GO Enrichment on Integrated Results.

GO Enrichment on Integrated Results.

InteFE(
  inte.res,
  fe.key,
  inte.type = c("DEbPeak", "PeakbPeak", "DEbDE"),
  out.folder = NULL,
  gene.type = c("ENSEMBL", "ENTREZID", "SYMBOL"),
  go.type = c("ALL", "BP", "MF", "CC"),
  enrich.pvalue = 0.05,
  enrich.qvalue = 0.05,
  species = c("Human", "Mouse", "Rat", "Fly", "Arabidopsis", "Yeast", "Zebrafish",
    "Worm", "Bovine", "Pig", "Chicken", "Rhesus", "Canine", "Xenopus", "Anopheles",
    "Chimp", "E coli strain Sakai", "Myxococcus xanthus DK 1622"),
  padj.method = c("BH", "holm", "hochberg", "hommel", "bonferroni", "BY", "fdr",
    "none"),
  show.term = 15,
  str.width = 30,
  plot.resolution = 300,
  plot.width = 7,
  plot.height = 9,
  save = TRUE
)

Arguments

inte.res	Integration results, can be output of DEbPeak, PeakbPeak, DEbDE.
fe.key	The key type of integrated results ("Type" column of inte.res) to perform functional enrichment.
inte.type	The integration type, choose from "DEbDE", "PeakbPeak", "DEbPeak". Default: "DEbPeak".
out.folder	Folder to save enrichment results. Default: wording directory.
gene.type	Gene name type (if inte.res is from DEbPeak, this should be ENTREZID; if inte.res is from PeakbPeak, this should be Gene name type of P1_Gene; if inte.res is from DEbDE, this should be Gene name type of DE1_Gene). Chosen from ENSEMBL, ENTREZID,SYMBOL. Default: ENSEMBL.
go.type	GO enrichment type, chosen from ALL, BP, MF, CC. Default: ALL.
enrich.pvalue	Cutoff value of pvalue. Default: 0.05.
enrich.qvalue	Cutoff value of qvalue. Default: 0.05.
species	Species used, chosen from "Human","Mouse","Rat","Fly","Arabidopsis","Yeast","Zebrafish","Worm","Bovine","Pig","Chicken","Rhesus", "Canine","Xenopus","Anopheles","Chimp","E coli strain Sakai","Myxococcus xanthus DK 1622". Default: "Human".
padj.method	One of "holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr", "none". Default: BH.
show.term	Number of enrichment term to show. Default: 15.
str.width	Length of enrichment term in plot. Default: 30.
plot.resolution	Resolution of plot. Default: 300.
plot.width	The width of plot. Default: 7.
plot.height	The height of plot. Default: 9.
save	Logical value, whether to save all results. Default: TRUE.

Value

If save is TRUE, return NULL (all results are in out.folder), else retutn result dataframe.

Examples

library(DEbPeak)
#### RNA-seq and RNA-seq
rna.diff.file <- system.file("extdata", "RA_RNA_diff.txt", package = "DEbPeak")
de1.res <- read.table(file = rna.diff.file, header = TRUE, sep = "\t")
de2.res <- read.table(file = rna.diff.file, header = TRUE, sep = "\t")
# use same file as example
de.de <- DEbDE(de1.res = de1.res, de2.res = de2.res, de1.l2fc.threshold = 0.5, de2.l2fc.threshold = 1)
#> Differential expression analysis with DESeq2!
#> Differential expression analysis with DESeq2!
de.de.fe <- InteFE(
  inte.res = de.de, fe.key = "Down_Down", inte.type = "DEbDE", gene.type = "SYMBOL", go.type = "BP",
  species = "Mouse", save = F
)
#> Convert SYMBOL to ENTREZID!
#> 'select()' returned 1:1 mapping between keys and columns
#> Warning: 5.76% of input gene IDs are fail to map...
#> conduct BP GO enrichment analysis.
#> wrong orderBy parameter; set to default `orderBy = "x"`
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
#### peak-related and peak-related
# ChIP-seq data
chip.file <- system.file("extdata", "debchip_peaks.bed", package = "DEbPeak")
chip.df <- GetConsensusPeak(peak.file = chip.file)
chip.anno <- AnnoPeak(
  peak.df = chip.df, species = "Mouse",
  seq.style = "UCSC", up.dist = 20000, down.dist = 20000
)
#> >> preparing features information...		 2023-07-02 17时16分48秒 
#> >> identifying nearest features...		 2023-07-02 17时16分48秒 
#> >> calculating distance from peak to TSS...	 2023-07-02 17时16分49秒 
#> >> assigning genomic annotation...		 2023-07-02 17时16分49秒 
#> >> adding gene annotation...			 2023-07-02 17时16分50秒 
#> 'select()' returned 1:many mapping between keys and columns
#> >> assigning chromosome lengths			 2023-07-02 17时16分50秒 
#> >> done...					 2023-07-02 17时16分50秒 
#> Warning: Removed 6 rows containing non-finite values (`stat_count()`).
# ATAC-seq data
atac.file <- system.file("extdata", "debatac_peaks.bed", package = "DEbPeak")
atac.df <- GetConsensusPeak(peak.file = atac.file)
atac.anno <- AnnoPeak(
  peak.df = atac.df, species = "Mouse",
  seq.style = "UCSC", up.dist = 20000, down.dist = 20000
)
#> >> preparing features information...		 2023-07-02 17时16分52秒 
#> >> identifying nearest features...		 2023-07-02 17时16分52秒 
#> >> calculating distance from peak to TSS...	 2023-07-02 17时16分52秒 
#> >> assigning genomic annotation...		 2023-07-02 17时16分52秒 
#> >> adding gene annotation...			 2023-07-02 17时16分54秒 
#> 'select()' returned 1:many mapping between keys and columns
#> >> assigning chromosome lengths			 2023-07-02 17时16分54秒 
#> >> done...					 2023-07-02 17时16分54秒 
#> Warning: Removed 23 rows containing non-finite values (`stat_count()`).
# integrate
chip.atac <- PeakbPeak(peak1.res = chip.anno$df, peak2.res = atac.anno$df, peak.mode = "consensus", peak.anno.key = "Promoter")
# functional enrichment
chip.atac.fe <- InteFE(
  inte.res = chip.atac, fe.key = "Common", inte.type = "PeakbPeak", gene.type = "SYMBOL",
  go.type = "BP", species = "Mouse", save = FALSE
)
#> Convert SYMBOL to ENTREZID!
#> 'select()' returned 1:1 mapping between keys and columns
#> Warning: 0.61% of input gene IDs are fail to map...
#> conduct BP GO enrichment analysis.
#> wrong orderBy parameter; set to default `orderBy = "x"`
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
#### RNA-seq and peak-related
library(DESeq2)
# ChIP-Seq data
peak.file <- system.file("extdata", "debchip_peaks.bed", package = "DEbPeak")
peak.df <- GetConsensusPeak(peak.file = peak.file)
peak.profile <- PeakProfile(peak.df, species = "Mouse", by = "gene", region.type = "body", nbin = 800)
#> >> preparing promoter regions...	 2023-07-02 17时17分06秒 
#> >> preparing tag matrix...		 2023-07-02 17时17分06秒 
#> >> preparing start_site regions by ... 2023-07-02 17时17分06秒
#> >> preparing tag matrix...  2023-07-02 17时17分06秒 
#> >> generating figure...		 2023-07-02 17时17分15秒 
#> >> done...			 2023-07-02 17时17分15秒 
#> >> binning method is used...2023-07-02 17时17分15秒
#> >> preparing start_site regions by gene... 2023-07-02 17时17分15秒
#> >> preparing tag matrix by binning...  2023-07-02 17时17分15秒 
#> >> Running bootstrapping for tag matrix...		 2023-07-02 17时17分23秒 
#> >> binning method is used...2023-07-02 17时17分24秒
#> >> preparing body regions by gene... 2023-07-02 17时17分24秒
#> >> preparing tag matrix by binning...  2023-07-02 17时17分24秒 
#> >> preparing matrix with extension from (TSS-20%)~(TTS+20%)... 2023-07-02 17时17分24秒
#> >> 1 peaks(0.1536098%), having lengths smaller than 800bp, are filtered... 2023-07-02 17时17分27秒
#> >> Running bootstrapping for tag matrix...		 2023-07-02 17时18分08秒 
peak.anno <- AnnoPeak(
  peak.df = peak.df, species = "Mouse",
  seq.style = "UCSC", up.dist = 20000, down.dist = 20000
)
#> >> preparing features information...		 2023-07-02 17时18分09秒 
#> >> identifying nearest features...		 2023-07-02 17时18分09秒 
#> >> calculating distance from peak to TSS...	 2023-07-02 17时18分09秒 
#> >> assigning genomic annotation...		 2023-07-02 17时18分09秒 
#> >> adding gene annotation...			 2023-07-02 17时18分12秒 
#> 'select()' returned 1:many mapping between keys and columns
#> >> assigning chromosome lengths			 2023-07-02 17时18分12秒 
#> >> done...					 2023-07-02 17时18分12秒 
#> Warning: Removed 6 rows containing non-finite values (`stat_count()`).
# RNA-Seq data
count.file <- system.file("extdata", "debchip_count.txt", package = "DEbPeak")
meta.file <- system.file("extdata", "debchip_meta.txt", package = "DEbPeak")
count.matrix <- read.table(file = count.file, header = TRUE, sep = "\t")
meta.info <- read.table(file = meta.file, header = TRUE)
# create DESeqDataSet object
dds <- DESeq2::DESeqDataSetFromMatrix(
  countData = count.matrix, colData = meta.info,
  design = ~condition
)
#> Warning: some variables in design formula are characters, converting to factors
# set control level
dds$condition <- relevel(dds$condition, ref = "NF")
# conduct differential expressed genes analysis
dds <- DESeq(dds)
#> estimating size factors
#> estimating dispersions
#> gene-wise dispersion estimates
#> mean-dispersion relationship
#> final dispersion estimates
#> fitting model and testing
# extract results
dds.results <- results(dds, contrast = c("condition", "RX", "NF"))
dds.results.ordered <- dds.results[order(dds.results$log2FoldChange, decreasing = TRUE), ]
# Integrated with RNA-Seq
debchip.res <- DEbPeak(
  de.res = dds.results.ordered, peak.res = peak.anno[["df"]],
  peak.anno.key = "Promoter", merge.key = "SYMBOL"
)
#> Differential expression analysis with DESeq2!
# functional enrichment on UPbPeak genes
upbpeak.fe.results <- InteFE(
  inte.res = debchip.res, fe.key = "UPbPeak", inte.type = "DEbPeak", gene.type = "ENTREZID",
  species = "Mouse", save = FALSE
)
#> conduct ALL GO enrichment analysis on: UPbPeak
#> wrong orderBy parameter; set to default `orderBy = "x"`
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
#> wrong orderBy parameter; set to default `orderBy = "x"`
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.
#> wrong orderBy parameter; set to default `orderBy = "x"`
#> Scale for y is already present.
#> Adding another scale for y, which will replace the existing scale.