Mercurial > repos > gkumar09 > trinityrnaseq_protocol
changeset 30:fac55e1121ee draft default tip
Uploaded
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/EdgeR_differentialExpression.xml Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,40 @@ +<tool id="EdgeR_differentialExpression" name="EdgeR_differentialExpression" version="0.0.1"> + + <description>Identify Differentially Expressed Transcripts Using EdgeR</description> + <requirements> + <requirement type="package">trinity</requirement> + </requirements> + <command interpreter="python"> + + EdgeR_differentialExpression_wrapper.py + $counts_matrix + $dispersion + + </command> + <inputs> + + <param type="data" format="txt" name="counts_matrix" label="Matrix of RNA-Seq fragment counts for transcripts per condition" /> + <param type="data" format="fasta" name="transcripts_fasta_file" label="Transcripts fasta file corresponding to matrix" /> + <param type="float" name="dispersion" value="0.1" min="0" label="dispersion value" help="Dispersion value to be used in the negative binomial" /> + + </inputs> + <outputs> + + <data format="tar.gz" name="EdgeR_Archive" label="${tool.name} on ${on_string}: EdgeR_Results.tar.gz" from_work_dir="edgeR_results.tar.gz" /> + + </outputs> + <tests> + + <test> + <param name="counts_matrix" value="matrix_text_file" /> + <param name="transcript_fasta_file" value="fasta_file" /> + <param name="dispersion" value="0.1" /> + <output name="EdgeR_Archive" file="EdgeR_Results.tar.gz" /> + </test> + + + </tests> + <help> + help info here. + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/EdgeR_differentialExpression_wrapper.py Wed Dec 02 00:04:10 2015 -0500 @@ -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)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/__add_to_PATH_setting.txt Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,1 @@ +/usr/local/bin
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/abundance_estimation_to_matrix.xml Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,42 @@ +<tool id="abundance_estimation_to_matrix" name="abundance_estimation_to_matrix" version="0.0.1"> + + <description>Join RSEM estimates from multiple samples into a single matrix</description> + <requirements> + <requirement type="package">trinity</requirement> + </requirements> + <command interpreter="python"> + + abundance_estimation_to_matrix_wrapper.py + #for $q in $RSEM_samples + ${q.file} "${q.column_label}" + #end for + + </command> + <inputs> + + <repeat name="RSEM_samples" title="RSEM abundance estimates for samples"> + <param name="file" label="Add file" type="data" format="text"/> + <param name="column_label" label="column label" type="text" /> + </repeat> + + </inputs> + <outputs> + <data format="text" name="counts_matrix" label="${tool.name} on ${on_string}: Counts Matrix" from_work_dir="matrix.counts.matrix"/> + </outputs> + <tests> + + + <test> + <param name="target" value="trinity/Trinity.fasta" /> + <param name="aligner" value="bowtie" /> + <param name="paired_or_single" value="single" /> + <param name="library_type" value="None" /> + <param name="input" value="trinity/reads.left.fq" /> + </test> + + + </tests> + <help> + .. _Trinity: http://trinityrnaseq.sourceforge.net + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/abundance_estimation_to_matrix_wrapper.py Wed Dec 02 00:04:10 2015 -0500 @@ -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_norm TMM " + " ".join(label_list) + +run_command(cmd) + +sys.exit(0) +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/align_and_estimate_abundance.xml Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,89 @@ +<tool id="RSEM_abundance_estimation" name="RSEM_abundance_estimation" version="0.0.1"> + + <description>run RSEM to estimate transcript abundances</description> + <requirements> + <requirement type="package">trinity</requirement> + </requirements> + <command interpreter="python"> + + trinityToolWrapper.py util/align_and_estimate_abundance.pl --transcripts $transcripts --est_method RSEM --aln_method bowtie --trinity_mode --prep_reference --output_dir "subdir" + + ## Inputs. + #if str($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 $inputs.library_type + #end if + #end if + + + </command> + <inputs> + <param format="fasta" name="transcripts" type="data" label="transcripts_fasta" help="Fasta sequences for which reads are aligned." /> + + <conditional name="inputs"> + <param name="paired_or_single" type="select" label="Paired or Single-end data?"> + <option value="paired">Paired</option> + <option value="single">Single</option> + </param> + <when value="paired"> + <param format="fasta,fastq" name="left_input" type="data" label="Left/Forward strand reads" help=""/> + <param format="fasta,fastq" name="right_input" type="data" label="Right/Reverse strand reads" help=""/> + <param name="library_type" type="select" label="Strand-specific Library Type"> + <option value="None">None</option> + <option value="FR">FR</option> + <option value="RF">RF</option> + </param> + + </when> + <when value="single"> + <param format="fasta,fastq" name="input" type="data" label="Single-end reads" help=""/> + <param name="library_type" type="select" label="Strand-specific Library Type"> + <option value="None">None</option> + <option value="F">F</option> + <option value="R">R</option> + </param> + + </when> + </conditional> + + + </inputs> + <outputs> + <data format="text" name="transcript_counts" label="${tool.name} on ${on_string}: Isoform Counts" from_work_dir="subdir/RSEM.isoforms.results"/> + <data format="text" name="gene_counts" label="${tool.name} on ${on_string}: Gene counts" from_work_dir="subdir/RSEM.genes.results"/> + + + </outputs> + <tests> + + + <test> + <param name="transcript_file" value="fasta" /> + <param name="input" value="reads.left.fq" /> + <output name="transcripts_counts" file="text" /> + + </test> + + + </tests> + <help> + .. _Trinity: http://trinityrnaseq.sourceforge.net + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/analyze_diff_exp.xml Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,44 @@ +<tool id="Analyze_Diff_Exp" name="Analyze_Differential_Expression" version="0.0.1"> + + <description>Analyze differential expression</description> + <requirements> + <requirement type="package">trinity</requirement> + </requirements> + <command interpreter="python"> + + analyze_diff_exp_wrapper.py $EdgeRTarGz $TMM_Matrix_FPKM $Pvalue $Cvalue + + </command> + <inputs> + <param name="EdgeRTarGz" label="EdgeR tar gz file" type="data" format="file"/> + <param name="TMM_Matrix_FPKM" label="TMM Normalized FPKM matrix" type="data" format="file" /> + <param name="Pvalue" label="P-value" value="0.05" type="float" /> + <param name="Cvalue" label="C-value" value="0" type="float" /> + + </inputs> + <outputs> + <data format="data" name="diffExpr_matrix" label="${tool.name} on ${on_string}: Matrix" from_work_dir="diffExpr.matrix"/> + <data format="data" name="diffExpr_correlation_matrix" label="${tool.name} on ${on_string}: Sample_Correlation_Matrix" from_work_dir="diffExpr.matrix.log2.sample_cor.dat"/> + <data format="data" name="diffExpr_correlation_matrix_pdf" label="${tool.name} on ${on_string}: Sample_Correlation_Matrix_PDF" from_work_dir="diffExpr.matrix.log2.sample_cor_matrix.pdf"/> + <data format="data" name="Heatmap" label="${tool.name} on ${on_string}: Heatmap" from_work_dir="diffExpr.matrix.log2.centered.genes_vs_samples_heatmap.pdf"/> + </outputs> + <tests> + + + <test> + <param name="EdgeRtargz" value="EdgeR.tar.gz" /> + <param name="TMM_matrix" value="matrix_file" /> + <param name="P_value" value="float" /> + <param name="C_value" value="float" /> + <output name="diffExpr_matrix" file="diffExp.matrix" /> + <output name="SampleCorrelation_matrix" file="diffExp.matrix.log2.dat" /> + <output name="Correlation_matrix" file="diffExp_matrix.pdf" /> + <output name="heatmap" file="heatmap.pdf" /> + </test> + + + </tests> + <help> + .. _Trinity: http://trinityrnaseq.sourceforge.net + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/analyze_diff_exp_wrapper.py Wed Dec 02 00:04:10 2015 -0500 @@ -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)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/bash_command_executer.py Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,44 @@ +#!/usr/bin/env python + + +import sys, subprocess, os + +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" ) + + 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__()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/concatenate.xml Wed Dec 02 00:04:10 2015 -0500 @@ -0,0 +1,41 @@ +<tool id="catbash" name="Concatenate datasets"> + <description> concatenate datasets from tail to head</description> + <command interpreter="python"> + bash_command_executer.py cat + $input1 + #for $q in $queries + ${q.input2} + #end for + > $out_file1 + </command> + <inputs> + <param name="input1" type="data" label="Concatenate Dataset"/> + <repeat name="queries" title="Dataset"> + <param name="input2" type="data" label="Select" /> + </repeat> + </inputs> + <outputs> + <data name="out_file1" format="input" metadata_source="input1"/> + </outputs> + <tests> + <test> + <param name="input1" value="1.bed"/> + <param name="input2" value="2.bed"/> + <output name="out_file1" file="cat_wrapper_out1.bed"/> + </test> + <!--TODO: if possible, enhance the underlying test code to handle this test + the problem is multiple params with the same name "input2" + <test> + <param name="input1" value="1.bed"/> + <param name="input2" value="2.bed"/> + <param name="input2" value="3.bed"/> + <output name="out_file1" file="cat_wrapper_out2.bed"/> + </test> + --> + </tests> + <help> + + no help + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/trinityrnaseq_protocol/trinityToolWrapper.py Wed Dec 02 00:04:10 2015 -0500 @@ -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__()