Merge pull request #47 from ulelab/dev

Pre-release updates

CODEOWNERS

@@ -0,0 +1,50 @@
+# This is a comment.
+# Each line is a file pattern followed by one or more owners.
+
+# These owners will be the default owners for everything in
+# the repo. Unless a later match takes precedence,
+# @global-owner1 and @global-owner2 will be requested for
+# review when someone opens a pull request.
+*       @amchakra @CharlotteAnne
+
+# Order is important; the last matching pattern takes the most
+# precedence. When someone opens a pull request that only
+# modifies JS files, only @js-owner and not the global
+# owner(s) will be requested for a review.
+*.js    @js-owner
+
+# You can also use email addresses if you prefer. They'll be
+# used to look up users just like we do for commit author
+# emails.
+*.go docs@example.com
+
+# Teams can be specified as code owners as well. Teams should
+# be identified in the format @org/team-name. Teams must have
+# explicit write access to the repository. In this example,
+# the octocats team in the octo-org organization owns all .txt files.
+*.txt @octo-org/octocats
+
+# In this example, @doctocat owns any files in the build/logs
+# directory at the root of the repository and any of its
+# subdirectories.
+/build/logs/ @doctocat
+
+# The `docs/*` pattern will match files like
+# `docs/getting-started.md` but not further nested files like
+# `docs/build-app/troubleshooting.md`.
+docs/*  docs@example.com
+
+# In this example, @octocat owns any file in an apps directory
+# anywhere in your repository.
+apps/ @octocat
+
+# In this example, @doctocat owns any file in the `/docs`
+# directory in the root of your repository and any of its
+# subdirectories.
+/docs/ @doctocat
+
+# In this example, @octocat owns any file in the `/apps` 
+# directory in the root of your repository except for the `/apps/github` 
+# subdirectory, as its owners are left empty.
+/apps/ @octocat
+/apps/github 

README.md

@@ -124,6 +124,8 @@ Where multiple files are specified for a parameter, these should be comma-separa
 
 * `--highlight` can be used to specify a region in the format `'start_coordinate:end_coordinate'`. This will be highlighted by grey shading. 
 
+* `--tidy_y_labels` can be use to tidy the y-axis labels and keep alternate ones if there are 5 or more.
+
 ### 2. Auxiliary plot
 
 * `-y` or `--auxiliary` can be used to supply the auxiliary tracks. These should be in a standard 6-column BED format. Optionally, if a 9-column BED file is supplied then the 9th column `itemRgb` will be used to colour the intervals. These tracks could be peak intervals, but could be any features of interest. You can label the tracks with `--auxiliary_labels`, otherwise the first 10 characters of the filename are used.
@@ -225,8 +227,10 @@ cd test
 -w 50 \
 -y 'test_Alu_rev.bed.gz' \
 --auxiliary_labels 'reverse Alu' \
---coverage 'test_CTRL_plus.bigwig,test_KD1_plus.bigwig,test_KD2_plus.bigwig' \
---coverage_labels 'CTRL,KD1,KD2' \
+--coverage 'test_ERR127306_plus.bigwig,test_ERR127307_plus.bigwig,test_ERR127308_plus.bigwig,test_ERR127309_plus.bigwig,test_ERR127302_plus.bigwig,test_ERR127303_plus.bigwig,test_ERR127304_plus.bigwig,test_ERR127305_plus.bigwig' \
+--coverage_labels 'CTRL1 1,CTRL1 2,CTRL2 1,CTRL2 2,KD1 1,KD1 2,KD2 1,KD2 2' \
+--coverage_colours '#A1D99B,#74C476,#31A354,#006D2C,#FDAE6B,#E6550D,#FC9272,#DE2D26' \
+--coverage_groups 'CTRL,CTRL,CTRL,CTRL,KD,KD,KD,KD' \
 -g CD55_gencode.v34lift37.annotation.gtf.gz \
 -r 'chr1:207513000:207515000:+' \
 --highlight '207513650:207513800' \

clipplotr

@@ -26,7 +26,8 @@ option_list <- list(make_option(c("-x", "--xlinks"), action = "store", type = "c
                     make_option(c("", "--highlight"), action = "store", type = "character", help = "Region to highlight as 35754106:35856276"),                    
                     make_option(c("-n", "--normalisation"), action = "store", type = "character", help = "Normalisation options: none, maxpeak, libsize, custom, libsize_maxpeak, custom_maxpeak [default %default]", default = "libsize"),
                     make_option(c("", "--size_factors"), action = "store", type = "character", help = "Size factors for custom normalisation (comma separated)"),
-                    make_option(c("", "--scale_y"), action = "store_true", type = "logical", help = "Scale facetted CLIP y-axis", default = FALSE),
+                    make_option(c("", "--scale_y"), action = "store_true", type = "logical", help = "Scale CLIP y-axis for each group independently", default = FALSE),
+                    make_option(c("", "--tidy_y_labels"), action = "store", type = "integer", help = "Keep this many y-axis labels (may be slightly more or fewer depending on data)"),
                     make_option(c("-s", "--smoothing"), action = "store", type = "character", help = "Smoothing options: none, rollmean, gaussian [default %default]", default = "rollmean"),
                     make_option(c("-w", "--smoothing_window"), action = "store", type = "integer", help = "Smoothing window [default %default]", default = 100),
                     make_option(c("-a", "--annotation"), action = "store", type = "character", help = "Annotation options: original, gene, transcript, none [default %default]", default = "transcript"),
@@ -391,6 +392,13 @@ if(!is.null(opt$highlight)) {
 
 }
 
+if(!is.null(opt$tidy_y_labels)) {
+
+  # p.iclip <- p.iclip + scale_y_continuous(breaks = scales::breaks_extended(n = opt$tidy_y_labels))
+  p.iclip <- p.iclip + scale_y_continuous(n.breaks = opt$tidy_y_labels)
+
+}
+
 # ==========
 # Part 1b - top half: auxiliary file annotation (eg.peaks)
 # ==========
@@ -515,7 +523,6 @@ if(!is.null(opt$coverage)) {
           y = "Coverage",
           colour = "") +
       scale_colour_manual(values = coverage_colours) +
-      # facet_grid(exp ~ ., labeller=label_wrap_gen(10)) +
       theme_minimal_grid() + theme(legend.position = "bottom") + theme(strip.text.y = element_text(size = 10, angle = 0, hjust = 0)) +
       xlim(start(region.gr), end(region.gr))
 
@@ -527,7 +534,6 @@ if(!is.null(opt$coverage)) {
            y = "Coverage",
            colour = "") +
       scale_colour_tableau(palette = "Superfishel Stone") +
-      # facet_grid(exp ~ ., labeller=label_wrap_gen(10)) +
       theme_minimal_grid() + theme(legend.position = "bottom") + theme(strip.text.y = element_text(size = 10, angle = 0, hjust = 0)) +
       xlim(start(region.gr), end(region.gr))
 
@@ -671,11 +677,6 @@ if(opt$annotation == "transcript") {
   # Plot
   p.annot <- ggplot() +
     geom_segment(data = sel.region.tiled.dt, mapping = aes(x = start, xend = end, y = group, yend = group), arrow = arrow(length = unit(0.1, "cm")), colour = "grey50") +
-    # geom_rect(data = sel.exons_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.25, ymax = group + 0.25), fill = "black") +
-    # geom_rect(data = sel.cds_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.25, ymax = group + 0.25), fill = "black") +
-    # geom_rect(data = sel.utr5_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.15, ymax = group + 0.15), fill = "black") +
-    # geom_rect(data = sel.utr3_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.15, ymax = group + 0.15), fill = "black") +
-    # geom_text(data = tx.order.dt, aes(label = transcript_id, y = group, x = centre), size = 3, vjust = 0) +
     geom_rect(data = sel.exons_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.25, ymax = group + 0.25, fill = gene)) +
     geom_rect(data = sel.cds_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.25, ymax = group + 0.25, fill = gene)) +
     geom_rect(data = sel.utr5_tx.dt, mapping = aes(xmin = start, xmax = end, ymin = group - 0.15, ymax = group + 0.15, fill = gene)) +
@@ -687,14 +688,6 @@ if(opt$annotation == "transcript") {
          fill = "") +
     coord_cartesian(xlim = c(start(region), end(region)))
 
-  # 
-  # if(opt$show_tx_name == TRUE) {
-  #   
-  #   p.annot <- p.annot + geom_text(data = tx.order.dt, aes(label = transcript_id, y = group + 0.3, x = centre), size = 3, vjust = 0)
-  #   # Need to fix ones that are outside of window
-  #   
-  # }
-
 }
 
 # ==========
@@ -777,8 +770,7 @@ if(is.null(opt$ratios)){ #if the user hasnt specified ratios
     # Could change this to ifelse depending on annotation style
   }
   p <- p + plot_layout(heights = ratios) 
-} else { #if the user has specified ratios
-  # rts = unlist(strsplit(opt$ratios, ",")) # This is already defined at the beginning
+} else { 
   p <- p.iclip
   ratios <- rts[[1]]
   if(exists("p.auxiliary")) {

examples/make_plots_for_figures.sh

@@ -23,7 +23,10 @@ $CLIPPLOTR \
 -w 50 \
 -y 'Alu_rev.bed.gz' \
 --auxiliary_labels 'reverse Alu' \
---coverage 'CTRL.bigwig,KD1.bigwig,KD2.bigwig' \
+--coverage 'ERR127306_plus.bigwig,ERR127307_plus.bigwig,ERR127308_plus.bigwig,ERR127309_plus.bigwig,ERR127302_plus.bigwig,ERR127303_plus.bigwig,ERR127304_plus.bigwig,ERR127305_plus.bigwig' \
+--coverage_labels 'CTRL1 1,CTRL1 2,CTRL2 1,CTRL2 2,KD1 1,KD1 2,KD2 1,KD2 2' \
+--coverage_colours '#A1D99B,#74C476,#31A354,#006D2C,#FDAE6B,#E6550D,#FC9272,#DE2D26' \
+--coverage_groups 'CTRL,CTRL,CTRL,CTRL,KD,KD,KD,KD' \
 -g gencode.v34lift37.annotation.gtf.gz \
 -r 'chr1:207513000:207515000:+' \
 --highlight '207513650:207513800' \
@@ -83,27 +86,15 @@ $CLIPPLOTR \
 -n libsize \
 -y 'HepG2.bed.gz,K562.bed.gz' \
 --auxiliary_labels 'HepG2 peaks,K562 peaks' \
--g gencode.v34.annotation.gtf.gz \
+-g gencode.v34.basic.annotation.gtf.gz \
 -r 'chr17:8458500:8469500:+' \
+--highlight '8462500:8467500' \
 -a gene \
 --ratio '2,0.5,0,0.25' \
 --size_x 200 \
 --size_y 200 \
 -o '../../plots/NDEL1_libsize_gene.pdf'
 
-# $CLIPPLOTR \
-# -x 'ENCFF239CML.xl.bed.gz,ENCFF170YQV.xl.bed.gz,ENCFF515BTB.xl.bed.gz,ENCFF537RYR.xl.bed.gz,ENCFF296GDR.xl.bed.gz,ENCFF212IIR.xl.bed.gz' \
-# -l 'HepG2 IP1,HepG2 IP2,HepG2 SMI,K562 IP1,K562_IP2,K562 SMI' \
-# -c '#324376,#586BA4,#B4BCD6,#771434,#A54D69,#D2A6B4' \
-# --groups 'HepG2,HepG2,HepG2,K562,K562,K562' \
-# -n libsize \
-# -y 'HepG2.bed.gz,K562.bed.gz' \
-# --auxiliary_labels 'HepG2 peaks,K562 peaks' \
-# -g gencode.v34.annotation.gtf.gz \
-# -r 'chr17:8458500:8469500:+' \
-# -a transcript \
-# -o '../../plots/NDEL1_libsize.pdf'
-
 $CLIPPLOTR \
 -x 'ENCFF239CML.xl.bed.gz,ENCFF170YQV.xl.bed.gz,ENCFF515BTB.xl.bed.gz,ENCFF537RYR.xl.bed.gz,ENCFF296GDR.xl.bed.gz,ENCFF212IIR.xl.bed.gz' \
 -l 'HepG2 IP1,HepG2 IP2,HepG2 SMI,K562 IP1,K562_IP2,K562 SMI' \
@@ -112,37 +103,40 @@ $CLIPPLOTR \
 -n libsize \
 --scale_y \
 -g gencode.v34.annotation.gtf.gz \
--r 'chr17:8458500:8469500:+' \
+-r 'chr17:8462500:8467500:+' \
 -a none \
 --ratio '2,0.5,0,0.25' \
 --size_x 200 \
 --size_y 100 \
+--tidy_y_labels 4 \
 -o '../../plots/NDEL1_libsize_scaled.pdf'
 
 $CLIPPLOTR \
 -x 'ENCFF239CML.xl.bed.gz,ENCFF170YQV.xl.bed.gz,ENCFF515BTB.xl.bed.gz,ENCFF537RYR.xl.bed.gz,ENCFF296GDR.xl.bed.gz,ENCFF212IIR.xl.bed.gz' \
 -l 'HepG2 IP1,HepG2 IP2,HepG2 SMI,K562 IP1,K562_IP2,K562 SMI' \
 -c '#324376,#586BA4,#B4BCD6,#771434,#A54D69,#D2A6B4' \
 --groups 'HepG2,HepG2,HepG2,K562,K562,K562' \
--n libsize_maxpeak \
+-n maxpeak \
 -g gencode.v34.annotation.gtf.gz \
--r 'chr17:8458500:8469500:+' \
+-r 'chr17:8462500:8467500:+' \
 -a none \
 --ratio '2,0.5,0,0.25' \
---size_x 205 \
+--size_x 198 \
 --size_y 100 \
--o '../../plots/NDEL1_libsize_maxpeak.pdf'
+--tidy_y_labels 3 \
+-o '../../plots/NDEL1_maxpeak.pdf'
 
 $CLIPPLOTR \
 -x 'ENCFF239CML.xl.bed.gz,ENCFF170YQV.xl.bed.gz,ENCFF515BTB.xl.bed.gz,ENCFF537RYR.xl.bed.gz,ENCFF296GDR.xl.bed.gz,ENCFF212IIR.xl.bed.gz' \
 -l 'HepG2 IP1,HepG2 IP2,HepG2 SMI,K562 IP1,K562_IP2,K562 SMI' \
 -c '#324376,#586BA4,#B4BCD6,#771434,#A54D69,#D2A6B4' \
 --groups 'HepG2,HepG2,HepG2,K562,K562,K562' \
--n maxpeak \
+-n libsize_maxpeak \
 -g gencode.v34.annotation.gtf.gz \
--r 'chr17:8458500:8469500:+' \
+-r 'chr17:8462500:8467500:+' \
 -a none \
 --ratio '2,0.5,0,0.25' \
---size_x 200 \
+--size_x 207 \
 --size_y 100 \
--o '../../plots/NDEL1_maxpeak.pdf'
+--tidy_y_labels 3 \
+-o '../../plots/NDEL1_libsize_maxpeak.pdf'