New upstream version 2.6.5+dfsg (e6bd23d0) · Commits · Debian Med / trinityrnaseq

Analysis/DifferentialExpression/GOplot.Rscript

+4 −3

Original line number	Diff line number	Diff line
		@@ -63,8 +63,9 @@ GOBubble(reduced_circ, labels = 2.8)
		GOCircle(circ)

		# Generate a circular visualization of selected terms
		IDs <- c('GO:0007507', 'GO:0001568', 'GO:0001944', 'GO:0048729', 'GO:0048514', 'GO:0005886', 'GO:0008092', 'GO:0008047')
		GOCircle(circ, nsub = IDs)
		# (set the ids to your liking)
		#IDs <- c('GO:0007507', 'GO:0001568', 'GO:0001944', 'GO:0048729', 'GO:0048514', 'GO:0005886', 'GO:0008092', 'GO:0008047')
		#GOCircle(circ, nsub = IDs)

		# Generate a circular visualization for 10 terms
		GOCircle(circ, nsub = 10)
		@@ -72,5 +73,5 @@ GOCircle(circ, nsub = 10)

		##### Now, the rest is up to you. ;-)

		quit(save = "no", status = 0, runLast = FALSE)
		quit(save = "yes", status = 0, runLast = FALSE)

Analysis/DifferentialExpression/plot_log2FC_hist.Rscript

0 → 100755

+11 −0

Original line number	Diff line number	Diff line
		#!/usr/bin/env Rscript

		files=list.files(pattern=".*DE_results$")
		pdf("logFC.histograms.pdf")

		for (file in files) {
		message("analyzing: ", file)
		data = read.table(file, header=T)
		hist(data$log2FoldChange, br=50, main=file)
		}

Analysis/DifferentialExpression/rename_matrix_feature_identifiers.pl

+3 −0

Original line number	Diff line number	Diff line
		@@ -50,6 +50,9 @@ main: {

		chomp;
		my @ids = split(/\t/);

		$ids[0] =~ s/\\|.*$//;

		if (my $new_id = $new_ids{$ids[0]}) {
		$ids[0] = $new_id;
		}

Analysis/DifferentialExpression/run_DE_analysis.pl

+4 −2

Original line number	Diff line number	Diff line
		@@ -306,7 +306,7 @@ sub parse_sample_info {

		my %samples;

		open (my $fh, $sample_file) or die $!;
		open (my $fh, $sample_file) or die "Error, cannot locate samples file: $sample_file";
		while (<$fh>) {
		unless (/\w/) { next; }
		if (/^\#/) { next; } # allow comments
		@@ -521,8 +521,10 @@ sub run_DESeq2_sample_pair {

		print $ofh "res\$padj[is.na(res\$padj)] <- 1\n"; # Carsten Kuenne

		print $ofh "res = as.data.frame(res[order(res\$pvalue),])\n"; # rank by pvalue

		## output results
		print $ofh "write.table(as.data.frame(res[order(res\$pvalue),]), file=\'$output_prefix.DESeq2.DE_results\', sep='\t', quote=FALSE)\n";
		print $ofh "write.table(res, file=\'$output_prefix.DESeq2.DE_results\', sep='\t', quote=FALSE)\n";
		print $ofh "write.table(rnaseqMatrix, file=\'$output_prefix.DESeq2.count_matrix\', sep='\t', quote=FALSE)\n";

Analysis/SuperTranscripts/AllelicVariants/run_variant_calling.py

+27 −5

Original line number	Diff line number	Diff line
		@@ -20,6 +20,8 @@ import Pipeliner

		logger = None

		UTILDIR = os.path.sep.join([os.path.dirname(os.path.realpath(__file__)), "util"])


		def main():

		@@ -59,6 +61,9 @@ def main():

		parser.add_argument('-m', '--maxram', dest="maxram", type=str, default="50000000000", help="Maximum amount of RAM allowed for STAR's genome generation step (only change if you get an error from STAR complaining about this value).")


		parser.add_argument("--STAR_genomeGenerate_opts", type=str, default="", help="options to pass through to STAR's genomeGenerate function")

		args = parser.parse_args()


		@@ -108,7 +113,8 @@ def main():
		else:
		pipeliner.add_commands([Pipeliner.Command("java -jar " + PICARD_HOME + "/picard.jar" +
		" CreateSequenceDictionary R=" + st_fa_path +
		" O=" + dict_file,
		" O=" + dict_file +
		" VALIDATION_STRINGENCY=LENIENT ",
		"picard_dict_st.ok")])
		pipeliner.run()

		@@ -120,9 +126,12 @@ def main():
		" --runMode genomeGenerate" +
		" --genomeDir star_genome_idx " +
		" --genomeFastaFiles {} ".format(st_fa_path) +
		" --genomeSAindexNbases 8 " + # as per A. Dobin
		" --sjdbGTFfile {} ".format(st_gtf_path) +
		" --sjdbOverhang {} ".format(args.sjdbOverhang) +
		" --limitGenomeGenerateRAM {}".format(args.maxram) )
		" --limitGenomeGenerateRAM {}".format(args.maxram) +
		" {} ".format(args.STAR_genomeGenerate_opts)
		)

		pipeliner.add_commands([
		Pipeliner.Command("mkdir star_genome_idx", "mkdir_star_genome_idx.ok"),
		@@ -160,6 +169,7 @@ def main():
		" AddOrReplaceReadGroups " +
		"I=Aligned.sortedByCoord.out.bam " +
		"O=rg_added_sorted.bam " +
		" VALIDATION_STRINGENCY=SILENT " +
		"SO=coordinate RGID=id RGLB=library RGPL=platform RGPU=machine RGSM=sample",
		"add_read_groups.ok"),

		@@ -169,10 +179,22 @@ def main():
		"CREATE_INDEX=true VALIDATION_STRINGENCY=SILENT M=output.metrics",
		"mark_dups.ok"),

		Pipeliner.Command("java -jar " + PICARD_HOME + "/picard.jar ValidateSamFile " +
		"I=dedupped.bam " +
		"IGNORE_WARNINGS=true " +
		"MAX_OUTPUT=100000 " +
		"IGNORE=MATE_NOT_FOUND " +
		"O=dedupped.bam.validation",
		"bam_validate.ok",
		ignore_error=True),

		Pipeliner.Command(UTILDIR + "/clean_bam.pl dedupped.bam dedupped.bam.validation dedupped.valid.bam",
		"make_valid_dedupped_bam.ok"),

		Pipeliner.Command("java -jar " + GATK_HOME + "/GenomeAnalysisTK.jar " +
		"-T SplitNCigarReads -R " + st_fa_path +
		" -I dedupped.bam -o splitNCigar.bam " +
		" -rf ReassignOneMappingQuality -RMQF 255 -RMQT 60 -U ALLOW_N_CIGAR_READS",
		" -I dedupped.valid.bam -o splitNCigar.bam " +
		" -rf ReassignOneMappingQuality -RMQF 255 -RMQT 60 -U ALLOW_N_CIGAR_READS --validation_strictness LENIENT",
		"splitNCigarReads.ok")
		])
		pipeliner.run()