value

a ggplot object

Note

used by plot_locus, plot_locus_with_random, plot_region

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rnorm(20, 2, 0.5), rnorm(30, 3, 0.6))
)
p <- draw_boxplot_by_factor(stat_df,
    xc = "Feature", yc = "Intensity",
    Ylab = "Signal Intensity"
)
p

Description

Plot boxplot without outliers, useful when outliers have a wide range and the median is squeezed at the bottom of the plot. The p-value significance level is the same as those in draw_boxplot_by_factor, but not displayed.

Usage

draw_boxplot_wo_outlier(
  stat_df,
  xc = "Feature",
  yc = "Intensity",
  fc = xc,
  comp = list(c(1, 2)),
  stats = "wilcox.test",
  Xlab = xc,
  Ylab = yc,
  nf = 1
)

Arguments

Value

a ggplot object

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rnorm(20, 2), rnorm(30, 3))
)

p <- draw_boxplot_wo_outlier(stat_df,
    xc = "Feature", yc = "Intensity",
    Ylab = "Signal Intensity"
)
p

Description

Place violin plot, boxplot without outliers, mean+se barplot and quantile plot on the same page

Usage

draw_combo_plot(
  stat_df,
  xc = "Feature",
  yc = "Intensity",
  comp = list(c(1, 2)),
  Xlab = xc,
  Ylab = yc,
  stats = "wilcox.test",
  fc = xc,
  Ylim = NULL,
  title = "",
  nf = 1
)

Arguments

Value

a ggplot object

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(200, 300)),
    Intensity = c(rnorm(200, 2, 5), rnorm(300, 3, 5)),
    Height = c(rnorm(200, 5, 5), rnorm(300, 1, 5))
)
stat_df_long <- tidyr::pivot_longer(stat_df,
    cols = c(Intensity, Height),
    names_to = "type", values_to = "value"
)

print(draw_combo_plot(stat_df_long,
    xc = "Feature", yc = "value", fc = "type",
    Ylab = "value", comp = list(c(1, 2), c(3, 4), c(1, 3), c(2, 4)), nf = 2
))

Description

Plot lines with standard error as the error band

Usage

draw_locus_profile(
  plot_df,
  xc = "Position",
  yc = "Intensity",
  cn = "Query",
  sn = NULL,
  Xlab = "Center",
  Ylab = "Signal Intensity",
  shade = FALSE,
  hl = c(0, 0)
)

Arguments

Value

a ggplot object

Note

used by plot_locus, plot_locus_with_random

Author(s)

Shuye Pu

Examples

library(dplyr)
Reference <- rep(rep(c("Ref1", "Ref2"), each = 100), 2)
Query <- rep(c("Query1", "Query2"), each = 200)
Position <- rep(seq(-50, 49), 4)
Intensity <- rlnorm(400)
se <- runif(400)
df <- data.frame(Intensity, se, Position, Query, Reference) %>%
    mutate(lower = Intensity - se, upper = Intensity + se) %>%
    mutate(Group = paste(Query, Reference, sep = ":"))

p <- draw_locus_profile(df, cn = "Group", shade = TRUE, hl = c(-10, 20))
p

Description

Make a complex heatmap with column annotations

Usage

draw_matrix_heatmap(
  fullMatrix,
  dataName = "geneData",
  labels_col = NULL,
  levels_col = NULL,
  ranking = "Sum",
  ranges = NULL,
  verbose = FALSE
)

Arguments

Value

a grob object

Author(s)

Shuye Pu

Examples

fullMatrix <- matrix(rnorm(10000), ncol = 100)
for (i in seq_len(80)) {
    fullMatrix[i, 16:75] <- runif(60) + i
}
labels_col <- as.character(seq_len(100))
levels_col <- c("start", "center", "end")
names(labels_col) <- rep(levels_col, c(15, 60, 25))

draw_matrix_heatmap(fullMatrix, dataName = "test", labels_col, levels_col,
  ranges = c(-2, 0, 20))

Description

Plot barplot for mean with standard error bars, no p-value significance levels are displayed, but ANOVA p-value is provided as tag and TukeyHSD test are displayed as caption.

Usage

draw_mean_se_barplot(
  stat_df,
  xc = "Feature",
  yc = "Intensity",
  fc = xc,
  comp = list(c(1, 2)),
  Xlab = xc,
  Ylab = yc,
  Ylim = NULL,
  nf = 1
)

Arguments

Value

a ggplot object

Note

used by plot_locus, plot_locus_with_random

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rnorm(20, 2), rnorm(30, 3))
)
p <- draw_mean_se_barplot(stat_df,
    xc = "Feature", yc = "Intensity",
    Ylab = "Intensity"
)
p

Description

Plot quantiles as y-axis, and values as x-axis. Same as 'geom_ecdf', but allows sub-grouping by a second factor.

Usage

draw_quantile_plot(
  stat_df,
  xc = "Feature",
  yc = "Intensity",
  Ylab = yc,
  fc = xc
)

Arguments

Value

a ggplot object

Note

used by plot_locus, plot_locus_with_random

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rnorm(20, 2, 5), rnorm(30, 3, 5)),
    Height = c(rnorm(20, 5, 5), rnorm(30, 1, 5))
)
stat_df_long <- tidyr::pivot_longer(stat_df,
    cols = c(Intensity, Height), names_to = "type",
    values_to = "value"
)

print(draw_quantile_plot(stat_df, xc = "Feature", yc = "Intensity"))
print(draw_quantile_plot(stat_df, xc = "Feature", yc = "Height"))
print(draw_quantile_plot(stat_df_long,
    xc = "Feature", yc = "value",
    fc = "type", Ylab = "value"
))

Description

Plot cumulative sum over rank as line plot, both cumulative sum and rank are scaled between 0 and 1. This is the same as the fingerprint plot of the deepTools.

Usage

draw_rank_plot(stat_df, xc = "Feature", yc = "Intensity", Ylab = yc)

Arguments

Value

a ggplot object

Author(s)

Shuye Pu

Examples

stat_df <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Intensity = c(rlnorm(20, 5, 5), rlnorm(30, 1, 5))
)
stat_df1 <- data.frame(
    Feature = rep(c("A", "B"), c(20, 30)),
    Height = c(rnorm(20, 5, 5), rnorm(30, 1, 5))
)

print(draw_rank_plot(stat_df,
    xc = "Feature", yc = "Intensity",
    Ylab = "Intensity"
))
print(draw_rank_plot(stat_df1,
    xc = "Feature", yc = "Height",
    Ylab = "Height"
))

Description

Plot a gene centered polygon for demarcating gene and its upstream and downstream regions

Usage

draw_region_landmark(featureNames, vx, xmax)

Arguments

Value

a ggplot object

Note

used by plot_5parts_metagene, plot_region

Author(s)

Shuye Pu

Examples

fn <- c("5'UTR", "CDS", "3'UTR")
mark <- c(1, 5, 20)
xmax <- 25

p <- draw_region_landmark(featureNames = fn, vx = mark, xmax = xmax)

Description

Plot sub-region labels under the landmark

Usage

draw_region_name(featureNames, scaled_bins, xmax)

Arguments

Value

a ggplot object

Note

used by plot_5parts_metagene, plot_region

Author(s)

Shuye Pu

Examples

fn <- c("5'UTR", "CDS", "3'UTR")
bins <- c(5, 15, 5)
xmax <- 25

p <- draw_region_name(featureNames = fn, scaled_bins = bins, xmax = xmax)

Description

Plot lines with standard error as the error band

Usage

draw_region_profile(
  plot_df,
  xc = "Position",
  yc = "Intensity",
  cn = "Query",
  sn = NULL,
  Ylab = "Signal Intensity",
  vx
)

Arguments

Value

a ggplot object

Note

used by plot_5parts_metagene, plot_region

Author(s)

Shuye Pu

Examples

library(dplyr)
Reference <- rep(rep(c("Ref1", "Ref2"), each = 100), 2)
Query <- rep(c("Query1", "Query2"), each = 200)
Position <- rep(seq_len(100), 4)
Intensity <- rlnorm(400)
se <- runif(400)
df <- data.frame(Intensity, se, Position, Query, Reference) %>%
    mutate(lower = Intensity - se, upper = Intensity + se) %>%
    mutate(Group = paste(Query, Reference, sep = ":"))
vx <- c(1, 23, 70)

p <- draw_region_profile(df, cn = "Group", vx = vx)
p

Description

Plot profile on top of heatmap, and align feature labels.

Usage

draw_stacked_plot(plot_list, heatmap_list)

Arguments

Value

a null value

Note

used by plot_locus, plot_5parts_metagene, plot_region

Author(s)

Shuye Pu

Description

Plot lines with standard error as the error band, also plots number of regions having non-zero signals

Usage

draw_stacked_profile(
  plot_df,
  xc = "Position",
  yc = "Intensity",
  cn = "Query",
  ext = c(0, 0, 0, 0),
  hl = c(0, 0, 0, 0),
  atitle = "title",
  insert = 0,
  Ylab = "Signal Intensity",
  shade = FALSE,
  stack = TRUE
)

Arguments

Value

a ggplot object

Note

used by plot_start_end, plot_start_end_with_random

Author(s)

Shuye Pu

Examples

library(dplyr)
Reference <- rep(rep(c("Ref1", "Ref2"), each = 100), 2)
Query <- rep(c("Query1", "Query2"), each = 200)
Position <- rep(seq(-50, 49), 4)
Intensity <- rlnorm(400)
se <- runif(400)
start_df <- data.frame(Intensity, se, Position, Query, Reference) %>%
    mutate(lower = Intensity - se, upper = Intensity + se) %>%
    mutate(Group = paste(Query, Reference, sep = ":")) %>%
    mutate(Location = rep("Start", 400)) %>%
    mutate(Interval = sample.int(1000, 400))
Intensity <- rlnorm(400, meanlog = 1.5)
se <- runif(400)
center_df <- data.frame(Intensity, se, Position, Query, Reference) %>%
    mutate(lower = Intensity - se, upper = Intensity + se) %>%
    mutate(Group = paste(Query, Reference, sep = ":")) %>%
    mutate(Location = rep("Center", 400)) %>%
    mutate(Interval = sample.int(600, 400))
Intensity <- rlnorm(400, meanlog = 2)
se <- runif(400)
end_df <- data.frame(Intensity, se, Position, Query, Reference) %>%
    mutate(lower = Intensity - se, upper = Intensity + se) %>%
    mutate(Group = paste(Query, Reference, sep = ":")) %>%
    mutate(Location = rep("End", 400)) %>%
    mutate(Interval = sample.int(2000, 400))

df <- rbind(start_df, center_df, end_df)
p <- draw_stacked_profile(df, cn = "Group", shade = TRUE,
    ext = c(-50, 50, -50, 50),
    hl = c(-20, 20, -25, 25), insert = 100)
p

Description

This is a helper function for handle_input. edgeR::calcNormFactors function is used to estimate normalizing factors, which is used to multiply library sizes.

Usage

effective_size(outlist, outRle, genome = "hg19", nc = 2, verbose = FALSE)

Arguments

Value

a list of list objects with four elements ('query', 'size', 'type', 'weight'), with the 'size' element modified.

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "chip_treat_chr19.bam",
    package = "GenomicPlot"
)
names(queryFiles) <- "query"

inputFiles <- system.file("extdata", "chip_input_chr19.bam",
    package = "GenomicPlot"
)
names(inputFiles) <- "input"

chipImportParams <- setImportParams(
    offset = 0, fix_width = 150, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

out_list <- handle_input(
    inputFiles = c(queryFiles, inputFiles),
    importParams = chipImportParams, verbose = TRUE, nc = 2
)

out <- effective_size(out_list, outRle = TRUE)

Description

The data files in the extdata directory contain data for next generation sequencing read alignments, MACS2 peaks and gene annotation, which are used to test the package and generate plots in the package vignettes. To meet the package file size limit, all data are restricted to chr19:58000-507000 of the human genome version hg19. Details for each file are as follows.

Details

• "gencode.v19.annotation_chr19.gtf" is an excerpt of a gene annotation file by limiting to chr19:58000-507000 of the human genome.

• "gencode.v19.annotation_chr19.gtf.granges.rds" is a GRanges object produced by importing the above gtf file using RCAS::importGtf.

• "chip_treat_chr19.bam(.bai)" and "chip_input_chr19.bam(.bai)" are paired-end read alignment data from ChIPseq experiments.

• "treat_chr19.bam(.bai)" and "input_chr19.bam(.bai)" are single-end read alignment data from iCLIP experiments.

• "test_wig_chr19_+(-).wig", "test_wig_chr19_+(-).bw" are iCLIP alignment data in WIG and BIGWIG format, respectively; '+' and '-' represent forward and reverse strand, respectively.

• "test_clip_peak_chr19.bed" contains strand-specific iCLIP peak in BED format.

• "test_chip_peak_chr19.bed" and "test_chip_peak_chr19.narrowPeak" contain ChIPseq peaks generated with MACS2, in summit peak and narrow peak format, respectively. "test_chr19.bedGraph" contains the same data in bedGraph format.

• "test_file1.txt", "test_file2.txt", "test_file3.txt" and "test_file4.txt" are tab-delimited text files, each contains various human gene names in different columns.

Value

Various files used as inputs to run examples and tests

Author(s)

Shuye Pu

Source

The original gene annotation (gtf) file is downloaded from https://www.gencodegenes.org/human/.
Except for the gtf file, all other files are derived from experimental data produced in-house at the Greenblatt Lab, University of Toronto, Canada.

Description

Gene level computations require selecting one transcript per gene to avoid bias by genes with multiple isoforms. In ideal case, the most abundant transcript (principal or canonical isoform) should be chosen. However, the most abundant isoform may vary depending on tissue type or physiological condition, the longest transcript is usually the principal isoform, and alternatively spliced isoforms are not. This method get the longest transcript for each gene. The longest transcript is defined as the isoform that has the longest transcript length. In case of tie, the one with longer CDS is selected. If the lengths of CDS tie again, the transcript with smaller id is selected arbitrarily.

Usage

extract_longest_tx(txdb)

Arguments

Value

a dataframe of transcript information with the following columns: "tx_id tx_name gene_id nexon tx_len cds_len utr5_len utr3_len"

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")
longestTx <- extract_longest_tx(txdb)

Description

This function reports all query GRanges that do not overlaps GRanges in subject. Strand information is used to define overlap.

Usage

filter_by_nonoverlaps_stranded(
  query,
  subject,
  maxgap = -1L,
  minoverlap = 0L,
  ignore.order = TRUE
)

Arguments

Value

a GRanges object

Author(s)

Shuye Pu

Examples

query <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

res <- filter_by_nonoverlaps_stranded(query, subject)
res

Description

This function reports all query GRanges that have overlaps in subject GRanges. Strand information is not required.

Usage

filter_by_overlaps_nonstranded(
  query,
  subject,
  maxgap = -1L,
  minoverlap = 0L,
  ignore.order = TRUE
)

Arguments

Value

a GRanges object

Author(s)

Shuye Pu

Examples

query <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

res <- filter_by_overlaps_nonstranded(query, subject, ignore.order = TRUE)
res

Description

This function reports all query GRanges that have overlaps in subject GRanges. Strand information is used to define overlap.

Usage

filter_by_overlaps_stranded(
  query,
  subject,
  maxgap = -1L,
  minoverlap = 0L,
  ignore.order = TRUE
)

Arguments

Value

a GRanges object

Author(s)

Shuye Pu

Examples

query <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

res <- filter_by_overlaps_stranded(query, subject)
res
resf <- filter_by_overlaps_stranded(query, subject, ignore.order = FALSE)
resf

Description

Given a list of gene names in a file or in a character vector, turn them into a vector of transcript ids.

Usage

gene2tx(gtfFile, geneList, geneCol = 1)

Arguments

Value

a vector of transcript ids (eg. ENST00000577222.1)

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)
genes <- c("RPRD1A", "RPAP2", "RPRD1B", "RPRD2", "ZNF281", "YTHDF2")

tx <- gene2tx(gtfFile = gtfFile, geneList = genes)

Description

An R package for efficient and flexible visualization of genome-wide NGS coverage profiles

Details

The goal of 'GenomicPlot' is to provide an efficient visualization tool for next generation sequencing (NGS) data with rich functionality and flexibility. 'GenomicPlot' enables plotting of NGS data in various formats (bam, bed, wig and bigwig); both coverage and enrichment over input can be computed and displayed with respect to genomic features (such as UTR, CDS, enhancer), and user defined genomic loci or regions. Statistical tests on signal intensity within user defined regions of interest can be performed and presented as box plots or pie charts. Parallel processing is enabled to speed up computation on multi-core platforms. Main functions are as follows:

• plot_5parts_metagene generates genomic (with introns) or metagenomic (without introns) plots around gene body and its upstream and downstream regions, the gene body can be further segmented into 5'UTR, CDS and 3'UTR.

• plot_start_end plots genomic profiles around the start and end of genomic features (like exons or introns), or user defined genomic regions. A center region with user defined width can be plotted simultaneously.

• plot_locus plots distance between sample peaks and genomic features, or distance from one set of peaks to another set of peaks.

• plot_region plots signal profiles within and around genomic features, or user defined genomic regions.

• plot_peak_annotation plots peak annotation statistics (distribution in different type of genes, and in different parts of genes).

• plot_overlap_bed plots peak overlaps as Venn diagrams.

• Random features can be generated and plotted to serve as contrast to real features in plot_locus_with_random and plot_start_end_with_random.

• All profile line plots have error bands.

• Statistical analysis results on user defined regions of interest are plotted along with the profile plots in plot_region, plot_locus and plot_locus_with_random.

Author(s)

Shuye Pu

_PACKAGE

Description

Extract genomic coordinates and make bed or bed 12 files from a TxDb object for a variety of annotated genomic features. The output of this function is a list. The first element of the list is a GRanges object that provide the start and end information of the feature. The second element is a GRangesList providing information for sub-components. The third element is the name of a bed file.

Usage

get_genomic_feature_coordinates(
  txdb,
  featureName,
  featureSource = NULL,
  export = FALSE,
  longest = FALSE,
  protein_coding = FALSE
)

Arguments

Details

For "utr3", "utr5", "cds" and "transcript", the GRanges object denotes the start and end of the feature in one transcript, and the range is named by the transcript id and may span introns; the GrangesList object is a list of exons comprising each feature and indexed on transcript id. The bed file is in bed12 format. For "exon" and "intron", the GRanges object denotes unnamed ranges of individual exon and intron, and the GrangesList object is a list of exons or introns belonging to one transcript and indexed on transcript id. The bed file is in bed6 format. For "gene", both GRanges object and GRangesList object have the same ranges and names. The bed file is in bed6 format.

Value

a list of three objects, the first is a GRanges object, the second is a GRangesList object, the last is the output file name if export is TRUE.

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")

output <- get_genomic_feature_coordinates(txdb,
    featureName = "cds", featureSource = "gencode",
    export = FALSE, longest = TRUE, protein_coding = TRUE
)

Description

Annotate each peak with genomic features based on overlap, and produce summary statistics for distribution of peaks in features of protein-coding genes. If a peak overlap multiple features, a feature is assigned to the peak in the following order of precedence: "5'UTR", "3'UTR", "CDS", "Intron", "Promoter", "TTS".

Usage

get_targeted_genes(peak, features, stranded = TRUE)

Arguments

Value

a list object

Note

used in plot_peak_annotation

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")
f <- get_txdb_features(txdb, dsTSS = 100, fiveP = 0, threeP = 1000)

p <- RCAS::importBed(system.file("extdata", "test_chip_peak_chr19.bed",
    package = "GenomicPlot"
))
ann <- get_targeted_genes(peak = p, features = f, stranded = FALSE)

Description

Get genomic coordinates of promoter, 5'UTR, CDS, 3'UTR, TTS and intron for the longest transcript of protein-coding genes. The range of promoter is defined by fiveP and dsTSS upstream and downstream TSS, respectively, the TTS ranges from the 3' end of the gene to threeP downstream, or the start of a downstream gene, whichever is closer.

Usage

get_txdb_features(txdb, fiveP = -1000, dsTSS = 300, threeP = 1000, nc = 2)

Arguments

Value

a GRangesList object

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")

f <- get_txdb_features(txdb, dsTSS = 100, fiveP = -100, threeP = 100)

Description

Genomic coordinates of 72 transcripts in hg19 for genomic features promoter, 5'UTR, CDS, 3'UTR, TTS, as well as user inputs for processing these features. See prepare_5parts_genomic_features for details.

Value

A named list with the following elements:

windowRs

a list of 5 GrangesList objects for the 5 genomic features

nbins

a positive integer

scaled_bins

a vector of 5 integers

fiveP

a negative integer

threeP

a positive integer

meta

logical

longest

logical

Author(s)

Shuye Pu

Source

The data is produced by running the following code:
txdb <- AnnotationDbi::loadDb(system.file("extdata", "txdb.sql", package = "GenomicPlot"))
gf5_genomic <- GenomicPlot::prepare_5parts_genomic_features(txdb, meta = FALSE, nbins = 100, fiveP = -2000, threeP = 1000, longest = TRUE)

Description

Metagenomic coordinates of 72 transcripts in hg19 for genomic features promoter, 5'UTR, CDS, 3'UTR, TTS, as well as user inputs for processing these features. See prepare_5parts_genomic_features for details.

Value

A named list with the following elements:

windowRs

a list of 5 GrangesList objects for the 5 genomic features

nbins

a positive integer

scaled_bins

a vector of 5 integers

fiveP

a negative integer

threeP

a positive integer

meta

logical

longest

logical

Author(s)

Shuye Pu

Source

The data is produced by running the following code:
txdb <- AnnotationDbi::loadDb(system.file("extdata", "txdb.sql", package = "GenomicPlot"))
gf5_meta <- GenomicPlot::prepare_5parts_genomic_features(txdb, meta = TRUE, nbins = 100, fiveP = -2000, threeP = 1000, longest = TRUE)

Description

Convert a GRanges object with meta data columns to a dataframe, with the first 6 columns corresponding those of BED6 format, and the meta data as additional columns

Usage

gr2df(gr)

Arguments

Value

a dataframe

Author(s)

Shuye Pu

Examples

gr2 <- GenomicRanges::GRanges(c("chr1", "chr1"),
    IRanges::IRanges(c(7, 13), width = 3),
    strand = c("+", "-")
)
GenomicRanges::mcols(gr2) <- data.frame(
    score = c(0.3, 0.9),
    cat = c(TRUE, FALSE)
)
df2 <- gr2df(gr2)

Description

This is a function for read NGS reads data in bam format, store the input data in a list of GRanges objects or RleList objects. For paired-end reads, only take the second read in a pair, assuming which is the sense read for strand-specific RNAseq.

Usage

handle_bam(inputFile, importParams = NULL, verbose = FALSE)

Arguments

Details

The reads are filtered using mapq score >= 10 by default, only mapped reads are counted towards library size.

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the library size, 'type' is the input file type, weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "treat_chr19.bam",
    package = "GenomicPlot"
)
names(queryFiles) <- "query"

bamimportParams <- setImportParams(
    offset = -1, fix_width = 0, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out <- handle_bam(
    inputFile = queryFiles, importParams = bamimportParams, verbose = TRUE
)

Description

This is a function for read peaks data in bed format, store the input data in a list of GRanges objects or RleList objects.

Usage

handle_bed(inputFile, importParams = NULL, verbose = FALSE)

Arguments

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the library size, 'type' is the input file type, 'weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "test_chip_peak_chr19.narrowPeak",
    package = "GenomicPlot"
)
names(queryFiles) <- "narrowPeak"

bedimportParams <- setImportParams(
    offset = 0, fix_width = 100, fix_point = "center", norm = FALSE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out <- handle_bed(queryFiles, bedimportParams, verbose = TRUE)
lapply(out$query, sum)

Description

This is a function for read peaks data in bedGraph format, store the input data in a list of GRanges objects or RleList objects.

Usage

handle_bedGraph(inputFile, importParams = NULL, verbose = FALSE)

Arguments

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the library size, 'type' is the input file type, 'weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "test_chr19.bedGraph",
    package = "GenomicPlot"
)
names(queryFiles) <- "chipPeak"

importParams <- setImportParams(
    offset = 0, fix_width = 0, fix_point = "start", norm = FALSE,
    useScore = TRUE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19",
    val = 4, skip = 1
)

out <- handle_bedGraph(queryFiles, importParams, verbose = TRUE)
out$query

Description

This is a function for read NGS coverage data in bigwig format, store the input data in a list of GRanges objects or RleList objects. The input bw file can be stranded or non-stranded. Library size is calculate as the sum of all coverage.

Usage

handle_bw(inputFile, importParams, verbose = FALSE)

Arguments

Details

For stranded files, forward and reverse strands are stored in separate files, with '+' or 'p' in the forward strand file name and '-' or 'm' in the reverse strand file name.

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the estimated library size, 'type' is the input file type, weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "test_wig_chr19_+.bw",
    package = "GenomicPlot"
)
names(queryFiles) <- "test_bw"

wigimportParams <- setImportParams(
    offset = 0, fix_width = 0, fix_point = "start", norm = FALSE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out <- handle_bw(queryFiles, wigimportParams, verbose = TRUE)

Description

This is a wrapper function for read NGS data in different file formats, store the input data in a list of GRanges objects or RleList objects. File names end in bed|bam|bw|bigwig|bigWig|BigWig|BW|BIGWIG are recognized, and a named list of files with mixed formats are allowed.

Usage

handle_input(inputFiles, importParams = NULL, verbose = FALSE, nc = 2)

Arguments

Details

when 'useScore' is TRUE, the score column of the bed file will be used in the metadata column 'score' of the GRanges object, or the 'Values' field of the RleList object. Otherwise the value 1 will be used instead. When the intended use of the input bed is a reference feature, both 'useScore' and 'outRle' should be set to FALSE.

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the library size, 'type' is the input file type, 'weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles1 <- system.file("extdata", "treat_chr19.bam",
    package = "GenomicPlot"
)
names(queryFiles1) <- "query"

inputFiles1 <- system.file("extdata", "input_chr19.bam",
    package = "GenomicPlot"
)
names(inputFiles1) <- "input"

bamimportParams <- setImportParams(
    offset = -1, fix_width = 0, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out_list <- handle_input(
    inputFiles = c(queryFiles1, inputFiles1),
    importParams = bamimportParams, verbose = TRUE, nc = 2
)

queryFiles2 <- system.file("extdata", "test_wig_chr19_+.wig",
    package = "GenomicPlot"
)
names(queryFiles2) <- "test_wig"

wigimportParams <- setImportParams(
    offset = 0, fix_width = 0, fix_point = "start", norm = FALSE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out <- handle_input(queryFiles2, wigimportParams, verbose = TRUE)

queryFiles3 <- system.file("extdata", "test_wig_chr19_+.bw",
    package = "GenomicPlot"
)
names(queryFiles3) <- "test_bw"

out <- handle_input(c(queryFiles1, queryFiles2, queryFiles3),
    wigimportParams,
    verbose = TRUE
)

Description

This is a function for read NGS coverage data in wig format, store the input data in a list of GRanges objects or RleList objects. The input wig file can be stranded or non-stranded. Library size is calculate as the sum of all coverage.

Usage

handle_wig(inputFile, importParams, verbose = FALSE)

Arguments

Details

For stranded files, forward and reverse strands are stored in separate files, with '+' or 'p' in the forward strand file name and '-' or 'm' in the reverse strand file name.

Value

a list object with four elements, 'query' is a list GRanges objects or RleList objects, 'size' is the library size, 'type' is the input file type, 'weight' is the name of the metadata column to be used as weight for coverage calculation

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "test_wig_chr19_+.wig",
    package = "GenomicPlot"
)
names(queryFiles) <- "test_wig"

wigimportParams <- setImportParams(
    offset = 0, fix_width = 0, fix_point = "start", norm = FALSE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

out <- handle_wig(queryFiles, wigimportParams, verbose = TRUE)

Description

Make a partial TxDb object given a GTF file and a list of gene names in a file or in a character vector.

Usage

make_subTxDb_from_GTF(gtfFile, genome = "hg19", geneList, geneCol = 1)

Arguments

Value

a TxDb object

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)
genes <- c("RPRD1A", "RPAP2", "RPRD1B", "RPRD2", "ZNF281", "YTHDF2")

txdb <- make_subTxDb_from_GTF(gtfFile = gtfFile, geneList = genes)

Description

This is a helper function for Venn diagram plot. A Venn diagram is plotted as output. For GRanges, as A overlap B may not be the same as B overlap A, the order of GRanges in a list matters, certain order may produce an error.

Usage

overlap_pair(apair, overlap_fun, title = NULL)

Arguments

Value

a VennDiagram object

Author(s)

Shuye Pu

Examples

test_list <- list(A = c(1, 2, 3, 4, 5), B = c(4, 5, 7))
overlap_pair(test_list, intersect, title = "test")

## GRanges overlap
query <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

overlap_pair(
    list(query = query, subject = subject),
    filter_by_overlaps_stranded
)

Description

This is a helper function for Venn diagram plot. A Venn diagram is plotted as output. For GRanges, as A overlap B may not be the same as B overlap A, the order of GRanges in a list matters, certain order may produce an error.

Usage

overlap_quad(aquad, overlap_fun, title = NULL)

Arguments

Value

a VennDiagram object

Author(s)

Shuye Pu

Examples

test_list <- list(A = c(1, 2, 3, 4, 5), B = c(4, 5, 7), C = c(1, 3), D = 6)
overlap_quad(test_list, intersect)

## GRanges overlap
query1 <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

query2 <- GRanges("chr19",
    IRanges(rep(c(1, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject1 <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

subject2 <- GRanges("chr19",
    IRanges(rep(c(13, 50), 2), width = c(10, 14, 20, 21)),
    strand = c("+", "-", "-", "+")
)

overlap_quad(list(
    subject1 = subject1, subject2 = subject2, query1 = query1,
    query2 = query2
), filter_by_overlaps_stranded)

Description

This is a helper function for Venn diagram plot. A Venn diagram is plotted as output. For GRanges, as A overlap B may not be the same as B overlap A, the order of GRanges in a list matters, certain order may produce an error.

Usage

overlap_triple(atriple, overlap_fun, title = NULL)

Arguments

Value

a VennDiagram object

Author(s)

Shuye Pu

Examples

test_list <- list(A = c(1, 2, 3, 4, 5), B = c(4, 5, 7), C = c(1, 3))
overlap_triple(test_list, intersect, title = "test")

## GRanges overlap
query <- GRanges("chr19",
    IRanges(rep(c(10, 15), 2), width = c(1, 20, 40, 50)),
    strand = c("+", "+", "-", "-")
)

subject1 <- GRanges("chr19",
    IRanges(rep(c(13, 150), 2), width = c(10, 14, 20, 28)),
    strand = c("+", "-", "-", "+")
)

subject2 <- GRanges("chr19",
    IRanges(rep(c(13, 50), 2), width = c(10, 14, 20, 21)),
    strand = c("+", "-", "-", "+")
)

overlap_triple(
    list(subject1 = subject1, subject2 = subject2, query = query),
    filter_by_overlaps_stranded
)

Description

Function for parallel computation of countOverlaps function in the GenomicRanges package

Usage

parallel_countOverlaps(grange_list, tileBins, nc = 2, switch = FALSE)

Arguments

Value

a list of numeric vectors

Author(s)

Shuye Pu

Examples

bedQueryFiles <- c(
    system.file("extdata", "test_chip_peak_chr19.narrowPeak",
        package = "GenomicPlot"
    ),
    system.file("extdata", "test_chip_peak_chr19.bed",
        package = "GenomicPlot"),
    system.file("extdata", "test_clip_peak_chr19.bed",
        package = "GenomicPlot")
)
names(bedQueryFiles) <- c("NarrowPeak", "SummitPeak", "iCLIPPeak")

bedimportParams <- setImportParams(
    offset = 0, fix_width = 100, fix_point = "center", norm = FALSE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

out_list <- handle_input(
    inputFiles = bedQueryFiles,
    importParams = bedimportParams, verbose = TRUE, nc = 2
)

chromInfo <- circlize::read.chromInfo(species = "hg19")$df
seqi <- Seqinfo(seqnames = chromInfo$chr, seqlengths = chromInfo$end,
               isCircular = rep(FALSE, nrow(chromInfo)),
               genome = "hg19")
grange_list <- lapply(out_list, function(x) x$query)
tilewidth <- 100000
tileBins <- tileGenome(seqi,
    tilewidth = tilewidth,
    cut.last.tile.in.chrom = TRUE
)

score_list1 <- parallel_countOverlaps(grange_list, tileBins, nc = 2)
dplyr::glimpse(score_list1)

Description

Function for parallel computation of scoreMatrixBin. The 'windows' parameter of the scoreMatrixBin method is split into nc chunks, and scoreMatrixBin is called on each chunk simultaneously to speed up the computation.

Usage

parallel_scoreMatrixBin(
  queryRegions,
  windowRs,
  bin_num,
  bin_op,
  weight_col,
  stranded,
  nc = 2
)

Arguments

Value

a numeric matrix

Author(s)

Shuye Pu

Examples

queryFiles <- system.file("extdata", "chip_treat_chr19.bam",
    package = "GenomicPlot"
)
names(queryFiles) <- "query"

chipimportParams <- setImportParams(
    offset = 0, fix_width = 150, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

queryRegion <- handle_input(queryFiles, chipimportParams,
    verbose = TRUE
)[[1]]$query

windowFiles <- system.file("extdata", "test_chip_peak_chr19.narrowPeak",
    package = "GenomicPlot"
)
names(windowFiles) <- "narrowPeak"

importParams <- setImportParams(
    offset = 0, fix_width = 0, fix_point = "start", norm = FALSE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

windowRegion <- handle_bed(windowFiles, importParams, verbose = TRUE)$query

out <- parallel_scoreMatrixBin(
    queryRegions = queryRegion,
    windowRs = windowRegion,
    bin_num = 50,
    bin_op = "mean",
    weight_col = "score",
    stranded = TRUE,
    nc = 2
)
#

Description

Plot reads or peak Coverage/base/gene of samples given in the query files around genes. The upstream and downstream windows flanking genes can be given separately, metagene plots are generated with 5'UTR, CDS and 3'UTR segments. The length of each segments are prorated according to the median length of each segments. If Input files are provided, ratio over Input is computed and displayed as well.

Usage

plot_5parts_metagene(
  queryFiles,
  gFeatures_list,
  inputFiles = NULL,
  importParams = NULL,
  verbose = FALSE,
  transform = NA,
  smooth = FALSE,
  scale = FALSE,
  stranded = TRUE,
  outPrefix = NULL,
  heatmap = FALSE,
  heatRange = NULL,
  rmOutlier = 0,
  Ylab = "Coverage/base/gene",
  hw = c(10, 10),
  nc = 2
)

Arguments

Value

a dataframe containing the data used for plotting

Author(s)

Shuye Pu

Examples

data(gf5_meta)
queryfiles <- system.file("extdata", "treat_chr19.bam",
                          package = "GenomicPlot")
names(queryfiles) <- "clip_bam"
inputfiles <- system.file("extdata", "input_chr19.bam",
                          package = "GenomicPlot")
names(inputfiles) <- "clip_input"

bamimportParams <- setImportParams(
    offset = -1, fix_width = 0, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

plot_5parts_metagene(
    queryFiles = queryfiles,
    gFeatures_list = list("metagene" = gf5_meta),
    inputFiles = inputfiles,
    scale = FALSE,
    verbose = FALSE,
    transform = NA,
    smooth = TRUE,
    stranded = TRUE,
    outPrefix = NULL,
    importParams = bamimportParams,
    heatmap = TRUE,
    rmOutlier = 0,
    nc = 2
)

Description

Plot correlation in reads coverage distributions along the genome for bam files. Generates a fingerprint plot, a heatmap of correlation coefficients with hierarchical clustering, a pairwise correlation plot and a PCA plot.

Usage

plot_bam_correlation(
  bamFiles,
  binSize = 1e+06,
  outPrefix = NULL,
  importParams = NULL,
  grouping = NULL,
  verbose = FALSE,
  hw = c(8, 8),
  nc = 2
)

Arguments

Value

a dataframe of read counts per bin per sample

Examples

bamQueryFiles <- c(
    system.file("extdata", "chip_input_chr19.bam", package = "GenomicPlot"),
    system.file("extdata", "chip_treat_chr19.bam", package = "GenomicPlot")
)
grouping <- c(1, 2)
names(bamQueryFiles) <- names(grouping) <- c("chip_input", "chip_treat")

bamImportParams <- setImportParams(
    offset = 0, fix_width = 150, fix_point = "start", norm = FALSE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

plot_bam_correlation(
    bamFiles = bamQueryFiles, binSize = 100000, outPrefix = NULL,
    importParams = bamImportParams, nc = 2, verbose = FALSE
)

Description

Plot reads or peak Coverage/base/gene of samples given in the query files around reference locus (start, end or center of a genomic region) defined in the centerFiles. The upstream and downstream windows flanking loci can be given separately, a smaller window can be defined to allow statistical comparisons between samples for the same reference, or between references for a given sample. If Input files are provided, ratio over Input is computed and displayed as well.

Usage

plot_locus(
  queryFiles,
  centerFiles,
  txdb = NULL,
  ext = c(-100, 100),
  hl = c(0, 0),
  shade = TRUE,
  smooth = FALSE,
  importParams = NULL,
  verbose = FALSE,
  binSize = 10,
  refPoint = "center",
  Xlab = "Center",
  Ylab = "Coverage/base/gene",
  inputFiles = NULL,
  stranded = TRUE,
  heatmap = TRUE,
  scale = FALSE,
  outPrefix = NULL,
  rmOutlier = 0,
  transform = NA,
  statsMethod = "wilcox.test",
  heatRange = NULL,
  hw = c(8, 8),
  nc = 2
)

Arguments

Value

a list of two dataframes containing the data used for plotting and for statistical testing

Author(s)

Shuye Pu

Examples

centerfiles <- c(
system.file("extdata", "test_clip_peak_chr19.bed", package = "GenomicPlot"),
system.file("extdata", "test_chip_peak_chr19.bed", package = "GenomicPlot"))

names(centerfiles) <- c("iCLIPPeak", "SummitPeak")
queryfiles <- c(
    system.file("extdata", "chip_treat_chr19.bam", package = "GenomicPlot"))

names(queryfiles) <- c("chip_bam")
inputfiles <- c(
    system.file("extdata", "chip_input_chr19.bam", package = "GenomicPlot"))
names(inputfiles) <- c("chip_input")

chipimportParams <- setImportParams(
    offset = 0, fix_width = 150, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

plot_locus(
  queryFiles = queryfiles,
  centerFiles = centerfiles,
  ext = c(-500, 500),
  hl = c(-100, 100),
  shade = TRUE,
  smooth = TRUE,
  importParams = chipimportParams,
  binSize = 10,
  refPoint = "center",
  Xlab = "Center",
  inputFiles = inputfiles,
  stranded = TRUE,
  scale = FALSE,
  outPrefix = NULL,
  verbose = FALSE,
  transform = NA,
  rmOutlier = 0,
  Ylab = "Coverage/base/peak",
  statsMethod = "wilcox.test",
  heatmap = TRUE,
  nc = 2
)

Description

Plot reads or peak Coverage/base/gene of samples given in the query files around reference locus defined in the centerFiles. The upstream and downstream windows flanking loci can be given separately, a smaller window can be defined to allow statistical comparisons between reference and random loci. The loci are further divided into sub-groups that are overlapping with c("5'UTR", "CDS", "3'UTR"), "unrestricted" means all loci regardless of overlapping.

Usage

plot_locus_with_random(
  queryFiles,
  centerFiles,
  txdb,
  ext = c(-200, 200),
  hl = c(-100, 100),
  shade = FALSE,
  importParams = NULL,
  verbose = FALSE,
  smooth = FALSE,
  transform = NA,
  binSize = 10,
  refPoint = "center",
  Xlab = "Center",
  Ylab = "Coverage/base/gene",
  inputFiles = NULL,
  stranded = TRUE,
  scale = FALSE,
  outPrefix = NULL,
  rmOutlier = 0,
  n_random = 1,
  hw = c(8, 8),
  detailed = FALSE,
  statsMethod = "wilcox.test",
  nc = 2
)

Arguments

Value

a dataframe containing the data used for plotting

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")
bedQueryFiles <- c(
system.file("extdata", "test_chip_peak_chr19.narrowPeak",
            package = "GenomicPlot"),
system.file("extdata", "test_chip_peak_chr19.bed", package = "GenomicPlot"),
system.file("extdata", "test_clip_peak_chr19.bed", package = "GenomicPlot")
)
names(bedQueryFiles) <- c("NarrowPeak", "SummitPeak", "iCLIPPeak")

bamQueryFiles <- system.file("extdata", "treat_chr19.bam",
                             package = "GenomicPlot")
names(bamQueryFiles) <- "clip_bam"
bamInputFiles <- system.file("extdata", "input_chr19.bam",
                             package = "GenomicPlot")
names(bamInputFiles) <- "clip_input"

bamImportParams <- setImportParams(
  offset = -1, fix_width = 0, fix_point = "start", norm = TRUE,
  useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)
plot_locus_with_random(
    queryFiles = bamQueryFiles,
    centerFiles = bedQueryFiles[3],
    txdb = txdb,
    ext = c(-200, 200),
    hl = c(-50, 50),
    shade = TRUE,
    importParams = bamImportParams,
    verbose = FALSE,
    smooth = TRUE,
    transform = NA,
    binSize = 10,
    refPoint = "center",
    Xlab = "Center",
    Ylab = "Coverage/base/peak",
    inputFiles = bamInputFiles,
    stranded = TRUE,
    scale = FALSE,
    outPrefix = NULL,
    rmOutlier = 0,
    n_random = 1,
    hw = c(8, 8),
    detailed = FALSE,
    statsMethod = "wilcox.test",
    nc = 2)

Description

This function takes a list of up to 4 bed file names, and produce a Venn diagram

Usage

plot_overlap_bed(
  bedList,
  outPrefix = NULL,
  importParams = NULL,
  pairOnly = TRUE,
  stranded = TRUE,
  hw = c(8, 8),
  verbose = FALSE
)

Arguments

Value

a ggplot object

Author(s)

Shuye Pu

Examples

queryFiles <- c(
    system.file("extdata", "test_chip_peak_chr19.narrowPeak",
        package = "GenomicPlot"
    ),
    system.file("extdata", "test_chip_peak_chr19.bed",
        package = "GenomicPlot"
    ),
    system.file("extdata", "test_clip_peak_chr19.bed",
        package = "GenomicPlot"
    )
)
names(queryFiles) <- c("narrowPeak", "summitPeak", "clipPeak")

bedimportParams <- setImportParams(
    offset = 0, fix_width = 100, fix_point = "center", norm = FALSE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

plot_overlap_bed(
    bedList = queryFiles, importParams = bedimportParams, pairOnly = FALSE,
    stranded = FALSE, outPrefix = NULL
)

Description

This function takes a list of (at most 4) tab-delimited file names, and produce a Venn diagram

Usage

plot_overlap_genes(
  fileList,
  columnList,
  pairOnly = TRUE,
  hw = c(8, 8),
  outPrefix = NULL
)

Arguments

Value

a list of vectors of gene names

Author(s)

Shuye Pu

Examples

testfile1 <- system.file("extdata", "test_file1.txt",
    package = "GenomicPlot"
)
testfile2 <- system.file("extdata", "test_file2.txt",
    package = "GenomicPlot"
)
testfile3 <- system.file("extdata", "test_file3.txt",
    package = "GenomicPlot"
)
testfile4 <- system.file("extdata", "test_file4.txt",
    package = "GenomicPlot"
)
testfiles <- c(testfile1, testfile2, testfile3, testfile4)
names(testfiles) <- c("test1", "test2", "test3", "test4")

plot_overlap_genes(testfiles, c(3, 2, 1, 1), pairOnly = FALSE)

Description

Produce a table of transcripts targeted by peaks, and generate plots for target gene types, and peak distribution in genomic features

Usage

plot_peak_annotation(
  peakFile,
  gtfFile,
  importParams = NULL,
  fiveP = -1000,
  dsTSS = 300,
  threeP = 1000,
  simple = FALSE,
  outPrefix = NULL,
  verbose = FALSE,
  hw = c(8, 8),
  nc = 2
)

Arguments

Value

a list of three dataframes, 'annotation' is the annotation of peaks into gene types, 'stat' is the summary stats for pie chart, 'simplified' is the summary stats excluding intron

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

centerFile <- system.file("extdata", "test_chip_peak_chr19.bed",
    package = "GenomicPlot"
)
names(centerFile) <- c("summitPeak")

bedimportParams <- setImportParams(
    offset = 0, fix_width = 100, fix_point = "center", norm = FALSE,
    useScore = FALSE, outRle = FALSE, useSizeFactor = FALSE, genome = "hg19"
)

plot_peak_annotation(
    peakFile = centerFile, gtfFile = gtfFile, importParams = bedimportParams,
    fiveP = -2000, dsTSS = 200, threeP = 2000, simple = FALSE
)

Description

Plot reads or peak Coverage/base/gene of samples given in the query files inside regions defined in the centerFiles. The upstream and downstream flanking windows can be given separately. If Input files are provided, ratio over Input is computed and displayed as well.

Usage

plot_region(
  queryFiles,
  centerFiles,
  txdb = NULL,
  regionName = "region",
  inputFiles = NULL,
  nbins = 100,
  importParams = NULL,
  verbose = FALSE,
  scale = FALSE,
  heatmap = FALSE,
  fiveP = -1000,
  threeP = 1000,
  smooth = FALSE,
  stranded = TRUE,
  transform = NA,
  outPrefix = NULL,
  rmOutlier = 0,
  heatRange = NULL,
  Ylab = "Coverage/base/gene",
  statsMethod = "wilcox.test",
  hw = c(8, 8),
  nc = 2
)

Arguments

Value

a dataframe containing the data used for plotting

Author(s)

Shuye Pu

Examples

centerfiles <- system.file("extdata", "test_chip_peak_chr19.narrowPeak",
package = "GenomicPlot")
names(centerfiles) <- c("NarrowPeak")
queryfiles <- c(
  system.file("extdata", "chip_treat_chr19.bam", package = "GenomicPlot"))
names(queryfiles) <- c("chip_bam")
inputfiles <- c(
  system.file("extdata", "chip_input_chr19.bam", package = "GenomicPlot"))
names(inputfiles) <- c("chip_input")

chipimportParams <- setImportParams(
  offset = 0, fix_width = 150, fix_point = "start", norm = TRUE,
  useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19",
  chr = c("chr19"))

plot_region(
  queryFiles = queryfiles,
  centerFiles = centerfiles,
  inputFiles = inputfiles,
  nbins = 100,
  heatmap = TRUE,
  scale = FALSE,
  regionName = "narrowPeak",
  importParams = chipimportParams,
  verbose = FALSE,
  fiveP = -500,
  threeP = 500,
  smooth = TRUE,
  transform = "log2",
  stranded = TRUE,
  outPrefix = NULL,
  Ylab = "Coverage/base/peak",
  rmOutlier = 0,
  nc = 2
)

Description

Plot reads or peak Coverage/base/gene of samples given in the query files around start and end of custom features. The upstream and downstream windows can be given separately, within the window, a smaller window can be defined to highlight region of interest. A line plot will be displayed for both start and end of feature. If Input files are provided, ratio over Input is computed and displayed as well.

Usage

plot_start_end(
  queryFiles,
  inputFiles = NULL,
  centerFiles,
  txdb = NULL,
  importParams = NULL,
  binSize = 10,
  insert = 0,
  verbose = FALSE,
  ext = c(-500, 100, -100, 500),
  hl = c(-50, 50, -50, 50),
  stranded = TRUE,
  scale = FALSE,
  smooth = FALSE,
  rmOutlier = 0,
  outPrefix = NULL,
  transform = NA,
  shade = TRUE,
  Ylab = "Coverage/base/gene",
  hw = c(8, 8),
  nc = 2
)

Arguments

Value

a list of two objects, the first is a GRanges object, the second is a GRangesList object

Author(s)

Shuye Pu

Examples

gtfFile <- system.file("extdata", "gencode.v19.annotation_chr19.gtf",
    package = "GenomicPlot"
)

txdb <- custom_TxDb_from_GTF(gtfFile, genome = "hg19")
bamQueryFiles <- system.file("extdata", "treat_chr19.bam",
    package = "GenomicPlot")
names(bamQueryFiles) <- "clip_bam"
bamInputFiles <- system.file("extdata", "input_chr19.bam",
                             package = "GenomicPlot")
names(bamInputFiles) <- "clip_input"

bamimportParams <- setImportParams(
    offset = -1, fix_width = 0, fix_point = "start", norm = TRUE,
    useScore = FALSE, outRle = TRUE, useSizeFactor = FALSE, genome = "hg19"
)

plot_start_end(
    queryFiles = bamQueryFiles,
    inputFiles = bamInputFiles,
    txdb = txdb,
    centerFiles = "intron",
    binSize = 10,
    importParams = bamimportParams,
    ext = c(-500, 200, -200, 500),
    hl = c(-100, 100, -100, 100),
    insert = 100,
    stranded = TRUE,
    scale = FALSE,
    smooth = TRUE,
    transform = "log2",
    outPrefix = NULL,
    nc = 2
)

Description

Plot reads or peak Coverage/base/gene of samples given in the query files around start, end and center of genomic features or custom feature given in a .bed file. The upstream and downstream windows can be given separately. If Input files are provided, ratio over Input is computed and displayed as well. A random feature can be generated to serve as a background for contrasting.

Usage

plot_start_end_with_random(
  queryFiles,
  inputFiles = NULL,
  txdb = NULL,
  centerFile,
  importParams = NULL,
  binSize = 10,
  insert = 0,
  verbose = FALSE,
  ext = c(-500, 200, -200, 500),
  hl = c(-50, 50, -50, 50),
  randomize = FALSE,
  stranded = TRUE,
  scale = FALSE,
  smooth = FALSE,
  rmOutlier = 0,
  outPrefix = NULL,
  transform = NA,
  shade = TRUE,
  nc = 2,
  hw = c(8, 8),
  Ylab = "Coverage/base/gene"
)

Arguments