| Previous changeset 7:c9e267cb84c0 (2016-09-18) Next changeset 9:92898cc3ea19 (2016-10-08) |
|
Commit message:
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_sr_readmap_and_size_histograms commit 97b40d7a593cef6c3303f7baba781a84d242e454 |
|
modified:
readmap.py readmap.xml smRtools.py test-data/Readmap_dataframe.tab test-data/Size_distribution_dataframe.tab |
|
added:
plot_size_readmap.r |
|
removed:
smRtools.pyc test-data/Readmaps.pdf test-data/Size_distribution.pdf test-data/Size_distribution_and_Readmaps.pdf tool_dependencies.xml |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc plot_size_readmap.r --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/plot_size_readmap.r Mon Sep 19 06:16:21 2016 -0400 |
| [ |
| @@ -0,0 +1,145 @@ +## Setup R error handling to go to stderr +options( show.error.messages=F, + error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } ) +library(RColorBrewer) +library(lattice) +library(latticeExtra) +library(grid) +library(gridExtra) +library(optparse) + +# Parse arguments +option_list <- list( + make_option(c("-r", "--readmap_tab"), type="character", help="Path to file with tabular readmap"), + make_option(c("-s", "--size_distribution_tab"), type="character", help="Path to file with tabular size distribution"), + make_option("--readmap_pdf", type="character", help="Path to file with readmap plot"), + make_option("--size_distribution_pdf", type="character", help="Path to file with size distribution plot"), + make_option("--combi_pdf", type="character", help="Path to file with size distribution and readmap plot"), + make_option("--title", type="character", help="Title for readmaps and size distribution"), + make_option("--xlabel", type="character", help="xlabel for readmaps and size distribution"), + make_option("--ylabel", type="character", help="ylabel for readmaps and size distribution"), + make_option("--yrange", type="integer", help="Y-axis range"), + make_option("--rows_per_page", type="integer", help="rows_per_page") + ) + +parser <- OptionParser(usage = "%prog [options] file", option_list=option_list) +args = parse_args(parser) + +## data frames implementation + +rm=read.delim(args$readmap_tab, header=T, row.names=NULL) +n_samples=length(unique(rm$sample)) +genes=unique(levels(rm$gene)) +per_gene_readmap=lapply(genes, function(x) subset(rm, gene==x)) +n_genes=length(per_gene_readmap) + +size=read.delim(args$size_distribution_tab, header=T, row.names=NULL) +per_gene_size=lapply(genes, function(x) subset(size, gene==x)) + +## end of data frames implementation + +## functions + +plot_readmap=function(df, ...) { +combineLimits(xyplot(count~coord|factor(sample, levels=unique(sample))+reorder(gene, count, function(x) -sum(abs(x))), +data=df, +type='h', +scales= list(relation="free", x=list(rot=0, cex=0.7, axs="i", tck=0.5), y=list(tick.number=4, rot=90, cex=0.7)), +xlab=NULL, main=NULL, ylab=NULL, +as.table=T, +origin = 0, +horizontal=FALSE, +group=polarity, +col=c("red","blue"), +par.strip.text = list(cex=0.7), +...)) +} + +plot_size_distribution= function(df, ...) { + smR.prepanel=function(x,y,...){; yscale=c(-max(abs(y)), max(abs(y)));list(ylim=yscale);} + bc= barchart(count~as.factor(size)|factor(sample, levels=unique(sample))+gene, data = df, origin = 0, + horizontal=FALSE, +group=polarity, +stack=TRUE, + col=c('red', 'blue'), + cex=0.75, + scales=list(y=list(tick.number=4, rot=90, relation="free", cex=0.7), x=list(cex=0.7) ), + prepanel=smR.prepanel, + xlab = NULL, + ylab = NULL, + main = NULL, + as.table=TRUE, + newpage = T, + par.strip.text = list(cex=0.7), + ...) + combineLimits(bc) + } + +## end of functions + +## function parameters' + +par.settings.readmap=list(layout.heights=list(top.padding=0, bottom.padding=-2.5), strip.background = list(col=c("lightblue","lightgreen")) ) +par.settings.size=list(layout.heights=list(top.padding=-1, bottom.padding=-2.5), strip.background = list(col=c("lightblue","lightgreen")) ) +par.settings.combination.readmap=list(layout.heights=list(top.padding=0, bottom.padding=-3), strip.background=list(col=c("lightblue","lightgreen")) ) +par.settings.combination.size=list(layout.heights=list(top.padding=-2, bottom.padding=-0.5), strip.background=list(col=c("lightblue", "lightgreen")) ) + +## end of function parameters' + +## GRAPHS + +if (n_genes > 7) {page_height_simple = 11.69; page_height_combi=11.69; rows_per_page=args$rows_per_page} else { + rows_per_page= n_genes; page_height_simple = 2.5*n_genes; page_height_combi=page_height_simple*2 } +if (n_samples > 4) {page_width = 8.2677*n_samples/4} else {page_width = 8.2677*n_samples/3} # to test + + +pdf(file=args$readmap_pdf, paper="special", height=page_height_simple, width=page_width) +for (i in seq(1,n_genes,rows_per_page)) { +start=i +end=i+rows_per_page-1 +if (end>n_genes) {end=n_genes} +if (args$yrange == 0) { readmap_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, par.settings=par.settings.readmap)) } else { +readmap_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, ylim=c(-args.yrange, args.yrange) , par.settings=par.settings.readmap)) } +args_list=c(readmap_plot.list, list(nrow=rows_per_page, ncol=1, + top=textGrob("Read Maps (nucleotide coordinates)", gp=gpar(cex=1), just="top"), + left=textGrob(args$ylabel, gp=gpar(cex=1), vjust=1, rot=90) + ) + ) +do.call(grid.arrange, args_list) +} +devname=dev.off() + +pdf(file=args$size_distribution_pdf, paper="special", height=page_height_simple, width=page_width) +for (i in seq(1,n_genes,rows_per_page)) { +start=i +end=i+rows_per_page-1 +if (end>n_genes) {end=n_genes} +plot.list=lapply(per_gene_size[start:end], function(x) plot_size_distribution(x, par.settings=par.settings.size) ) +args_list=c(plot.list, list(nrow=rows_per_page, ncol=1, + top=textGrob("Size distributions (in nucleotides)", gp=gpar(cex=1), just="top"), + left=textGrob(args$ylabel, gp=gpar(cex=1), vjust=1, rot=90) + ) + ) +do.call(grid.arrange, args_list) +} +devname=dev.off() + +pdf(file=args$combi_pdf, paper="special", height=page_height_combi, width=page_width) +if (rows_per_page %% 2 != 0) { rows_per_page = rows_per_page + 1} +for (i in seq(1,n_genes,rows_per_page/2)) { +start=i +end=i+rows_per_page/2-1 +if (end>n_genes) {end=n_genes} +if (args$yrange == 0) {readmap_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, par.settings=par.settings.readmap)) } else { +readmap_plot.list=lapply(per_gene_readmap[start:end], function(x) plot_readmap(x, ylim=c(-args.yrange, args.yrange), par.settings=par.settings.readmap)) } +size_plot.list=lapply(per_gene_size[start:end], function(x) plot_size_distribution(x, strip=FALSE, par.settings=par.settings.combination.size)) +plot.list=rbind(readmap_plot.list, size_plot.list ) +args_list=c(plot.list, list(nrow=rows_per_page+1, ncol=1, + top=textGrob(args$title, gp=gpar(cex=1), just="top"), + left=textGrob(args$ylabel, gp=gpar(cex=1), vjust=1, rot=90), + sub=textGrob(args$xlabel, gp=gpar(cex=1), just="bottom") + ) + ) +do.call(grid.arrange, args_list) +} +devname=dev.off() \ No newline at end of file |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc readmap.py --- a/readmap.py Sun Sep 18 12:55:27 2016 -0400 +++ b/readmap.py Mon Sep 19 06:16:21 2016 -0400 |
| [ |
| @@ -23,7 +23,6 @@ the_parser.add_argument('--gff', type=str, help="GFF containing regions of interest") the_parser.add_argument('--minquery', type=int, help="Minimum readsize") the_parser.add_argument('--maxquery', type=int, help="Maximum readsize") - the_parser.add_argument('--rcode', type=str, help="R script") args = the_parser.parse_args() return args @@ -38,7 +37,6 @@ size_distribution_file=args.output_size_distribution minquery=args.minquery maxquery=args.maxquery -Rcode = args.rcode filePath=args.input fileExt=args.ext fileLabel=args.label @@ -54,16 +52,19 @@ biosample=fileLabel[i], size_inf=minquery, size_sup=maxquery, norm=norm) return MasterListOfGenomes -def dataframe_sanityzer (listofdatalines): - Dict = defaultdict(float) +def remove_null_entries(listofdatalines): + """ + This function removes genes that have no reads aligned. + """ + Dict = defaultdict(float) for line in listofdatalines: fields= line.split("\t") - Dict[fields[0]] += float (fields[2]) + Dict[fields[0]] += abs(float(fields[2])) filtered_list = [] for line in listofdatalines: fields= line.split("\t") if Dict[fields[0]] != 0: - filtered_list.append(line) + filtered_list.append(line) return filtered_list @@ -110,9 +111,8 @@ plottable = dict[gene].readplot() plottable = handle_start_stop_coordinates(plottable, readDict) for line in plottable: - #print >>readmap, "%s\t%s" % (line, sample) listoflines.append ("%s\t%s" % (line, sample)) - listoflines = dataframe_sanityzer(listoflines) + listoflines = remove_null_entries(listoflines) for line in listoflines: print >>readmap, line @@ -126,19 +126,15 @@ else: dict=readDict[sample].instanceDict for gene in dict.keys(): - histogram = dict[gene].size_histogram(minquery=args.minquery, maxquery=args.maxquery) + histogram = dict[gene].size_histogram(minquery=minquery, maxquery=maxquery) for polarity in histogram.keys(): if polarity=='both': continue - #for size in xrange(args.minquery, args.maxquery): - # if not size in histogram[polarity].keys(): - # histogram[size]=0 for size, count in histogram[polarity].iteritems(): - #print >>size_distrib, "%s\t%s\t%s\t%s\t%s" % (gene, size, count, polarity, sample) # test, changed the order accordingly listoflines.append ("%s\t%s\t%s\t%s\t%s" % (gene, size, count, polarity, sample) ) - listoflines = dataframe_sanityzer(listoflines) + listoflines = remove_null_entries(listoflines) for line in listoflines: - print >>size_distrib, line + print >>size_distrib, line def gff_item_subinstances(readDict, gff3): GFFinstanceDict=OrderedDict() @@ -154,10 +150,6 @@ item_downstream_coordinate = int(gff_fields[4]) item_polarity = gff_fields[6] for sample in readDict.keys(): -## this is not required anymore but test -# if not GFFinstanceDict.has_key(sample): -# GFFinstanceDict[sample]={} -#### subinstance=extractsubinstance(item_upstream_coordinate, item_downstream_coordinate, readDict[sample].instanceDict[chrom]) if item_polarity == '-': subinstance.readDict={key*-1:value for key, value in subinstance.readDict.iteritems()} @@ -172,8 +164,4 @@ write_readplot_dataframe(MasterListOfGenomes, readmap_file) write_size_distribution_dataframe(MasterListOfGenomes, size_distribution_file) - -R_command="Rscript "+ Rcode -process = subprocess.Popen(R_command.split()) -process.wait() |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc readmap.xml --- a/readmap.xml Sun Sep 18 12:55:27 2016 -0400 +++ b/readmap.xml Mon Sep 19 06:16:21 2016 -0400 |
| [ |
| b'@@ -1,239 +1,109 @@\n-<tool id="Readmap" name="Generate readmap and histograms from alignment files" version="1.1.5">\n- <description>from sRbowtie aligment</description>\n- <requirements>\n- <requirement type="package" version="0.12.7">bowtie</requirement>\n- <requirement type="package" version="0.7.7">pysam</requirement>\n- <requirement type="package" version="3.1.2">R</requirement>\n- <requirement type="package" version="2.14">biocbasics</requirement>\n- <requirement type="package" version="1.9">numpy</requirement>\n- </requirements>\n-<command interpreter="python">\n- readmap.py \n-\t #if $refGenomeSource.genomeSource == "history":\n- \t --reference_fasta ## sys.argv[2]\n- $refGenomeSource.ownFile ## index source\n- \t #else:\n- #silent reference= filter( lambda x: str( x[0] ) == str( $refGenomeSource.series[0].input.dbkey ), $__app__.tool_data_tables[ \'bowtie_indexes\' ].get_fields() )[0][-1]\n-\t\t --reference_bowtie_index\n- $reference\n- \t #end if\n-\t\t --rcode\n-\t\t $plotCode\n-\t\t --output_readmap\n-\t\t $readmap_dataframe\n-\t\t --output_size_distribution\n-\t\t $size_distribution_dataframe\n-\t\t --minquery\n-\t\t $minquery\n-\t\t --maxquery\n-\t\t $maxquery\n-\t\t --input\n-\t\t #for $i in $refGenomeSource.series\n- \t\t $i.input \n-\t\t #end for\n-\t\t --ext\n-\t\t #for $i in $refGenomeSource.series\n- \t\t $i.input.ext \n-\t\t #end for\n-\t\t --label\n-\t\t #for $i in $refGenomeSource.series\n- \t\t "$i.input.name" \n-\t\t #end for\n-\t\t --normalization_factor\n-\t\t #for $i in $refGenomeSource.series\n- \t\t $i.norm\n-\t\t #end for\n-\t\t #if $gff:\n-\t\t --gff\n- $gff\n- #end if\n-\n+<tool id="Readmap" name="Generate readmap and histograms from alignment files" version="1.2.0">\n+ <description>from sRbowtie aligment</description>\n+ <requirements>\n+ <requirement type="package" version="1.0.0">bowtie</requirement>\n+ <requirement type="package" version="0.9.0">pysam</requirement>\n+ <requirement type="package" version="1.9.3">numpy</requirement>\n+ <requirement type="package" version="1.3.0">r-optparse</requirement>\n+ <requirement type="package" version="0.6_26">r-latticeextra</requirement>\n+ <requirement type="package" version="2.0.0">r-gridextra</requirement>\n+ </requirements>\n+ <command><![CDATA[\n+ python2 $__tool_directory__/readmap.py\n+ #if $refGenomeSource.genomeSource == "history":\n+ --reference_fasta\n+ $refGenomeSource.ownFile ## index source\n+ #else:\n+ #silent reference= filter( lambda x: str( x[0] ) == str( $refGenomeSource.series[0].input.dbkey ), $__app__.tool_data_tables[ \'bowtie_indexes\' ].get_fields() )[0][-1]\n+ --reference_bowtie_index\n+ $reference\n+ #end if\n+ --output_readmap\n+ "$readmap_dataframe"\n+ --output_size_distribution\n+ "$size_distribution_dataframe"\n+ --minquery $minquery\n+ --maxquery $maxquery\n+ --input\n+ #for $i in $refGenomeSource.series\n+ $i.input\n+ #end for\n+ --ext\n+ #for $i in $refGenomeSource.series\n+ $i.input.ext\n+ #end for\n+ --label\n+ #for $i in $refGenomeSource.series\n+ "$i.input.name"\n+ #end for\n+ --normalization_factor\n+ #for $i in $refGenomeSource.series\n+ $i.norm\n+ #end for\n+ #if $gff:\n+ --gff\n+ $gff\n+ #end if\n+ ; Rscript $__tool_directory__/plot_size_readmap.r\n+ --readmap_tab "$readmap_dataframe"\n+ --size_distribution_tab "$size_distribution_dataframe"\n+ --readmap_pdf "$readmap_PDF"\n+ --size_distribution_pdf "$size_PDF"\n+ --combi_pdf "$combi_PDF"\n+ --title "$title"\n+ --xlabel "$xlabel"\n+ --ylabel "$ylabel"\n+ --yrange "$yrange"\n+ --rows_p'..b'\n+ </outputs>\n+ <help>\n \n **What it does**\n \n-Takes one or more alignment files (BAM, SAM or tabular bowtie output) as input and produces a "Readmap", \n-where by default for each "chromosome" the position of the read is recorded on the x-axis, and the y-axis indicates \n+Takes one or more alignment files (BAM, SAM or tabular bowtie output) as input and produces a "Readmap",\n+where by default for each "chromosome" the position of the read is recorded on the x-axis, and the y-axis indicates\n the number of reads per position. Reads that map in sense are on the top, reads that map antisense are on the bottom.\n \n \n@@ -248,42 +118,39 @@\n Query sequence::\n For a SAM file as the following:\n \n- 5\t16\t2L_79\t24393\t255\t17M\t*\t0\t0\tCCTTCATCTTTTTTTTT\tIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:17\tNM:i:0\n+5\t16\t2L_79\t24393\t255\t17M\t*\t0\t0\tCCTTCATCTTTTTTTTT\tIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:17\tNM:i:0\n \n- 11\t0\t2R_1\t12675\t255\t21M\t*\t0\t0\tAAAAAAAACGCGTCCTTGTGC\tIIIIIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:21\tNM:i:0\n+11\t0\t2R_1\t12675\t255\t21M\t*\t0\t0\tAAAAAAAACGCGTCCTTGTGC\tIIIIIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:21\tNM:i:0\n \n- 2\t16\t2L_5\t669\t255\t23M\t*\t0\t0\tTGTTGCTGCATTTCTTTTTTTTT\tIIIIIIIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:23\tNM:i:0\n+2\t16\t2L_5\t669\t255\t23M\t*\t0\t0\tTGTTGCTGCATTTCTTTTTTTTT\tIIIIIIIIIIIIIIIIIIIIIII\tXA:i:0\tMD:Z:23\tNM:i:0\n \n produce a plot like this:\n \n ----\n \n-.. image:: static/images/readmap.png \n- :height: 800 \n- :width: 500\n+.. image:: static/images/readmap.png\n+:height: 800\n+:width: 500\n \n-</help>\n- <tests>\n- <test>\n- <param name="genomeSource" value="history" />\n- <param name="ownFile" value ="transposons.fasta" ftype="fasta" />\n- <param name="series_0|input" value="sample1.srbowtie_out" ftype="tabular"/>\n- <param name="series_0|norm" value="1" />\n- <param name="series_1|input" value="sample2.srbowtie_out" ftype="tabular"/>\n- <param name="series_1|norm" value="1" />\n- <param name="series_2|input" value="sample3.srbowtie_out" ftype="tabular"/>\n- <param name="series_2|norm" value="1" />\n- <param name="minquery" value="20" />\n- <param name="maxquery" value="30" />\n- <param name="title" value="Readmaps and size distributions" />\n- <param name="xlabel" value="Coordinates/read size" />\n- <param name="ylabel" value="Number of reads" />\n- <param name="rows_per_page" value="8" />\n- <output name="readmap_dataframe" ftype="tabular" file="Readmap_dataframe.tab" />\n- <output name="size_distribution_dataframe" ftype="tabular" file="Size_distribution_dataframe.tab" />\n- <output name="readmap_PDF" ftype="pdf" file="Readmaps.pdf" />\n- <output name="size_PDF" ftype="pdf" file="Size_distribution.pdf" />\n- <output name="combi_PDF" ftype="pdf" file="Size_distribution_and_Readmaps.pdf" />\n- </test>\n- </tests>\n+ </help>\n+ <tests>\n+ <test>\n+ <param name="genomeSource" value="history" />\n+ <param name="ownFile" value ="transposons.fasta" ftype="fasta" />\n+ <param name="series_0|input" value="sample1.srbowtie_out" ftype="tabular"/>\n+ <param name="series_0|norm" value="1" />\n+ <param name="series_1|input" value="sample2.srbowtie_out" ftype="tabular"/>\n+ <param name="series_1|norm" value="1" />\n+ <param name="series_2|input" value="sample3.srbowtie_out" ftype="tabular"/>\n+ <param name="series_2|norm" value="1" />\n+ <param name="minquery" value="20" />\n+ <param name="maxquery" value="30" />\n+ <param name="title" value="Readmaps and size distributions" />\n+ <param name="xlabel" value="Coordinates/read size" />\n+ <param name="ylabel" value="Number of reads" />\n+ <param name="rows_per_page" value="8" />\n+ <output name="readmap_dataframe" ftype="tabular" file="Readmap_dataframe.tab" />\n+ <output name="size_distribution_dataframe" ftype="tabular" file="Size_distribution_dataframe.tab" />\n+ </test>\n+ </tests>\n </tool>\n' |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc smRtools.py --- a/smRtools.py Sun Sep 18 12:55:27 2016 -0400 +++ b/smRtools.py Mon Sep 19 06:16:21 2016 -0400 |
| [ |
| @@ -142,26 +142,6 @@ self.alignedReads += 1 F.close() return self.instanceDict -# elif self.alignmentFileFormat == "sam": -# F = open (self.alignmentFile, "r") -# dict = {"0":"+", "16":"-"} -# for line in F: -# if line[0]=='@': -# continue -# fields = line.split() -# if fields[2] == "*": continue -# polarity = dict[fields[1]] -# gene = fields[2] -# offset = int(fields[3]) -# size = len (fields[9]) -# if self.size_inf: -# if (size>=self.size_inf and size<= self.size_sup): -# self.instanceDict[gene].addread (polarity, offset, size) -# self.alignedReads += 1 -# else: -# self.instanceDict[gene].addread (polarity, offset, size) -# self.alignedReads += 1 -# F.close() elif self.alignmentFileFormat == "bam" or self.alignmentFileFormat == "sam": import pysam samfile = pysam.Samfile(self.alignmentFile) @@ -184,22 +164,6 @@ self.alignedReads += 1 return self.instanceDict -# def size_histogram (self): -# size_dict={} -# size_dict['F']= defaultdict (int) -# size_dict['R']= defaultdict (int) -# size_dict['both'] = defaultdict (int) -# for item in self.instanceDict: -# buffer_dict_F = self.instanceDict[item].size_histogram()['F'] -# buffer_dict_R = self.instanceDict[item].size_histogram()['R'] -# for size in buffer_dict_F: -# size_dict['F'][size] += buffer_dict_F[size] -# for size in buffer_dict_R: -# size_dict['R'][size] -= buffer_dict_R[size] -# allSizeKeys = list (set (size_dict['F'].keys() + size_dict['R'].keys() ) ) -# for size in allSizeKeys: -# size_dict['both'][size] = size_dict['F'][size] + size_dict['R'][size] -# return size_dict def size_histogram (self): # in HandleSmRNAwindows '''refactored on 7-9-2014 to debug size_histogram tool''' size_dict={} @@ -361,24 +325,7 @@ for offset in range (min(dicsize.keys()), max(dicsize.keys())+1): dicsize[size] = dicsize.get(size, 0) # to fill offsets with null values return dicsize - -# def size_histogram(self): -# norm=self.norm -# hist_dict={} -# hist_dict['F']={} -# hist_dict['R']={} -# for offset in self.readDict: -# for size in self.readDict[offset]: -# if offset < 0: -# hist_dict['R'][size] = hist_dict['R'].get(size, 0) - 1*norm -# else: -# hist_dict['F'][size] = hist_dict['F'].get(size, 0) + 1*norm -# ## patch to avoid missing graphs when parsed by R-lattice. 27-08-2014. Test and validate ! -# if not (hist_dict['F']) and (not hist_dict['R']): -# hist_dict['F'][21] = 0 -# hist_dict['R'][21] = 0 -# ## -# return hist_dict + def size_histogram(self, minquery=None, maxquery=None): # in SmRNAwindow '''refactored on 7-9-2014 to debug size_histogram tool''' @@ -480,7 +427,6 @@ return ". | %s" % (freqDic["Trev"] / reverse_sum * 100) else: return "%s | %s" % (freqDic["Tfor"] / forward_sum * 100, freqDic["Trev"] / reverse_sum * 100) - def readplot (self): norm=self.norm |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc smRtools.pyc |
| b |
| Binary file smRtools.pyc has changed |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc test-data/Readmap_dataframe.tab --- a/test-data/Readmap_dataframe.tab Sun Sep 18 12:55:27 2016 -0400 +++ b/test-data/Readmap_dataframe.tab Mon Sep 19 06:16:21 2016 -0400 |
| b |
| b'@@ -1,4 +1,5 @@\n gene\tcoord\tcount\tpolarity\tsample\n+FBti0020401\t0\t0\tF\tsample1.srbowtie_out\n FBti0020401\t78\t-1.0\tR\tsample1.srbowtie_out\n FBti0020401\t102\t-1.0\tR\tsample1.srbowtie_out\n FBti0020401\t271\t-1.0\tR\tsample1.srbowtie_out\n@@ -47,12 +48,20 @@\n FBti0020401\t6184\t-2.0\tR\tsample1.srbowtie_out\n FBti0020401\t6209\t1.0\tF\tsample1.srbowtie_out\n FBti0020401\t6327\t-2.0\tR\tsample1.srbowtie_out\n+FBti0020401\t6348\t0\tF\tsample1.srbowtie_out\n+FBti0020406\t0\t0\tF\tsample1.srbowtie_out\n FBti0020406\t174\t1.0\tF\tsample1.srbowtie_out\n FBti0020406\t516\t-1.0\tR\tsample1.srbowtie_out\n FBti0020406\t542\t-1.0\tR\tsample1.srbowtie_out\n FBti0020406\t595\t-1.0\tR\tsample1.srbowtie_out\n+FBti0020406\t812\t0\tF\tsample1.srbowtie_out\n+FBti0019511\t0\t0\tF\tsample1.srbowtie_out\n FBti0019511\t1\t0\tF\tsample1.srbowtie_out\n+FBti0019511\t1402\t0\tF\tsample1.srbowtie_out\n+FBti0019512\t0\t0\tF\tsample1.srbowtie_out\n FBti0019512\t1\t0\tF\tsample1.srbowtie_out\n+FBti0019512\t221\t0\tF\tsample1.srbowtie_out\n+FBti0019473\t0\t0\tF\tsample1.srbowtie_out\n FBti0019473\t62\t-1.0\tR\tsample1.srbowtie_out\n FBti0019473\t199\t-1.0\tR\tsample1.srbowtie_out\n FBti0019473\t203\t1.0\tF\tsample1.srbowtie_out\n@@ -109,6 +118,8 @@\n FBti0019473\t4860\t-1.0\tR\tsample1.srbowtie_out\n FBti0019473\t4939\t1.0\tF\tsample1.srbowtie_out\n FBti0019473\t4948\t-2.0\tR\tsample1.srbowtie_out\n+FBti0019473\t5368\t0\tF\tsample1.srbowtie_out\n+FBti0019518\t0\t0\tF\tsample1.srbowtie_out\n FBti0019518\t130\t1.0\tF\tsample1.srbowtie_out\n FBti0019518\t182\t1.0\tF\tsample1.srbowtie_out\n FBti0019518\t217\t-1.0\tR\tsample1.srbowtie_out\n@@ -117,6 +128,8 @@\n FBti0019518\t589\t-1.0\tR\tsample1.srbowtie_out\n FBti0019518\t617\t3.0\tF\tsample1.srbowtie_out\n FBti0019518\t817\t-1.0\tR\tsample1.srbowtie_out\n+FBti0019518\t1012\t0\tF\tsample1.srbowtie_out\n+FBti0019519\t0\t0\tF\tsample1.srbowtie_out\n FBti0019519\t1202\t2.0\tF\tsample1.srbowtie_out\n FBti0019519\t1325\t2.0\tF\tsample1.srbowtie_out\n FBti0019519\t1379\t1.0\tF\tsample1.srbowtie_out\n@@ -132,7 +145,11 @@\n FBti0019519\t1985\t2.0\tF\tsample1.srbowtie_out\n FBti0019519\t2059\t1.0\tF\tsample1.srbowtie_out\n FBti0019519\t2247\t1.0\tF\tsample1.srbowtie_out\n+FBti0019519\t3897\t0\tF\tsample1.srbowtie_out\n+FBti0019514\t0\t0\tF\tsample1.srbowtie_out\n FBti0019514\t337\t1.0\tF\tsample1.srbowtie_out\n+FBti0019514\t466\t0\tF\tsample1.srbowtie_out\n+FBti0019515\t0\t0\tF\tsample1.srbowtie_out\n FBti0019515\t531\t-1.0\tR\tsample1.srbowtie_out\n FBti0019515\t1099\t-1.0\tR\tsample1.srbowtie_out\n FBti0019515\t1113\t1.0\tF\tsample1.srbowtie_out\n@@ -154,11 +171,15 @@\n FBti0019515\t2475\t-8.0\tR\tsample1.srbowtie_out\n FBti0019515\t2484\t-1.0\tR\tsample1.srbowtie_out\n FBti0019515\t2520\t1.0\tF\tsample1.srbowtie_out\n+FBti0019515\t2592\t0\tF\tsample1.srbowtie_out\n+FBti0019516\t0\t0\tF\tsample1.srbowtie_out\n FBti0019516\t15\t1.0\tF\tsample1.srbowtie_out\n FBti0019516\t264\t1.0\tF\tsample1.srbowtie_out\n FBti0019516\t737\t5.0\tF\tsample1.srbowtie_out\n FBti0019516\t799\t1.0\tF\tsample1.srbowtie_out\n FBti0019516\t941\t-1.0\tR\tsample1.srbowtie_out\n+FBti0019516\t1132\t0\tF\tsample1.srbowtie_out\n+FBti0019517\t0\t0\tF\tsample1.srbowtie_out\n FBti0019517\t5\t1.0\tF\tsample1.srbowtie_out\n FBti0019517\t47\t-1.0\tR\tsample1.srbowtie_out\n FBti0019517\t138\t-1.0\tR\tsample1.srbowtie_out\n@@ -184,6 +205,8 @@\n FBti0019517\t515\t-1.0\tR\tsample1.srbowtie_out\n FBti0019517\t581\t1.0\tF\tsample1.srbowtie_out\n FBti0019517\t590\t-1.0\tR\tsample1.srbowtie_out\n+FBti0019517\t740\t0\tF\tsample1.srbowtie_out\n+FBti0020404\t0\t0\tF\tsample1.srbowtie_out\n FBti0020404\t40\t1.0\tF\tsample1.srbowtie_out\n FBti0020404\t56\t1.0\tF\tsample1.srbowtie_out\n FBti0020404\t210\t3.0\tF\tsample1.srbowtie_out\n@@ -195,10 +218,14 @@\n FBti0020404\t835\t-3.0\tR\tsample1.srbowtie_out\n FBti0020404\t1309\t-2.0\tR\tsample1.srbowtie_out\n FBti0020404\t1383\t-1.0\tR\tsample1.srbowtie_out\n+FBti0020404\t1470\t0\tF\tsample1.srbowtie_out\n+FBti0020405\t0\t0\tF\tsample1.srbowtie_out\n FBti0020405\t127\t-1.0\tR\tsample1.srbowtie_out\n FBti0020405\t404\t1.0\tF\tsample1.srbowtie_out\n FBti0020405\t586\t2.0\tF\tsample1.srbowtie_out\n FBti0020405\t674\t1.0\tF\tsample1.srbowtie_out\n+FBti0020405\t745\t0\tF\tsample1.srbowtie_out\n+FBti0019499\t0\t0\tF\tsample1.srbowtie_out\n FBti0019499\t18\t1.0\tF\tsample1.srbowtie_out\n FBti0019499\t271\t1.0\tF\tsample1.srbowtie_out\n FBti0019499\t369\t-1.'..b'\tsample3.srbowtie_out\n FBti0019502\t86\t1.0\tF\tsample3.srbowtie_out\n@@ -3035,8 +3265,12 @@\n FBti0019502\t870\t1.0\tF\tsample3.srbowtie_out\n FBti0019502\t882\t-2.0\tR\tsample3.srbowtie_out\n FBti0019502\t1062\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019502\t1076\t0\tF\tsample3.srbowtie_out\n+FBti0019501\t0\t0\tF\tsample3.srbowtie_out\n FBti0019501\t599\t-1.0\tR\tsample3.srbowtie_out\n FBti0019501\t726\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019501\t966\t0\tF\tsample3.srbowtie_out\n+FBti0019500\t0\t0\tF\tsample3.srbowtie_out\n FBti0019500\t24\t-1.0\tR\tsample3.srbowtie_out\n FBti0019500\t56\t1.0\tF\tsample3.srbowtie_out\n FBti0019500\t58\t1.0\tF\tsample3.srbowtie_out\n@@ -3051,6 +3285,8 @@\n FBti0019500\t935\t-1.0\tR\tsample3.srbowtie_out\n FBti0019500\t1034\t-1.0\tR\tsample3.srbowtie_out\n FBti0019500\t1097\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019500\t1111\t0\tF\tsample3.srbowtie_out\n+FBti0020402\t0\t0\tF\tsample3.srbowtie_out\n FBti0020402\t44\t-1.0\tR\tsample3.srbowtie_out\n FBti0020402\t301\t1.0\tF\tsample3.srbowtie_out\n FBti0020402\t349\t-1.0\tR\tsample3.srbowtie_out\n@@ -3093,6 +3329,8 @@\n FBti0020402\t6361\t1.0\tF\tsample3.srbowtie_out\n FBti0020402\t6367\t-1.0\tR\tsample3.srbowtie_out\n FBti0020402\t6395\t1.0\tF\tsample3.srbowtie_out\n+FBti0020402\t6438\t0\tF\tsample3.srbowtie_out\n+FBti0020410\t0\t0\tF\tsample3.srbowtie_out\n FBti0020410\t103\t-1.0\tR\tsample3.srbowtie_out\n FBti0020410\t123\t1.0\tF\tsample3.srbowtie_out\n FBti0020410\t197\t1.0\tF\tsample3.srbowtie_out\n@@ -3148,6 +3386,8 @@\n FBti0020410\t6479\t-1.0\tR\tsample3.srbowtie_out\n FBti0020410\t6629\t-1.0\tR\tsample3.srbowtie_out\n FBti0020410\t6647\t1.0\tF\tsample3.srbowtie_out\n+FBti0020410\t6752\t0\tF\tsample3.srbowtie_out\n+FBti0020403\t0\t0\tF\tsample3.srbowtie_out\n FBti0020403\t40\t1.0\tF\tsample3.srbowtie_out\n FBti0020403\t60\t1.0\tF\tsample3.srbowtie_out\n FBti0020403\t161\t2.0\tF\tsample3.srbowtie_out\n@@ -3158,6 +3398,8 @@\n FBti0020403\t869\t-1.0\tR\tsample3.srbowtie_out\n FBti0020403\t908\t-1.0\tR\tsample3.srbowtie_out\n FBti0020403\t1014\t-1.0\tR\tsample3.srbowtie_out\n+FBti0020403\t1101\t0\tF\tsample3.srbowtie_out\n+FBti0019486\t0\t0\tF\tsample3.srbowtie_out\n FBti0019486\t299\t-1.0\tR\tsample3.srbowtie_out\n FBti0019486\t468\t-1.0\tR\tsample3.srbowtie_out\n FBti0019486\t529\t-1.0\tR\tsample3.srbowtie_out\n@@ -3166,7 +3408,11 @@\n FBti0019486\t715\t1.0\tF\tsample3.srbowtie_out\n FBti0019486\t784\t-1.0\tR\tsample3.srbowtie_out\n FBti0019486\t1008\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019486\t1205\t0\tF\tsample3.srbowtie_out\n+FBti0019489\t0\t0\tF\tsample3.srbowtie_out\n FBti0019489\t1\t0\tF\tsample3.srbowtie_out\n+FBti0019489\t369\t0\tF\tsample3.srbowtie_out\n+FBti0019484\t0\t0\tF\tsample3.srbowtie_out\n FBti0019484\t101\t1.0\tF\tsample3.srbowtie_out\n FBti0019484\t138\t-1.0\tR\tsample3.srbowtie_out\n FBti0019484\t247\t-1.0\tR\tsample3.srbowtie_out\n@@ -3176,11 +3422,17 @@\n FBti0019484\t703\t5.0\tF\tsample3.srbowtie_out\n FBti0019484\t903\t-2.0\tR\tsample3.srbowtie_out\n FBti0019484\t952\t2.0\tF\tsample3.srbowtie_out\n+FBti0019484\t1084\t0\tF\tsample3.srbowtie_out\n+FBti0019485\t0\t0\tF\tsample3.srbowtie_out\n FBti0019485\t220\t1.0\tF\tsample3.srbowtie_out\n FBti0019485\t711\t-1.0\tR\tsample3.srbowtie_out\n FBti0019485\t796\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019485\t1075\t0\tF\tsample3.srbowtie_out\n+FBti0019482\t0\t0\tF\tsample3.srbowtie_out\n FBti0019482\t112\t-1.0\tR\tsample3.srbowtie_out\n FBti0019482\t340\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019482\t597\t0\tF\tsample3.srbowtie_out\n+FBti0020400\t0\t0\tF\tsample3.srbowtie_out\n FBti0020400\t15\t2.0\tF\tsample3.srbowtie_out\n FBti0020400\t40\t1.0\tF\tsample3.srbowtie_out\n FBti0020400\t84\t1.0\tF\tsample3.srbowtie_out\n@@ -3430,3 +3682,14 @@\n FBti0020400\t9275\t1.0\tF\tsample3.srbowtie_out\n FBti0020400\t9306\t-1.0\tR\tsample3.srbowtie_out\n FBti0020400\t9334\t-1.0\tR\tsample3.srbowtie_out\n+FBti0020400\t9398\t0\tF\tsample3.srbowtie_out\n+FBti0019480\t0\t0\tF\tsample3.srbowtie_out\n+FBti0019480\t23\t1.0\tF\tsample3.srbowtie_out\n+FBti0019480\t384\t1.0\tF\tsample3.srbowtie_out\n+FBti0019480\t493\t5.0\tF\tsample3.srbowtie_out\n+FBti0019480\t501\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019480\t502\t-7.0\tR\tsample3.srbowtie_out\n+FBti0019480\t503\t-1.0\tR\tsample3.srbowtie_out\n+FBti0019480\t594\t1.0\tF\tsample3.srbowtie_out\n+FBti0019480\t619\t1.0\tF\tsample3.srbowtie_out\n+FBti0019480\t669\t0\tF\tsample3.srbowtie_out\n' |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc test-data/Readmaps.pdf |
| b |
| Binary file test-data/Readmaps.pdf has changed |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc test-data/Size_distribution.pdf |
| b |
| Binary file test-data/Size_distribution.pdf has changed |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc test-data/Size_distribution_and_Readmaps.pdf |
| b |
| Binary file test-data/Size_distribution_and_Readmaps.pdf has changed |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc test-data/Size_distribution_dataframe.tab --- a/test-data/Size_distribution_dataframe.tab Sun Sep 18 12:55:27 2016 -0400 +++ b/test-data/Size_distribution_dataframe.tab Mon Sep 19 06:16:21 2016 -0400 |
| b |
| @@ -879,6 +879,28 @@ FBti0020400 28 16.0 F sample1.srbowtie_out FBti0020400 29 0.0 F sample1.srbowtie_out FBti0020400 30 0 F sample1.srbowtie_out +FBti0019480 20 0 R sample1.srbowtie_out +FBti0019480 21 0 R sample1.srbowtie_out +FBti0019480 22 -1.0 R sample1.srbowtie_out +FBti0019480 23 0 R sample1.srbowtie_out +FBti0019480 24 -2.0 R sample1.srbowtie_out +FBti0019480 25 -1.0 R sample1.srbowtie_out +FBti0019480 26 0.0 R sample1.srbowtie_out +FBti0019480 27 0 R sample1.srbowtie_out +FBti0019480 28 0 R sample1.srbowtie_out +FBti0019480 29 0 R sample1.srbowtie_out +FBti0019480 30 0 R sample1.srbowtie_out +FBti0019480 20 0 F sample1.srbowtie_out +FBti0019480 21 0 F sample1.srbowtie_out +FBti0019480 22 0.0 F sample1.srbowtie_out +FBti0019480 23 0 F sample1.srbowtie_out +FBti0019480 24 0.0 F sample1.srbowtie_out +FBti0019480 25 1.0 F sample1.srbowtie_out +FBti0019480 26 2.0 F sample1.srbowtie_out +FBti0019480 27 0 F sample1.srbowtie_out +FBti0019480 28 0 F sample1.srbowtie_out +FBti0019480 29 0 F sample1.srbowtie_out +FBti0019480 30 0 F sample1.srbowtie_out FBti0020401 20 -2.0 R sample2.srbowtie_out FBti0020401 21 0 R sample2.srbowtie_out FBti0020401 22 0.0 R sample2.srbowtie_out @@ -1759,6 +1781,28 @@ FBti0020400 28 15.0 F sample2.srbowtie_out FBti0020400 29 1.0 F sample2.srbowtie_out FBti0020400 30 0 F sample2.srbowtie_out +FBti0019480 20 0.0 R sample2.srbowtie_out +FBti0019480 21 0 R sample2.srbowtie_out +FBti0019480 22 0 R sample2.srbowtie_out +FBti0019480 23 0 R sample2.srbowtie_out +FBti0019480 24 -2.0 R sample2.srbowtie_out +FBti0019480 25 -1.0 R sample2.srbowtie_out +FBti0019480 26 0.0 R sample2.srbowtie_out +FBti0019480 27 0.0 R sample2.srbowtie_out +FBti0019480 28 0 R sample2.srbowtie_out +FBti0019480 29 0 R sample2.srbowtie_out +FBti0019480 30 0 R sample2.srbowtie_out +FBti0019480 20 1.0 F sample2.srbowtie_out +FBti0019480 21 0 F sample2.srbowtie_out +FBti0019480 22 0 F sample2.srbowtie_out +FBti0019480 23 0 F sample2.srbowtie_out +FBti0019480 24 1.0 F sample2.srbowtie_out +FBti0019480 25 0.0 F sample2.srbowtie_out +FBti0019480 26 1.0 F sample2.srbowtie_out +FBti0019480 27 1.0 F sample2.srbowtie_out +FBti0019480 28 0 F sample2.srbowtie_out +FBti0019480 29 0 F sample2.srbowtie_out +FBti0019480 30 0 F sample2.srbowtie_out FBti0020401 20 -1.0 R sample3.srbowtie_out FBti0020401 21 0.0 R sample3.srbowtie_out FBti0020401 22 -1.0 R sample3.srbowtie_out @@ -2639,3 +2683,25 @@ FBti0020400 28 12.0 F sample3.srbowtie_out FBti0020400 29 0 F sample3.srbowtie_out FBti0020400 30 0 F sample3.srbowtie_out +FBti0019480 20 0 R sample3.srbowtie_out +FBti0019480 21 -1.0 R sample3.srbowtie_out +FBti0019480 22 0.0 R sample3.srbowtie_out +FBti0019480 23 -2.0 R sample3.srbowtie_out +FBti0019480 24 -5.0 R sample3.srbowtie_out +FBti0019480 25 -1.0 R sample3.srbowtie_out +FBti0019480 26 0.0 R sample3.srbowtie_out +FBti0019480 27 0.0 R sample3.srbowtie_out +FBti0019480 28 0 R sample3.srbowtie_out +FBti0019480 29 0 R sample3.srbowtie_out +FBti0019480 30 0 R sample3.srbowtie_out +FBti0019480 20 0 F sample3.srbowtie_out +FBti0019480 21 0.0 F sample3.srbowtie_out +FBti0019480 22 1.0 F sample3.srbowtie_out +FBti0019480 23 0.0 F sample3.srbowtie_out +FBti0019480 24 3.0 F sample3.srbowtie_out +FBti0019480 25 2.0 F sample3.srbowtie_out +FBti0019480 26 2.0 F sample3.srbowtie_out +FBti0019480 27 1.0 F sample3.srbowtie_out +FBti0019480 28 0 F sample3.srbowtie_out +FBti0019480 29 0 F sample3.srbowtie_out +FBti0019480 30 0 F sample3.srbowtie_out |
| b |
| diff -r c9e267cb84c0 -r be0c6b6466cc tool_dependencies.xml --- a/tool_dependencies.xml Sun Sep 18 12:55:27 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,18 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="bowtie" version="0.12.7"> - <repository changeset_revision="9f9f38617a98" name="package_bowtie_0_12_7" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - <package name="pysam" version="0.7.7"> - <repository changeset_revision="0a5141bdf9d0" name="package_pysam_0_7_7" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - <package name="numpy" version="1.9"> - <repository changeset_revision="83d12e13dbbd" name="package_numpy_1_9" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - <package name="R" version="3.1.2"> - <repository changeset_revision="4d2fd1413b56" name="package_r_3_1_2" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - <package name="biocbasics" version="2.14"> - <repository changeset_revision="f0ef1a7b157e" name="package_biocbasics_2_14" owner="mvdbeek" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency> |