# HG changeset patch # User gkumar09 # Date 1443492631 14400 # Node ID 7bfd42505a2e76acc4f88ca505f21c50199208a7 # Parent 8bce7f287a2a6eac84fbfe4da680682b6ff6f1af Uploaded diff -r 8bce7f287a2a -r 7bfd42505a2e Final/._RSEM_estimates_to_matrix.xml Binary file Final/._RSEM_estimates_to_matrix.xml has changed diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/._RSEM_estimates_to_matrix.xml Binary file trinityrnaseq_protocol/._RSEM_estimates_to_matrix.xml has changed diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/._alignreads.xml Binary file trinityrnaseq_protocol/._alignreads.xml has changed diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/EdgeR_differentialExpression.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/EdgeR_differentialExpression.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,38 @@ + + + Identify Differentially Expressed Transcripts Using EdgeR + + trinity + + + + EdgeR_differentialExpression_wrapper.py + $counts_matrix + $dispersion + + + + + + + + + + + + + + + + + + + + + + + + + help info here. + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/EdgeR_differentialExpression_wrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/EdgeR_differentialExpression_wrapper.py Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,40 @@ +import sys, os, subprocess + +TRINITY_BASE_DIR = "" +if os.environ.has_key('TRINITY_HOME'): + TRINITY_BASE_DIR = os.environ['TRINITY_HOME']; +else: + sys.stderr.write("You must set the environmental variable TRINITY_BASE_DIR to the base installation directory of Trinity before running this"); + sys.exit(1) + +usage= "usage: " + " $counts_matrix" + " $dispersion" + +if len(sys.argv)<2: + print "Require atleast two parameters" +else: + print "All good- command going ahead" +print " " + +def run_command(cmd): + print "The command used: " + cmd + pipe=subprocess.Popen(cmd, shell=True, stderr=subprocess.PIPE) + pipe.wait() + ret= pipe.returncode + if ret: + print "command died: " + str(ret) + print pipe.stderr.readlines() + sys.exit(1) + else: + return +print " " + +countmatrix= "counts_matrix" + +cmd= "cp " + sys.argv[1] + " " + countmatrix +run_command(cmd) + +cmd= TRINITY_BASE_DIR + "/Analysis/DifferentialExpression/run_DE_analysis.pl "+ " --matrix "+ countmatrix + " --method edgeR " + " --output edgeR_results "+ " --dispersion " + sys.argv[2] + " --tar_gz_outdir" + +run_command(cmd) + +sys.exit(0) diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/RSEM_estimates_to_matrix.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/RSEM_estimates_to_matrix.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,51 @@ + + + Join RSEM estimates from multiple samples into a single matrix + + trinity + + + + trinityToolWrapper.py util/RSEM_util/merge_RSEM_counts_and_labels_single_table.pl + + --labels + #for $entry in $RSEM_samples: + ${entry.column_label} + #end for + + --RSEM_counts + #for $entry in $RSEM_samples: + ${entry.file} + #end for + + > RSEM.counts.matrix + + + + + + + + + + + + + + + + + + + + + + + + + + + + .. _Trinity: http://trinityrnaseq.sourceforge.net + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/abundance_estimation_to_matrix.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/abundance_estimation_to_matrix.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,42 @@ + + + Join RSEM estimates from multiple samples into a single matrix + + trinity + + + + abundance_estimation_to_matrix_wrapper.py + #for $q in $RSEM_samples + ${q.file} "${q.column_label}" + #end for + + + + + + + + + + + + + + + + + + + + + + + + + + + + .. _Trinity: http://trinityrnaseq.sourceforge.net + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/abundance_estimation_to_matrix_wrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/abundance_estimation_to_matrix_wrapper.py Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,40 @@ +#!/usr/bin/env python + +import sys, os, string, subprocess + +#aliasing the filenames using the labels + + +def run_command(command): + print "Running command: " + command + + err_capture_file = open("my.stderr", 'w') # writing stderr to a file + cmd_run = subprocess.Popen(args=command, shell=True, stderr=err_capture_file, stdout=sys.stdout) + err = cmd_run.wait() # get exit code from command execution + err_capture_file.close() + + if err: + # report the error messages we captured, and exit non-zero + sys.stderr.write("Error, cmd: " + command + " died with ret: " + `err`) + for line in open(err_capture_file): + sys.stderr.write(line) + sys.exit(err) + return + +label_list = [] # symlink files to the labels +for i in range(1, len(sys.argv), 2): + filename=sys.argv[i] + label= sys.argv[i+1] + cmd= "ln -sf " + filename + " " + label + label_list.append(label) + run_command(cmd) + + +# run the abundance estimation script + +cmd = os.path.dirname(sys.argv[0]) + "/trinityToolWrapper.py " + " util/abundance_estimates_to_matrix.pl --est_method RSEM --cross_sample_fpkm_norm TMM " + " ".join(label_list) + +run_command(cmd) + +sys.exit(0) + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/align_and_estimate_abundance.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/align_and_estimate_abundance.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,90 @@ + + + run RSEM to estimate transcript abundances + + trinity + + + + trinityToolWrapper.py util/align_and_estimate_abundance.pl --transcripts $transcripts --est_method RSEM --aln_method bowtie --trinity_mode --prep_reference + + ## Inputs. + #if str($inputs.paired_or_single) == "paired": + --left $inputs.left_input --right $inputs.right_input + #if $inputs.left_input.ext == 'fa': + --seqType fa + #else: + --seqType fq + #end if + #if str($inputs.library_type) != "None": + --SS_lib_type $inputs.library_type + #end if + + #else: + --single $inputs.input + #if str($inputs.input.ext) == 'fa': + --seqType fa + #else: + --seqType fq + #end if + #if str($inputs.library_type) != "None": + --SS_lib_type $inputs.library_type + #end if + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .. _Trinity: http://trinityrnaseq.sourceforge.net + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/alignreads.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/alignreads.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,138 @@ + + + alignReads: short read alignment tool wrapper + + trinity + + + + trinityToolWrapper.py util/alignReads.pl --target $target -o alignment --aligner $aligner_selection.aligner + + + ## Inputs. + #if str($inputs.paired_or_single) == "paired": + --left $inputs.left_input --right $inputs.right_input + #if $inputs.left_input.ext == 'fa': + --seqType fa + #else: + --seqType fq + #end if + #if str($inputs.library_type) != "None": + --SS_lib_type $inputs.library_type + #end if + --max_dist_between_pairs $inputs.max_dist_between_pairs + #else: + --single $inputs.input + #if str($inputs.input.ext) == 'fa': + --seqType fa + #else: + --seqType fq + #end if + #if str($inputs.library_type) != "None": + --SS_lib_type $inputs.library_type + #end if + #end if + + ## Additional parameters. + ##if str($inputs.use_additional) == "yes": + ## -- $inputs.additional_params + ##end if + + + ## direct to output + > outCapture.txt + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .. _Trinity: http://trinityrnaseq.sourceforge.net + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/analyze_diff_exp.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/analyze_diff_exp.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,41 @@ + + + Analyze differential expression + + trinity + + + + analyze_diff_exp_wrapper.py $EdgeRTarGz $TMM_Matrix_FPKM $Pvalue $Cvalue + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .. _Trinity: http://trinityrnaseq.sourceforge.net + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/analyze_diff_exp_wrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/analyze_diff_exp_wrapper.py Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,63 @@ +import sys, os, subprocess + +TRINITY_BASE_DIR = "" +if os.environ.has_key('TRINITY_HOME'): + TRINITY_BASE_DIR = os.environ['TRINITY_HOME']; +else: + sys.stderr.write("You must set the environmental variable TRINITY_BASE_DIR to the base installation directory of Trinity before running this"); + sys.exit() + +usage= "usage: " + sys.argv[0] + " " + "edgeR.tar.gz " + "TMM_normalized_FPKM_matrix " + "P-value " + "C-value" +print sys.argv +print usage +print " " + +if len(sys.argv)<5: + print "Require atleast two parameters" +else: + print "All good- command going ahead" +print " " + +Normalized_Matrix=sys.argv[2] +Pvalue=sys.argv[3] +Cvalue=sys.argv[4] + +def run_command(cmd): + print "The command used: " + cmd + pipe= subprocess.Popen(cmd, shell=True, stderr=subprocess.PIPE) + pipe.wait() + ret= pipe.returncode + if ret: + print "command died: " + str(ret) + print pipe.stderr.readlines() + sys.exit(1) + else: + return +print " " + +Final_tar_gz= "edgeR.tar.gz" +run_command("cp "+ sys.argv[1] + " " + "Final_tar_gz") +run_command("tar -xvf " + "Final_tar_gz") +run_command("mv " + "edgeR_results" + "/* ." ) + +# run the analyze command +cmd= TRINITY_BASE_DIR + "/Analysis/DifferentialExpression/analyze_diff_expr.pl "+ "--matrix " + Normalized_Matrix + " -P " + Pvalue + " -C " + Cvalue +run_command(cmd) + +origMatrixName= "diffExpr.P" + Pvalue + "_" + "C" + Cvalue + ".matrix" +# diffExpr.P0.001_C2.0.matrix +run_command("mv " + origMatrixName + " diffExpr.matrix") + +SampleCorName= "diffExpr.P" + Pvalue + "_" + "C" + Cvalue + ".matrix.log2.sample_cor.dat" +# diffExpr.P0.001_C2.0.matrix.log2.sample_cor.dat +run_command("mv " + SampleCorName + " diffExpr.matrix.log2.sample_cor.dat") + +CorMatrix= "diffExpr.P" + Pvalue + "_" + "C" + Cvalue + ".matrix.log2.sample_cor_matrix.pdf" +# diffExpr.P0.001_C2.0.matrix.log2.sample_cor_matrix.pdf +run_command("mv " + CorMatrix + " diffExpr.matrix.log2.sample_cor_matrix.pdf") + +Heatmap= "diffExpr.P" + Pvalue + "_" + "C" + Cvalue + ".matrix.log2.centered.genes_vs_samples_heatmap.pdf" +#diffExpr.P0.001_C2.0.matrix.log2.centered.genes_vs_samples_heatmap.pdf +run_command("mv " + Heatmap + " diffExpr.matrix.log2.centered.genes_vs_samples_heatmap.pdf") + +sys.exit(0) diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/cat.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/cat.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,41 @@ + + tail-to-head + + bash_command_executer.py cat + $input1 + #for $q in $queries + ${q.input2} + #end for + > $out_file1 + + + + + + + + + + + + + + + + + + + + + no help + + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/diffExpress_edgeR.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/diffExpress_edgeR.xml Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,47 @@ + + + Identify Differentially Expressed Transcripts Using EdgeR + + edgeR + + + + trinityToolWrapper.py Analysis/DifferentialExpression/run_EdgeR.pl + --matrix $counts_matrix + --transcripts $transcripts_fasta_file + --output edgeR_results + --dispersion $dispersion + + > stdout.txt + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + help info here. + + diff -r 8bce7f287a2a -r 7bfd42505a2e trinityrnaseq_protocol/trinityToolWrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/trinityToolWrapper.py Mon Sep 28 22:10:31 2015 -0400 @@ -0,0 +1,82 @@ +#!/usr/bin/env python + + +# borrowed from: http://wiki.g2.bx.psu.edu/Future/Job%20Failure%20When%20stderr and modified for use with Trinity tools. + +""" +Wrapper that execute a program and its arguments but reports standard error +messages only if the program exit status was not 0 +Example: ./stderr_wrapper.py myprog arg1 -f arg2 +""" + +import sys, subprocess, os + +assert sys.version_info[:2] >= ( 2, 4 ) + +TRINITY_BASE_DIR = "" +if os.environ.has_key('TRINITY_HOME'): + TRINITY_BASE_DIR = os.environ['TRINITY_HOME']; +else: + sys.stderr.write("You must set the environmental variable TRINITY_BASE_DIR to the base installation directory of Trinity before running this"); + sys.exit() + + + +# get bindir +bindir = sys.argv[0] +bindir = bindir.split("/") +if len(bindir) > 1: + bindir.pop() + bindir = "/".join(bindir) +else: + bindir = "." + + +## add locations of tools to path setting. +TOOL_PATHS_FILE = bindir + "/__add_to_PATH_setting.txt"; +for line in open(TOOL_PATHS_FILE): + line = line.rstrip() + os.environ['PATH'] += ":" + line + + +def stop_err( msg ): + sys.stderr.write( "%s\n" % msg ) + sys.exit() + +def __main__(): + # Get command-line arguments + args = sys.argv + # Remove name of calling program, i.e. ./stderr_wrapper.py + args.pop(0) + # If there are no arguments left, we're done + if len(args) == 0: + return + + # If one needs to silence stdout + #args.append( ">" ) + #args.append( "/dev/null" ) + + args[0] = "".join([TRINITY_BASE_DIR, '/', args[0]]); + + cmdline = " ".join(args) + + + + try: + # Run program + err_capture = open("stderr.txt", 'w') + proc = subprocess.Popen( args=cmdline, shell=True, stderr=err_capture, stdout=sys.stdout ) + returncode = proc.wait() + err_capture.close() + + + if returncode != 0: + raise Exception + + except Exception: + # Running Grinder failed: write error message to stderr + err_text = open("stderr.txt").readlines() + stop_err( "ERROR:\n" + "\n".join(err_text)) + + +if __name__ == "__main__": __main__()