Mm10

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: ALPS
 Title: AnaLysis routines for ePigenomicS data
-Version: 0.99.9
+Version: 0.100.1
 Author: Venu Thatikonda, Natalie Jäger
 Maintainer: Venu Thatikonda <thatikonda92@gmail.com>
 Description: The package provides analysis and publication quality visualization routines for genome-wide 
@@ -12,7 +12,7 @@ Description: The package provides analysis and publication quality visualization
 License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: false
-RoxygenNote: 6.1.1
+RoxygenNote: 7.2.3
 Depends: R (>= 3.6)
 Imports: 
   assertthat,
@@ -39,6 +39,7 @@ Imports:
   tidyr,
   TxDb.Hsapiens.UCSC.hg19.knownGene,
   TxDb.Hsapiens.UCSC.hg38.knownGene,
+  TxDb.Mmusculus.UCSC.mm10.knownGene,
   utils
 URL: https://github.com/itsvenu/ALPS
 BugReports: https://github.com/itsvenu/ALPS/issues

NAMESPACE

@@ -18,6 +18,7 @@ export(process_transfac)
 import(corrplot)
 import(ggplot2)
 import(org.Hs.eg.db)
+importFrom(AnnotationDbi,mapIds)
 importFrom(BiocParallel,bplapply)
 importFrom(ChIPseeker,annotatePeak)
 importFrom(GGally,ggpairs)
@@ -26,8 +27,10 @@ importFrom(GenomicRanges,reduce)
 importFrom(Gviz,DataTrack)
 importFrom(Gviz,GeneRegionTrack)
 importFrom(Gviz,plotTracks)
+importFrom(IRanges,ranges)
 importFrom(TxDb.Hsapiens.UCSC.hg19.knownGene,TxDb.Hsapiens.UCSC.hg19.knownGene)
 importFrom(TxDb.Hsapiens.UCSC.hg38.knownGene,TxDb.Hsapiens.UCSC.hg38.knownGene)
+importFrom(TxDb.Mmusculus.UCSC.mm10.knownGene,TxDb.Mmusculus.UCSC.mm10.knownGene)
 importFrom(data.table,dcast)
 importFrom(data.table,fread)
 importFrom(dplyr,filter)
@@ -42,6 +45,8 @@ importFrom(genefilter,rowVars)
 importFrom(gghalves,geom_half_violin)
 importFrom(ggseqlogo,ggseqlogo)
 importFrom(magrittr,"%>%")
+importFrom(org.Hs.eg.db,org.Hs.eg.db)
+importFrom(org.Mm.eg.db,org.Mm.eg.db)
 importFrom(reshape2,melt)
 importFrom(rtracklayer,BigWigFileList)
 importFrom(rtracklayer,summary)

NEWS

@@ -1,3 +1,7 @@
+VERSION 0.100.0
+--------------
+  * Added support for mm10
+
 VERSION 0.99.8
 --------------
   * Bioc review fixes
@@ -9,4 +13,3 @@ VERSION 0.99.7
 VERSION 0.99.0
 --------------
   * FIRST RELEASE
-

R/get_genomic_annotations.R

@@ -59,7 +59,7 @@ merge_GR <- function(x) {
 #'
 #' @param data_table a data.frame of sample table, as is for
 #' \code{multiBigwig_summary} input table, default NULL
-#' @param ref_gen reference genome, either \code{hg38 or hg19},
+#' @param ref_gen reference genome, either \code{hg38, mm10 or hg19},
 #' default \code{hg38}
 #' @param tss_region bp ± TSS to define promoter regions
 #' @param merge_level either \code{all, group_level} or \code{none}.
@@ -71,6 +71,7 @@ merge_GR <- function(x) {
 #'
 #' @importFrom TxDb.Hsapiens.UCSC.hg38.knownGene TxDb.Hsapiens.UCSC.hg38.knownGene
 #' @importFrom TxDb.Hsapiens.UCSC.hg19.knownGene TxDb.Hsapiens.UCSC.hg19.knownGene
+#' @importFrom TxDb.Mmusculus.UCSC.mm10.knownGene TxDb.Mmusculus.UCSC.mm10.knownGene
 #' @importFrom dplyr filter pull
 #' @importFrom ChIPseeker annotatePeak
 #' @importFrom data.table dcast
@@ -100,10 +101,10 @@ get_genomic_annotations <- function(data_table,
 
     ## check ref_gen
     if (ref_gen == "hg38") {
-
         txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene::TxDb.Hsapiens.UCSC.hg38.knownGene
+    } else if (ref_gen == "mm10") {
+        txdb <- TxDb.Mmusculus.UCSC.mm10.knownGene::TxDb.Mmusculus.UCSC.mm10.knownGene
     } else {
-
         txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene::TxDb.Hsapiens.UCSC.hg19.knownGene
     }
 

R/plot_browser_tracks.R

@@ -1,15 +1,15 @@
 getChrStartEnd <- function(x) {
-
-    x_chr <- gsub(":.*", "", x) %>% as.character()
-    x_start <- gsub(".*:", "", x) %>% gsub("-.*",
-        "", .) %>% as.numeric()
-    x_end <- gsub(".*:", "", x) %>% gsub(".*-",
-        "", .) %>% as.numeric()
-
-    x_res <- list(chr = x_chr, from = x_start,
-        to = x_end)
-
-    return(x_res)
+  
+  x_chr <- gsub(":.*", "", x) %>% as.character()
+  x_start <- gsub(".*:", "", x) %>% gsub("-.*",
+                                         "", .) %>% as.numeric()
+  x_end <- gsub(".*:", "", x) %>% gsub(".*-",
+                                       "", .) %>% as.numeric()
+  
+  x_res <- list(chr = x_chr, from = x_start,
+                to = x_end)
+  
+  return(x_res)
 }
 
 #' UCSC Genome browser like plots
@@ -21,15 +21,20 @@ getChrStartEnd <- function(x) {
 #'
 #' @param data_table a dataframe that contains \code{bw_path}, \code{sample_id} and \code{color_code}. Tracks are colored according to \code{color_code}. Default \code{NULL}
 #' @param gene_range genomic region for which browser-like plots needed in format \code{chr:start-end}. Default \code{NULL}
-#' @param ref_gen reference genome, to get gene annotations, currently supports  \code{hg19} and \code{hg38}. Default, \code{hg38}
+#' @param ref_gen reference genome, to get gene annotations, currently supports  \code{hg19} \code{mm10} and \code{hg38}. Default, \code{hg38}
 #' @param cex.axis axis label size, default \code{0.5}
 #' @param cex.title axis title size, default \code{0.8}
 #' @param ... additional arguments to change the appearence of a plot. All arguments that can be passed to base R graphics are supported
 #'
 #' @importFrom TxDb.Hsapiens.UCSC.hg38.knownGene TxDb.Hsapiens.UCSC.hg38.knownGene
 #' @importFrom TxDb.Hsapiens.UCSC.hg19.knownGene TxDb.Hsapiens.UCSC.hg19.knownGene
+#' @importFrom TxDb.Mmusculus.UCSC.mm10.knownGene TxDb.Mmusculus.UCSC.mm10.knownGene
 #' @importFrom dplyr filter pull
 #' @importFrom Gviz GeneRegionTrack DataTrack plotTracks
+#' @importFrom org.Mm.eg.db org.Mm.eg.db
+#' @importFrom org.Hs.eg.db org.Hs.eg.db
+#' @importFrom IRanges ranges
+#' @importFrom AnnotationDbi mapIds
 #'
 #' @return plot of genome browser tracks
 #'
@@ -58,67 +63,80 @@ plot_browser_tracks <- function(data_table,
                                 ref_gen = "hg38",
                                 cex.axis = 0.5,
                                 cex.title = 0.8, ...) {
-
-    assertthat::assert_that(is.data.frame(data_table), msg = "Please provide `data_table`")
-    assertthat::assert_that(assertthat::has_name(data_table, "bw_path"))
-    assertthat::assert_that(assertthat::has_name(data_table, "sample_id"))
-    assertthat::assert_that(assertthat::has_name(data_table, "color_code"))
-
-    assertthat::assert_that(!is.null(gene_range), msg = "Please provide `gene_range` in format; chr:start-end")
-
-    gene_range_split <- getChrStartEnd(x = gene_range)
-
-    ## build genetrack
-    if (ref_gen == "hg38") {
-
-        txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene::TxDb.Hsapiens.UCSC.hg38.knownGene
-
-    } else {
-
-        txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene::TxDb.Hsapiens.UCSC.hg19.knownGene
-    }
-
-    ##
-    grtrack <- Gviz::GeneRegionTrack(txdb,
-                                     genome = ref_gen,
-                                     chromosome = gene_range_split$chr,
-                                     window = -1, name = NULL, background.title = "white",
-                                     col.frame = "white", col.axis = "black",
-                                     col = "black", col.title = "black",
-                                     geneSymbol = TRUE, showId = TRUE,
-                                     from = gene_range_split$from, to = gene_range_split$to)
-
-    ## build enrichment tracks
-    dt_list <- list()
-    all_sample_ids <- data_table$sample_id %>%
-      as.character()
-
-    for (i in seq_along(all_sample_ids)) {
-
-        x_id <- all_sample_ids[i]
-        x_dat <- data_table %>% dplyr::filter(sample_id == get("x_id"))
-
-        x_bw <- x_dat %>% dplyr::pull(bw_path) %>% as.character()
-        x_col <- x_dat %>% dplyr::pull(color_code) %>% as.character()
-
-        x_dt <- Gviz::DataTrack(range = x_bw,
-                                genome = ref_gen,
-                                chromosome = gene_range_split$chr,
-                                name = x_id, type = "hist", window = -1,
-                                fill.histogram = x_col, col.histogram = "NA",
-                                background.title = "white", col.frame = "white",
-                                col.axis = "black", col = "black",
-                                col.title = "black")
-
-        dt_list[[i]] <- x_dt
-
-    }
-
-    gtrack_pos <- length(dt_list) + 1
-    dt_list[[gtrack_pos]] <- grtrack
-
-    Gviz::plotTracks(dt_list, from = gene_range_split$from,
-                     to = gene_range_split$to, cex.axis = cex.axis,
-                     cex.title = cex.title, ...)
-
+
+  assertthat::assert_that(is.data.frame(data_table), msg = "Please provide `data_table`")
+  assertthat::assert_that(assertthat::has_name(data_table, "bw_path"))
+  assertthat::assert_that(assertthat::has_name(data_table, "sample_id"))
+  assertthat::assert_that(assertthat::has_name(data_table, "color_code"))
+
+  assertthat::assert_that(!is.null(gene_range), msg = "Please provide `gene_range` in format; chr:start-end")
+
+  gene_range_split <- getChrStartEnd(x = gene_range)
+
+  ## build genetrack
+  if (ref_gen == "hg38") {
+    txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene::TxDb.Hsapiens.UCSC.hg38.knownGene
+    symbol_db <- org.Hs.eg.db::org.Hs.eg.db
+  } else if (ref_gen == "mm10") {
+    txdb <- TxDb.Mmusculus.UCSC.mm10.knownGene::TxDb.Mmusculus.UCSC.mm10.knownGene
+    symbol_db <- org.Mm.eg.db::org.Mm.eg.db
+  } else {
+    txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene::TxDb.Hsapiens.UCSC.hg19.knownGene
+    symbol_db <- org.Hs.eg.db::org.Hs.eg.db
+  }
+
+  ##
+  grtrack <- Gviz::GeneRegionTrack(txdb,
+                                   genome = ref_gen,
+                                   chromosome = gene_range_split$chr,
+                                   window = -1, name = NULL, background.title = "white",
+                                   col.frame = "white", col.axis = "black",
+                                   col = "black", col.title = "black",
+                                   geneSymbol = TRUE, showId = TRUE,
+                                   from = gene_range_split$from, to = gene_range_split$to,
+                                   collapseTranscripts="longest", shape="arrow", transcriptAnnotation = "symbol")
+
+  # map gene symbol
+  gene_ids = IRanges::ranges(grtrack)
+  gene_symbols <- AnnotationDbi::mapIds(symbol_db, keys=gene_ids$gene, column = "SYMBOL", keytype = "ENTREZID", multiVals = "first")
+  gene_symbols[is.na(names(gene_symbols))] <- gene_ids$transcript[is.na(names(gene_symbols))]
+  gene_ids$symbol <- gene_symbols
+  IRanges::ranges(grtrack) <- gene_ids
+
+  ## build enrichment tracks
+  dt_list <- list()
+  all_sample_ids <- data_table$sample_id %>%
+    as.character()
+
+  axisTrack <- Gviz::GenomeAxisTrack()
+  atrack <- length(dt_list)+1
+  dt_list[[atrack]] <- axisTrack
+
+  for (i in seq_along(all_sample_ids)) {
+
+    x_id <- all_sample_ids[i]
+    x_dat <- data_table %>% dplyr::filter(sample_id == get("x_id"))
+
+    x_bw <- x_dat %>% dplyr::pull(bw_path) %>% as.character()
+    x_col <- x_dat %>% dplyr::pull(color_code) %>% as.character()
+
+    x_dt <- Gviz::DataTrack(range = x_bw,
+                            genome = ref_gen,
+                            chromosome = gene_range_split$chr,
+                            name = gsub("_", " ", x_id), type = "hist", window = -1,
+                            fill.histogram = x_col, col.histogram = "NA",
+                            background.title = "white", col.frame = "white",
+                            col.axis = "black", col = "black",
+                            col.title = "black")
+
+    dt_list[[i+1]] <- x_dt
+
+  }
+
+  gtrack_pos <- length(dt_list) + 1
+  dt_list[[gtrack_pos]] <- grtrack
+
+  Gviz::plotTracks(dt_list, from = gene_range_split$from,
+                   to = gene_range_split$to, cex.axis = cex.axis,
+                   cex.title = cex.title, ...)
 }