check

DESCRIPTION

@@ -5,8 +5,8 @@ Authors@R:
     person(given = "Yabing",
            family = "Song",
            role = c("aut", "cre"),
-           email = "[email protected]",
-           comment = c(ORCID = "YOUR-ORCID-ID"))
+           email = "[email protected]")
+Maintainer: Yabing Song <[email protected]>
 Description: DEbChIP aims to explore, analyze, visualize and interpret RNA-seq data. It contains five functional panels: Quality Control (QC),
     Principal Component Analysis (PCA), Differential Expression Analysis (DEA), Functional Enrichment Analysis (FEA), Integrate with ChIP-seq (DEbChIP), Utils.
 License: MIT + file LICENSE
@@ -16,7 +16,6 @@ RoxygenNote: 7.1.1
 Depends:
     R (>= 4.0.0)
 Imports: 
-    BiocGenerics,
     BiocManager,
     circlize,
     clusterProfiler (>= 3.18.1),
@@ -32,6 +31,8 @@ Imports:
     ggplot2,
     ggplotify,
     ggrepel,
+    ggvenn,
+    ggupset,
     graphics,
     grDevices,
     grid,
@@ -44,6 +45,7 @@ Imports:
     RColorBrewer,
     reshape2,
     rrcov,
+    rlang,
     stats,
     stringr,
     SummarizedExperiment,
@@ -53,11 +55,16 @@ Imports:
     utils,
     ChIPseeker,
     GenomeInfoDb,
-    ggvenn,
-    viridis
+    viridis,
+    patchwork
 Suggests: 
     rmarkdown,
-    knitr
+    knitr,
+    msigdbr,
+    htmltools,
+    BiocStyle,
+    airway
 Remotes:
-    GuangchuangYu/enrichplot
+    YuLab-SMU/enrichplot
+    YuLab-SMU/ChIPseeker
 VignetteBuilder: knitr

NAMESPACE

@@ -34,12 +34,14 @@ import(ChIPseeker)
 import(ComplexHeatmap)
 import(clusterProfiler)
 import(ggplot2)
+import(ggupset)
 import(ggvenn)
 importFrom(BiocManager,install)
 importFrom(ComplexHeatmap,draw)
 importFrom(ComplexHeatmap,pheatmap)
 importFrom(DEFormats,as.DESeqDataSet)
 importFrom(DEFormats,as.DGEList)
+importFrom(DESeq2,DESeqDataSetFromMatrix)
 importFrom(DESeq2,counts)
 importFrom(DESeq2,estimateSizeFactors)
 importFrom(DESeq2,normTransform)
@@ -84,8 +86,17 @@ importFrom(enrichplot,dotplot)
 importFrom(enrichplot,gseaplot2)
 importFrom(ggplotify,as.ggplot)
 importFrom(ggrepel,geom_text_repel)
+importFrom(grDevices,col2rgb)
 importFrom(grDevices,colorRampPalette)
+importFrom(grDevices,dev.off)
+importFrom(grDevices,pdf)
+importFrom(grDevices,rgb)
+importFrom(graphics,abline)
+importFrom(graphics,barplot)
 importFrom(graphics,image)
+importFrom(graphics,legend)
+importFrom(graphics,mtext)
+importFrom(graphics,title)
 importFrom(grid,grid.grabExpr)
 importFrom(magrittr,"%>%")
 importFrom(matrixStats,rowVars)
@@ -94,10 +105,13 @@ importFrom(plot3D,scatter3D)
 importFrom(plot3D,text3D)
 importFrom(purrr,set_names)
 importFrom(reshape2,melt)
+importFrom(rlang,":=")
 importFrom(rrcov,PcaGrid)
 importFrom(rrcov,PcaHubert)
+importFrom(stats,as.formula)
 importFrom(stats,cor)
 importFrom(stats,dist)
+importFrom(stats,na.omit)
 importFrom(stats,prcomp)
 importFrom(stringr,str_wrap)
 importFrom(sva,ComBat_seq)
@@ -106,4 +120,6 @@ importFrom(tibble,deframe)
 importFrom(tibble,rownames_to_column)
 importFrom(tidyr,drop_na)
 importFrom(utils,read.table)
+importFrom(utils,write.csv)
+importFrom(utils,write.table)
 importFrom(viridis,viridis)

R/ChIP_consensus_peak.R

@@ -33,7 +33,7 @@ GetConsensusPeak <- function(peak.file, peak.folder = NULL, mspc.path = NULL, re
 
   # prepare input files
   if (!is.null(peak.folder)) {
-    peak.file <- list.files(path = peak.folder, full.names = T)
+    peak.file <- list.files(path = peak.folder, full.names = TRUE)
   }
   # check peak file number
   if (length(peak.file) < 1) {

R/ChIP_peak_annotation.R

@@ -1,37 +1,3 @@
-# 存在的问题：
-# * gene id的对应问题
-
-# https://bioconductor.org/packages/3.15/data/annotation/
-# BiocManager::install(c("TxDb.Athaliana.BioMart.plantsmart28","TxDb.Btaurus.UCSC.bosTau9.refGene",
-#                        "TxDb.Celegans.UCSC.ce11.refGene","TxDb.Cfamiliaris.UCSC.canFam3.refGene",
-#                        "TxDb.Dmelanogaster.UCSC.dm6.ensGene","TxDb.Drerio.UCSC.danRer11.refGene",
-#                        "TxDb.Ggallus.UCSC.galGal6.refGene","TxDb.Hsapiens.UCSC.hg38.knownGene",
-#                        "TxDb.Mmulatta.UCSC.rheMac10.refGene","TxDb.Mmusculus.UCSC.mm10.knownGene",
-#                        "TxDb.Ptroglodytes.UCSC.panTro6.refGene","TxDb.Sscrofa.UCSC.susScr11.refGene",
-#                        "TxDb.Rnorvegicus.UCSC.rn6.refGene","TxDb.Scerevisiae.UCSC.sacCer3.sgdGene"))
-
-# TxDb.Athaliana.BioMart.plantsmart28: Arabidopsis thaliana
-# TxDb.Btaurus.UCSC.bosTau9.refGene: Bos taurus
-# TxDb.Celegans.UCSC.ce11.refGene: Caenorhabditis elegans
-# TxDb.Cfamiliaris.UCSC.canFam3.refGene: Canis familiaris
-# TxDb.Dmelanogaster.UCSC.dm6.ensGene: Drosophila melanogaster
-# TxDb.Drerio.UCSC.danRer11.refGene: Danio rerio
-# TxDb.Ggallus.UCSC.galGal6.refGene: Gallus gallus
-# TxDb.Hsapiens.UCSC.hg38.knownGene: Homo sapiens
-# TxDb.Mmulatta.UCSC.rheMac10.refGene: Macaca mulatta
-# TxDb.Mmusculus.UCSC.mm10.knownGene: Mus musculus
-# TxDb.Ptroglodytes.UCSC.panTro6.refGene: Pan troglodytes
-# TxDb.Sscrofa.UCSC.susScr11.refGene: Sus scrofa
-# TxDb.Rnorvegicus.UCSC.rn6.refGene: Rattus norvegicus
-# TxDb.Scerevisiae.UCSC.sacCer3.sgdGene: Saccharomyces cerevisiae
-
-# genes(TxDb.Mmulatta.UCSC.rheMac10.refGene, columns=c("TXID", "TXNAME", "GENEID"))
-#
-# library(TxDb.Hsapiens.UCSC.hg38.knownGene)
-# #
-# seqlevelsStyle(TxDb.Hsapiens.UCSC.hg38.knownGene)
-
-
 # get txdb and orgdb for species
 GetSpeciesAnno <- function(species) {
   spe_names <- c(
@@ -195,6 +161,7 @@ PeakProfile <- function(peak.df, species = c(
 #' @importFrom ggplotify as.ggplot
 #' @importFrom cowplot plot_grid
 #' @import ChIPseeker
+#' @import ggupset
 #' @export
 #'
 #' @examples
@@ -248,7 +215,7 @@ AnnoPeak <- function(peak.df, species = c(
   # annotation
   txdb.obj <- get(txdb)
   if (seq.style != "None") {
-    seqlevelsStyle(txdb.obj) <- seq.style
+    GenomeInfoDb::seqlevelsStyle(txdb.obj) <- seq.style
     peak.seqs <- GenomeInfoDb::seqlevels(peak.gr)
     # to avoid Unable to find an inherited method for function 'NSBS' for signature '"SortedByQueryHits"'
     txdb.obj <- keepSeqlevels(x = txdb.obj, value = peak.seqs)

R/DE_bind_ChIP.R

@@ -30,8 +30,8 @@
 #' # RNA-Seq data
 #' count.file <- system.file("extdata", "debchip_count.txt", package = "DEbChIP")
 #' meta.file <- system.file("extdata", "debchip_meta.txt", package = "DEbChIP")
-#' count.matrix <- read.table(file = count.file, header = T, sep = "\t")
-#' meta.info <- read.table(file = meta.file, header = T)
+#' 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,
@@ -46,7 +46,7 @@
 #' dds.results.ordered <- dds.results[order(dds.results$log2FoldChange, decreasing = TRUE), ]
 #' # Integrated with RNA-Seq
 #' debchip.res <- DEbChIP(
-#'   de.res = dds.results.ordered, chip.res = peak.anno.df,
+#'   de.res = dds.results.ordered, chip.res = peak.anno[["df"]],
 #'   chip.anno.key = "Promoter", merge.key = "SYMBOL"
 #' )
 DEbChIP <- function(de.res, chip.res, chip.anno.key = c("Promoter", "5' UTR", "3' UTR", "Exon", "Intron", "Downstream", "Distal Intergenic", "All"),
@@ -118,8 +118,8 @@ DEbChIP <- function(de.res, chip.res, chip.anno.key = c("Promoter", "5' UTR", "3
 #' # RNA-Seq data
 #' count.file <- system.file("extdata", "debchip_count.txt", package = "DEbChIP")
 #' meta.file <- system.file("extdata", "debchip_meta.txt", package = "DEbChIP")
-#' count.matrix <- read.table(file = count.file, header = T, sep = "\t")
-#' meta.info <- read.table(file = meta.file, header = T)
+#' count.matrix <- read.table(file = count.file, header = TRUE, sep = "\t")
+#' meta.info <- read.table(file = meta.file, header = TRUE)
 #' # create DESeqDataSet object
 #' dds <- DESeq2::DESeqDataSetFromMatrix(
 #'   countData = count.matrix, colData = meta.info,
@@ -134,7 +134,7 @@ DEbChIP <- function(de.res, chip.res, chip.anno.key = c("Promoter", "5' UTR", "3
 #' dds.results.ordered <- dds.results[order(dds.results$log2FoldChange, decreasing = TRUE), ]
 #' # Integrated with RNA-Seq
 #' debchip.res <- DEbChIP(
-#'   de.res = dds.results.ordered, chip.res = peak.anno.df,
+#'   de.res = dds.results.ordered, chip.res = peak.anno[["df"]],
 #'   chip.anno.key = "Promoter", merge.key = "SYMBOL"
 #' )
 #' # DE and ChIP venn plot
@@ -166,7 +166,8 @@ PlotDEbChIP <- function(de.chip, ...) {
 #' @param go.type GO enrichment type, chosen from ALL, BP, MF, CC. Default: ALL.
 #' @param enrich.pvalue Cutoff value of pvalue. Default: 0.05.
 #' @param enrich.qvalue Cutoff value of qvalue. Default: 0.05.
-#' @param org.db Organism database. Default: org.Mm.eg.db.
+#' @param 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".
 #' @param padj.method One of "holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr", "none". Default: BH.
 #' @param show.term Number of enrichment term to show. Default: 15.
 #' @param str.width Length of enrichment term in plot. Default: 30.
@@ -202,8 +203,8 @@ PlotDEbChIP <- function(de.chip, ...) {
 #' # RNA-Seq data
 #' count.file <- system.file("extdata", "debchip_count.txt", package = "DEbChIP")
 #' meta.file <- system.file("extdata", "debchip_meta.txt", package = "DEbChIP")
-#' count.matrix <- read.table(file = count.file, header = T, sep = "\t")
-#' meta.info <- read.table(file = meta.file, header = T)
+#' 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,
@@ -218,18 +219,18 @@ PlotDEbChIP <- function(de.chip, ...) {
 #' dds.results.ordered <- dds.results[order(dds.results$log2FoldChange, decreasing = TRUE), ]
 #' # Integrated with RNA-Seq
 #' debchip.res <- DEbChIP(
-#'   de.res = dds.results.ordered, chip.res = peak.anno.df,
+#'   de.res = dds.results.ordered, chip.res = peak.anno[["df"]],
 #'   chip.anno.key = "Promoter", merge.key = "SYMBOL"
 #' )
 #' # functional enrichment on genes
-#' fe.results <- DEbChIPFE(de.chip = debchip.res, gene.type = "ENTREZID", species = "Mouse", save = F)
+#' fe.results <- DEbChIPFE(de.chip = debchip.res, gene.type = "ENTREZID", species = "Mouse", save = FALSE)
 DEbChIPFE <- function(de.chip, 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 = T) {
+                      show.term = 15, str.width = 30, plot.resolution = 300, plot.width = 7, plot.height = 9, save = TRUE) {
   # check parameter
   gene.type <- match.arg(arg = gene.type)
   go.type <- match.arg(arg = go.type)