CuffDiff Output

# HG changeset patch # User Jim Johnson # Date 1349728007 18000 # Node ID 6a9bc26ab8d9277a161db9b3ed008349a9a556c7 # Parent 8ba5f0460b1e7e6746b9233d4ee9f20fd09bbe77 Added cuffdata and cuffdatadb datatypes, cuffdiff multiselect outputs diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cuffdata.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cuffdata.py Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,73 @@ +""" +CuffData +""" +import logging +import os,os.path,re +import galaxy.datatypes.data +from galaxy.datatypes.images import Html +from galaxy import util +from galaxy.datatypes.metadata import MetadataElement + +log = logging.getLogger(__name__) + +class CuffDiffData( Html ): + """ + CuffDiff output files: + run.info + read_groups.info + cds.count_tracking + cds.diff + cds.fpkm_tracking + cds.read_group_tracking + cds_exp.diff + gene_exp.diff + genes.count_tracking + genes.fpkm_tracking + genes.read_group_tracking + isoform_exp.diff + isoforms.count_tracking + isoforms.fpkm_tracking + isoforms.read_group_tracking + promoters.diff + splicing.diff + tss_group_exp.diff + tss_groups.count_tracking + tss_groups.fpkm_tracking + tss_groups.read_group_tracking + """ + file_ext = 'cuffdata' + is_binary = True + composite_type = 'auto_primary_file' + allow_datatype_change = False + + def generate_primary_file( self, dataset = None ): + """ + This is called only at upload to write the html file + cannot rename the datasets here - they come with the default unfortunately + """ + return 'AutoGenerated Primary File for Composite Dataset' + + def regenerate_primary_file(self,dataset): + """ + cannot do this until we are setting metadata + """ + flist = os.listdir(dataset.extra_files_path) + rval = ['CuffDiff Output'] + rval.append('') + rval.append('

CuffDiff Outputs:

%s' % ( sfname, sfname ) ) + rval.append( '

' ) + f = file(dataset.file_name,'w') + f.write("\n".join( rval )) + f.write('\n') + f.close() + + def set_meta( self, dataset, **kwd ): + Html.set_meta( self, dataset, **kwd ) + self.regenerate_primary_file(dataset) + + def sniff( self, filename ): + return False + diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cuffdata_cummerbund.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cuffdata_cummerbund.xml Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,36 @@ + + + Create CummeRbund database + + ## symlink all files to job working dir + for i in ${cuffdata.extra_files_path}/*; #raw do ln -s $i ${i##*/}; done; #end raw + ## run rscript + Rscript --vanilla --quiet -e 'library(cummeRbund); cuff<-readCufflinks(dbFile="cuffData.db"); samples(cuff@genes); cuff' 2> r.stderr | sed 's/\[1\]/samples:/' + + + + + + + + + + + + + + +**Cuffdiff cuffdata to CummeRBund database** + +Create a CummeRBund_ SQLite database from the cuffdata output from Cuffdiff_. + +Cuffdiff_ is part of Cufflinks_. Cuffdiff find significant changes in transcript expression, splicing, and promoter use. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621 + +CummeRbund_ is a collaborative effort between the Computational Biology group led by Manolis Kellis at MIT's Computer Science and Artificial Intelligence Laboratory, and the Rinn Lab at the Harvard University department of Stem Cells and Regenerative Medicine + +.. _CummeRBund: http://compbio.mit.edu/cummeRbund/ +.. _Cufflinks: http://cufflinks.cbcb.umd.edu/ +.. _Cuffdiff: http://cufflinks.cbcb.umd.edu/manual.html#cuffdiff + + + diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cuffdata_datasets.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cuffdata_datasets.xml Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,189 @@ + + + history datasets from Cuffdiff output + + cufflinks + + + #set sel_outputs = $output_sel.__str__.split(',') + #if 'run_info' in $sel_outputs: + cat ${cuffdata.extra_files_path}/run.info > $run_info; + #end if + #if 'read_groups_info' in $sel_outputs: + cat ${cuffdata.extra_files_path}/read_groups.info > $read_groups_info; + #end if + + #if 'splicing_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/splicing.diff > $splicing_diff; + #end if + #if 'promoters_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/promoters.diff > $promoters_diff; + #end if + + #if 'cds_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/cds.diff > $cds_diff; + #end if + #if 'cds_exp_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/cds_exp.diff > $cds_exp_diff; + #end if + #if 'cds_fpkm_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/cds.fpkm_tracking > $cds_fpkm_tracking; + #end if + #if 'cds_count_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/cds.count_tracking > $cds_count_tracking; + #end if + #if 'cds_read_group_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/cds.read_group_tracking > $cds_read_group_tracking; + #end if + + #if 'tss_groups_exp_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/tss_groups_exp.diff > $tss_groups_exp_diff; + #end if + #if 'tss_groups_fpkm_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/tss_groups.fpkm_tracking > $tss_groups_fpkm_tracking; + #end if + #if 'tss_groups_count_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/tss_groups.count_tracking > $tss_groups_count_tracking; + #end if + #if 'tss_groups_read_group_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/tss_groups.read_group_tracking > $tss_groups_read_group_tracking; + #end if + + #if 'genes_exp_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/genes_exp.diff > $genes_exp_diff; + #end if + #if 'genes_fpkm_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/genes.fpkm_tracking > $genes_fpkm_tracking; + #end if + #if 'genes_count_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/genes.count_tracking > $genes_count_tracking; + #end if + #if 'genes_read_group_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/genes.read_group_tracking > $genes_read_group_tracking; + #end if + + #if 'isoforms_exp_diff' in $sel_outputs: + cat ${cuffdata.extra_files_path}/isoforms_exp.diff > $isoforms_exp_diff; + #end if + #if 'isoforms_fpkm_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/isoforms.fpkm_tracking > $isoforms_fpkm_tracking; + #end if + #if 'isoforms_count_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/isoforms.count_tracking > $isoforms_count_tracking; + #end if + #if 'isoforms_read_group_tracking' in $sel_outputs: + cat ${cuffdata.extra_files_path}/isoforms.read_group_tracking > $isoforms_read_group_tracking; + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 'run_info' in output_sel + + + 'read_groups_info' in output_sel + + + 'splicing_diff' in output_sel + + + 'promoters_diff' in output_sel + + + 'cds_diff' in output_sel + + + 'cds_exp_diff' in output_sel + + + 'cds_fpkm_tracking' in output_sel + + + 'cds_count_tracking' in output_sel + + + 'cds_read_group_tracking' in output_sel + + + 'tss_groups_exp' in output_sel + + + 'tss_groups_fpkm_tracking' in output_sel + + + 'tss_groups_count_tracking' in output_sel + + + 'tss_groups_read_group_tracking' in output_sel + + + 'isoforms_exp' in output_sel + + + 'isoforms_fpkm_tracking' in output_sel + + + 'isoforms_count_tracking' in output_sel + + + 'isoforms_read_group_tracking' in output_sel + + + 'genes_exp' in output_sel + + + 'genes_fpkm_tracking' in output_sel + + + 'genes_count_tracking' in output_sel + + + 'genes_read_group_tracking' in output_sel + + + + + + + + + + + +**Cuffdata to history datasets** + +Copy Cuffdiff output files from a cuffdata html page to datasets in your history. + +Cuffdiff is part of Cufflinks_. Cuffdiff find significant changes in transcript expression, splicing, and promoter use. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621 + +.. _Cufflinks: http://cufflinks.cbcb.umd.edu/ + + + diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cuffdiff_wrapper.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cuffdiff_wrapper.py Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,320 @@ +#!/usr/bin/env python + +# Wrapper supports Cuffdiff versions v1.3.0-v2.0 + +import optparse, os, shutil, subprocess, sys, tempfile + +def group_callback( option, op_str, value, parser ): + groups = [] + flist = [] + for arg in parser.rargs: + arg = arg.strip() + if arg[0] is "-": + break + elif arg[0] is ",": + groups.append(flist) + flist = [] + else: + flist.append(arg) + groups.append(flist) + + setattr(parser.values, option.dest, groups) + +def label_callback( option, op_str, value, parser ): + labels = [] + for arg in parser.rargs: + arg = arg.strip() + if arg[0] is "-": + break + else: + labels.append(arg) + + setattr(parser.values, option.dest, labels) + +def stop_err( msg ): + sys.stderr.write( "%s\n" % msg ) + sys.exit() + +# Copied from sam_to_bam.py: +def check_seq_file( dbkey, cached_seqs_pointer_file ): + seq_path = '' + for line in open( cached_seqs_pointer_file ): + line = line.rstrip( '\r\n' ) + if line and not line.startswith( '#' ) and line.startswith( 'index' ): + fields = line.split( '\t' ) + if len( fields ) < 3: + continue + if fields[1] == dbkey: + seq_path = fields[2].strip() + break + return seq_path + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + + # Cuffdiff options. + parser.add_option( '-s', '--inner-dist-std-dev', dest='inner_dist_std_dev', help='The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.' ) + parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' ) + parser.add_option( '-m', '--inner-mean-dist', dest='inner_mean_dist', help='This is the expected (mean) inner distance between mate pairs. \ + For, example, for paired end runs with fragments selected at 300bp, \ + where each end is 50bp, you should set -r to be 200. The default is 45bp.') + parser.add_option( '-c', '--min-alignment-count', dest='min_alignment_count', help='The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples. If no testing is performed, changes in the locus are deemed not signficant, and the locus\' observed changes don\'t contribute to correction for multiple testing. The default is 1,000 fragment alignments (up to 2,000 paired reads).' ) + parser.add_option( '--FDR', dest='FDR', help='The allowed false discovery rate. The default is 0.05.' ) + parser.add_option( '-u', '--multi-read-correct', dest='multi_read_correct', action="store_true", help='Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome') + + # Advanced Options: + parser.add_option( '--num-importance-samples', dest='num_importance_samples', help='Sets the number of importance samples generated for each locus during abundance estimation. Default: 1000' ) + parser.add_option( '--max-mle-iterations', dest='max_mle_iterations', help='Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000' ) + + # Wrapper / Galaxy options. + parser.add_option( '-f', '--files', dest='groups', action="callback", callback=group_callback, help="Groups to be processed, groups are separated by spaces, replicates in a group comma separated. group1_rep1,group1_rep2 group2_rep1,group2_rep2, ..., groupN_rep1, groupN_rep2" ) + parser.add_option( '-A', '--inputA', dest='inputA', help='A transcript GTF file produced by cufflinks, cuffcompare, or other source.') + parser.add_option( '-1', '--input1', dest='input1', help='File of RNA-Seq read alignments in the SAM format. SAM is a standard short read alignment, that allows aligners to attach custom tags to individual alignments, and Cufflinks requires that the alignments you supply have some of these tags. Please see Input formats for more details.' ) + parser.add_option( '-2', '--input2', dest='input2', help='File of RNA-Seq read alignments in the SAM format. SAM is a standard short read alignment, that allows aligners to attach custom tags to individual alignments, and Cufflinks requires that the alignments you supply have some of these tags. Please see Input formats for more details.' ) + + # Label options + parser.add_option('-L', '--labels', dest='labels', action="callback", callback=label_callback, help="Labels for the groups the replicates are in.") + + # Normalization options. + parser.add_option( "-N", "--quartile-normalization", dest="do_normalization", action="store_true" ) + + # Bias correction options. + parser.add_option( '-b', dest='do_bias_correction', action="store_true", help='Providing Cufflinks with a multifasta file via this option instructs it to run our new bias detection and correction algorithm which can significantly improve accuracy of transcript abundance estimates.') + parser.add_option( '', '--dbkey', dest='dbkey', help='The build of the reference dataset' ) + parser.add_option( '', '--index_dir', dest='index_dir', help='GALAXY_DATA_INDEX_DIR' ) + parser.add_option( '', '--ref_file', dest='ref_file', help='The reference dataset from the history' ) + + # Outputs. + parser.add_option( "--isoforms_fpkm_tracking_output", dest="isoforms_fpkm_tracking_output" ) + parser.add_option( "--genes_fpkm_tracking_output", dest="genes_fpkm_tracking_output" ) + parser.add_option( "--cds_fpkm_tracking_output", dest="cds_fpkm_tracking_output" ) + parser.add_option( "--tss_groups_fpkm_tracking_output", dest="tss_groups_fpkm_tracking_output" ) + parser.add_option( "--isoforms_read_group_tracking_output", dest="isoforms_read_group_tracking_output", default=None) + parser.add_option( "--genes_read_group_tracking_output", dest="genes_read_group_tracking_output", default=None ) + parser.add_option( "--cds_read_group_tracking_output", dest="cds_read_group_tracking_output", default=None ) + parser.add_option( "--tss_groups_read_group_tracking_output", dest="tss_groups_read_group_tracking_output", default=None ) + parser.add_option( "--isoforms_exp_output", dest="isoforms_exp_output" ) + parser.add_option( "--genes_exp_output", dest="genes_exp_output" ) + parser.add_option( "--tss_groups_exp_output", dest="tss_groups_exp_output" ) + parser.add_option( "--cds_exp_fpkm_tracking_output", dest="cds_exp_fpkm_tracking_output" ) + parser.add_option( "--cds_diff_output", dest="cds_diff_output" ) + parser.add_option( "--isoforms_count_tracking_output", dest="isoforms_count_tracking_output" ) + parser.add_option( "--genes_count_tracking_output", dest="genes_count_tracking_output" ) + parser.add_option( "--cds_count_tracking_output", dest="cds_count_tracking_output" ) + parser.add_option( "--tss_groups_count_tracking_output", dest="tss_groups_count_tracking_output" ) + parser.add_option( "--splicing_diff_output", dest="splicing_diff_output" ) + parser.add_option( "--promoters_diff_output", dest="promoters_diff_output" ) + parser.add_option( "--run_info_output", dest="run_info_output" ) + parser.add_option( "--read_groups_info_output", dest="read_groups_info_output" ) + parser.add_option( "--cuffdatadir", dest="cuffdatadir", default=None) + parser.add_option( "--cummeRbund_db_output", dest="cummeRbund_db_output", default=None) + + (options, args) = parser.parse_args() + + # output version # of tool + try: + tmp = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp, 'wb' ) + proc = subprocess.Popen( args='cuffdiff --no-update-check 2>&1', shell=True, stdout=tmp_stdout ) + tmp_stdout.close() + returncode = proc.wait() + stdout = None + for line in open( tmp_stdout.name, 'rb' ): + if line.lower().find( 'cuffdiff v' ) >= 0: + stdout = line.strip() + break + if stdout: + sys.stdout.write( '%s\n' % stdout ) + else: + raise Exception + except: + sys.stdout.write( 'Could not determine Cuffdiff version\n' ) + + # Make temp directory for output. + tmp_output_dir = tempfile.mkdtemp() + cuffdatadir = options.cuffdatadir if options.cuffdatadir else tmp_output_dir + if not os.path.exists( cuffdatadir ): + os.makedirs( cuffdatadir ) + + + # If doing bias correction, set/link to sequence file. + if options.do_bias_correction: + if options.ref_file != 'None': + # Sequence data from history. + # Create symbolic link to ref_file so that index will be created in working directory. + seq_path = os.path.join( cuffdatadir, "ref.fa" ) + os.symlink( options.ref_file, seq_path ) + else: + # Sequence data from loc file. + cached_seqs_pointer_file = os.path.join( options.index_dir, 'sam_fa_indices.loc' ) + if not os.path.exists( cached_seqs_pointer_file ): + stop_err( 'The required file (%s) does not exist.' % cached_seqs_pointer_file ) + # If found for the dbkey, seq_path will look something like /galaxy/data/equCab2/sam_index/equCab2.fa, + # and the equCab2.fa file will contain fasta sequences. + seq_path = check_seq_file( options.dbkey, cached_seqs_pointer_file ) + if seq_path == '': + stop_err( 'No sequence data found for dbkey %s, so bias correction cannot be used.' % options.dbkey ) + + # Build command. + + # Base; always use quiet mode to avoid problems with storing log output. + cmd = "cuffdiff --no-update-check -q" + + # Add options. + if options.inner_dist_std_dev: + cmd += ( " -s %i" % int ( options.inner_dist_std_dev ) ) + if options.num_threads: + cmd += ( " -p %i" % int ( options.num_threads ) ) + if options.inner_mean_dist: + cmd += ( " -m %i" % int ( options.inner_mean_dist ) ) + if options.min_alignment_count: + cmd += ( " -c %i" % int ( options.min_alignment_count ) ) + if options.FDR: + cmd += ( " --FDR %f" % float( options.FDR ) ) + if options.multi_read_correct: + cmd += ( " -u" ) + if options.num_importance_samples: + cmd += ( " --num-importance-samples %i" % int ( options.num_importance_samples ) ) + if options.max_mle_iterations: + cmd += ( " --max-mle-iterations %i" % int ( options.max_mle_iterations ) ) + if options.do_normalization: + cmd += ( " -N" ) + if options.do_bias_correction: + cmd += ( " -b %s" % seq_path ) + + # Add inputs. + # For replicate analysis: group1_rep1,group1_rep2 groupN_rep1,groupN_rep2 + if options.groups: + cmd += " --labels " + for label in options.labels: + cmd += label + "," + cmd = cmd[:-1] + + cmd += " " + options.inputA + " " + + for group in options.groups: + for filename in group: + cmd += filename + "," + cmd = cmd[:-1] + " " + else: + cmd += " " + options.inputA + " " + options.input1 + " " + options.input2 + + # Debugging. + print cmd + + # Run command. + try: + tmp_name = tempfile.NamedTemporaryFile( dir=tmp_output_dir ).name + tmp_stderr = open( tmp_name, 'wb' ) + proc = subprocess.Popen( args=cmd, shell=True, cwd=cuffdatadir, stderr=tmp_stderr.fileno() ) + returncode = proc.wait() + tmp_stderr.close() + + # Get stderr, allowing for case where it's very large. + tmp_stderr = open( tmp_name, 'rb' ) + stderr = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stderr.close() + + # Error checking. + if returncode != 0: + raise Exception, stderr + + # check that there are results in the output file + if len( open( os.path.join( cuffdatadir, "isoforms.fpkm_tracking" ), 'rb' ).read().strip() ) == 0: + raise Exception, 'The main output file is empty, there may be an error with your input file or settings.' + except Exception, e: + stop_err( 'Error running cuffdiff. ' + str( e ) ) + + + # Copy output files from tmp directory to specified files. + try: + try: + if options.isoforms_fpkm_tracking_output and os.path.exists(os.path.join( cuffdatadir, "isoforms.fpkm_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "isoforms.fpkm_tracking" ), options.isoforms_fpkm_tracking_output ) + if options.genes_fpkm_tracking_output and os.path.exists(os.path.join( cuffdatadir, "genes.fpkm_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "genes.fpkm_tracking" ), options.genes_fpkm_tracking_output ) + if options.cds_fpkm_tracking_output and os.path.exists(os.path.join( cuffdatadir, "cds.fpkm_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "cds.fpkm_tracking" ), options.cds_fpkm_tracking_output ) + if options.tss_groups_fpkm_tracking_output and os.path.exists(os.path.join( cuffdatadir, "tss_groups.fpkm_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "tss_groups.fpkm_tracking" ), options.tss_groups_fpkm_tracking_output ) + + if options.isoforms_read_group_tracking_output and os.path.exists(os.path.join( cuffdatadir, "isoforms.read_group_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "isoforms.read_group_tracking" ), options.isoforms_read_group_tracking_output ) + if options.genes_read_group_tracking_output and os.path.exists(os.path.join( cuffdatadir, "genes.read_group_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "genes.read_group_tracking" ), options.genes_read_group_tracking_output ) + if options.cds_read_group_tracking_output and os.path.exists(os.path.join( cuffdatadir, "cds.read_group_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "cds.read_group_tracking" ), options.cds_read_group_tracking_output ) + if options.tss_groups_read_group_tracking_output and os.path.exists(os.path.join( cuffdatadir, "tss_groups.read_group_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "tss_groups.read_group_tracking" ), options.tss_groups_read_group_tracking_output ) + + if options.isoforms_exp_output and os.path.exists(os.path.join( cuffdatadir, "isoform_exp.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "isoform_exp.diff" ), options.isoforms_exp_output ) + if options.genes_exp_output and os.path.exists(os.path.join( cuffdatadir, "gene_exp.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "gene_exp.diff" ), options.genes_exp_output ) + if options.cds_exp_fpkm_tracking_output and os.path.exists(os.path.join( cuffdatadir, "cds_exp.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "cds_exp.diff" ), options.cds_exp_fpkm_tracking_output ) + if options.tss_groups_exp_output and os.path.exists(os.path.join( cuffdatadir, "tss_group_exp.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "tss_group_exp.diff" ), options.tss_groups_exp_output ) + + if options.isoforms_count_tracking_output and os.path.exists(os.path.join( cuffdatadir, "isoforms.count_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "isoforms.count_tracking" ), options.isoforms_count_tracking_output ) + if options.genes_count_tracking_output and os.path.exists(os.path.join( cuffdatadir, "genes.count_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "genes.count_tracking" ), options.genes_count_tracking_output ) + if options.cds_count_tracking_output and os.path.exists(os.path.join( cuffdatadir, "cds.count_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "cds.count_tracking" ), options.cds_count_tracking_output ) + if options.tss_groups_count_tracking_output and os.path.exists(os.path.join( cuffdatadir, "tss_groups.count_tracking" )): + shutil.copyfile( os.path.join( cuffdatadir, "tss_groups.count_tracking" ), options.tss_groups_count_tracking_output ) + + if options.cds_diff_output and os.path.exists(os.path.join( cuffdatadir, "cds.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "cds.diff" ), options.cds_diff_output ) + + if options.splicing_diff_output and os.path.exists(os.path.join( cuffdatadir, "splicing.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "splicing.diff" ), options.splicing_diff_output ) + if options.promoters_diff_output and os.path.exists(os.path.join( cuffdatadir, "promoters.diff" )): + shutil.copyfile( os.path.join( cuffdatadir, "promoters.diff" ), options.promoters_diff_output ) + + if options.run_info_output and os.path.exists(os.path.join( cuffdatadir, "run.info" )): + shutil.copyfile( os.path.join( cuffdatadir, "run.info" ), options.run_info_output ) + if options.read_groups_info_output and os.path.exists(os.path.join( cuffdatadir, "read_groups.info" )): + shutil.copyfile( os.path.join( cuffdatadir, "read_groups.info" ), options.read_groups_info_output ) + + except Exception, e: + stop_err( 'Error in cuffdiff:\n' + str( e ) ) + if options.cummeRbund_db_output: + try: + dbFile = 'cuffData.db' + rscript = tempfile.NamedTemporaryFile( dir=tmp_output_dir,suffix='.r' ).name + rscript_fh = open( rscript, 'wb' ) + rscript_fh.write('library(cummeRbund)\n') + if options.inputA and options.ref_file: + rscript_fh.write('cuff<-readCufflinks(dir = "%s", dbFile = "%s", gtfFile = "%s", genome = "%s", rebuild = T)\n' % (cuffdatadir,dbFile,options.inputA,options.ref_file)) + else: + rscript_fh.write('cuff<-readCufflinks(dir = "%s", dbFile = "%s", rebuild = T)\n' % (cuffdatadir,dbFile)) + rscript_fh.close() + cmd = ( "Rscript --vanilla %s" % rscript ) + tmp_name = tempfile.NamedTemporaryFile( dir=tmp_output_dir ).name + tmp_stderr = open( tmp_name, 'wb' ) + proc = subprocess.Popen( args=cmd, shell=True, stderr=tmp_stderr.fileno() ) + #proc = subprocess.Popen( args=cmd, shell=True) + returncode = proc.wait() + tmp_stderr.close() + if os.path.exists(os.path.join( cuffdatadir, dbFile )): + shutil.copyfile( os.path.join( cuffdatadir, dbFile ), options.cummeRbund_db_output ) + shutil.rmtree(os.path.join( cuffdatadir, dbFile )) + except Exception, e: + stop_err( 'Error generating cummeRbund cuffData.db:\n' + str( e ) ) + finally: + # Clean up temp dirs + if os.path.exists( tmp_output_dir ): + shutil.rmtree( tmp_output_dir ) + +if __name__=="__main__": __main__() diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cuffdiff_wrapper.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cuffdiff_wrapper.xml Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,383 @@ + + + find significant changes in transcript expression, splicing, and promoter use + + cufflinks + + + #set sel_outputs = $output_sel.__str__.split(',') + cuffdiff_wrapper.py + --FDR=$fdr + --num-threads="4" + --min-alignment-count=$min_alignment_count + + #if 'cuffdata' in $sel_outputs or not $output_sel: + --cuffdatadir=$cuffdata.extra_files_path + #end if + #if 'cummeRbund_db' in $sel_outputs: + --cummeRbund_db=$cummeRbund_db + #end if + + #if 'isoforms_fpkm_tracking' in $sel_outputs: + --isoforms_fpkm_tracking_output=$isoforms_fpkm_tracking + #end if + #if 'genes_fpkm_tracking' in $sel_outputs: + --genes_fpkm_tracking_output=$genes_fpkm_tracking + #end if + #if 'cds_fpkm_tracking' in $sel_outputs: + --cds_fpkm_tracking_output=$cds_fpkm_tracking + #end if + #if 'tss_groups_fpkm_tracking' in $sel_outputs: + --tss_groups_fpkm_tracking_output=$tss_groups_fpkm_tracking + #end if + #if 'isoforms_exp_diff' in $sel_outputs: + --isoforms_exp_output=$isoforms_exp_diff + #end if + #if 'genes_exp_diff' in $sel_outputs: + --genes_exp_output=$genes_exp_diff + #end if + #if 'tss_groups_exp_diff' in $sel_outputs: + --tss_groups_exp_output=$tss_groups_exp_diff + #end if + #if 'cds_exp_fpkm_tracking' in $sel_outputs: + --cds_exp_fpkm_tracking_output=$cds_exp_fpkm_tracking + #end if + #if 'splicing_diff' in $sel_outputs: + --splicing_diff_output=$splicing_diff + #end if + #if 'cds_diff' in $sel_outputs: + --cds_diff_output=$cds_diff + #end if + #if 'promoters_diff' in $sel_outputs: + --promoters_diff_output=$promoters_diff + #end if + #if 'cds_read_group_tracking' in $sel_outputs: + --cds_read_group_tracking=$cds_read_group_tracking + #end if + #if 'tss_groups_read_group_tracking' in $sel_outputs: + --tss_groups_read_group_tracking=$tss_groups_read_group_tracking + #end if + #if 'genes_read_group_tracking' in $sel_outputs: + --genes_read_group_tracking=$genes_read_group_tracking + #end if + #if 'isoforms_read_group_tracking' in $sel_outputs: + --isoforms_read_group_tracking=$isoforms_read_group_tracking + #end if + + ## Set advanced data parameters? + #if $additional.sAdditional == "Yes": + -m $additional.frag_mean_len + -s $additional.frag_len_std_dev + #end if + + ## Normalization? + #if str($do_normalization) == "Yes": + -N + #end if + + ## Multi-read correct? + #if str($multiread_correct) == "Yes": + -u + #end if + + ## Bias correction? + #if $bias_correction.do_bias_correction == "Yes": + -b + #if $bias_correction.seq_source.index_source == "history": + --ref_file=$bias_correction.seq_source.ref_file + #else: + --ref_file="None" + #end if + --dbkey=${gtf_input.metadata.dbkey} + --index_dir=${GALAXY_DATA_INDEX_DIR} + #end if + + ## Inputs. + --inputA=$gtf_input + #if $group_analysis.do_groups == "No": + --input1=$aligned_reads1 + --input2=$aligned_reads2 + #else: + ## Replicates. + --labels + #for $group in $group_analysis.groups + ${group.group} + #end for + --files + #for $group in $group_analysis.groups + #for $file in $group.files: + ${file.file} + #end for + , + #end for + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + output_sel and 'run_info' in output_sel + + + output_sel and 'read_groups_info' in output_sel + + + output_sel and 'splicing_diff' in output_sel + + + output_sel and 'promoters_diff' in output_sel + + + output_sel and 'cds_diff' in output_sel + + + output_sel and 'cds_exp_diff' in output_sel + + + output_sel and 'cds_fpkm_tracking' in output_sel + + + output_sel and 'cds_count_tracking' in output_sel + + + output_sel and 'cds_read_group_tracking' in output_sel + + + output_sel and 'tss_groups_exp' in output_sel + + + output_sel and 'tss_groups_fpkm_tracking' in output_sel + + + output_sel and 'tss_groups_count_tracking' in output_sel + + + output_sel and 'tss_groups_read_group_tracking' in output_sel + + + output_sel and 'isoforms_exp' in output_sel + + + output_sel and 'isoforms_fpkm_tracking' in output_sel + + + output_sel and 'isoforms_count_tracking' in output_sel + + + output_sel and 'isoforms_read_group_tracking' in output_sel + + + output_sel and 'genes_exp' in output_sel + + + output_sel and 'genes_fpkm_tracking' in output_sel + + + output_sel and 'genes_count_tracking' in output_sel + + + output_sel and 'genes_read_group_tracking' in output_sel + + + not output_sel or output_sel and 'cuffdata' in output_sel + + + output_sel and 'cummeRbund_db' in output_sel + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**Cuffdiff Overview** + +Cuffdiff is part of Cufflinks_. Cuffdiff find significant changes in transcript expression, splicing, and promoter use. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621 + +.. _Cufflinks: http://cufflinks.cbcb.umd.edu/ + +------ + +**Know what you are doing** + +.. class:: warningmark + +There is no such thing (yet) as an automated gearshift in expression analysis. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy. + +.. __: http://cufflinks.cbcb.umd.edu/manual.html#cuffdiff + +------ + +**Input format** + +Cuffdiff takes Cufflinks or Cuffcompare GTF files as input along with two SAM files containing the fragment alignments for two or more samples. + +------ + +**Outputs** + +Cuffdiff produces many output files: + +1. Transcript FPKM expression tracking. +2. Gene FPKM expression tracking; tracks the summed FPKM of transcripts sharing each gene_id +3. Primary transcript FPKM tracking; tracks the summed FPKM of transcripts sharing each tss_id +4. Coding sequence FPKM tracking; tracks the summed FPKM of transcripts sharing each p_id, independent of tss_id +5. Transcript differential FPKM. +6. Gene differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each gene_id +7. Primary transcript differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each tss_id +8. Coding sequence differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each p_id independent of tss_id +9. Differential splicing tests: this tab delimited file lists, for each primary transcript, the amount of overloading detected among its isoforms, i.e. how much differential splicing exists between isoforms processed from a single primary transcript. Only primary transcripts from which two or more isoforms are spliced are listed in this file. +10. Differential promoter tests: this tab delimited file lists, for each gene, the amount of overloading detected among its primary transcripts, i.e. how much differential promoter use exists between samples. Only genes producing two or more distinct primary transcripts (i.e. multi-promoter genes) are listed here. +11. Differential CDS tests: this tab delimited file lists, for each gene, the amount of overloading detected among its coding sequences, i.e. how much differential CDS output exists between samples. Only genes producing two or more distinct CDS (i.e. multi-protein genes) are listed here. + +------- + +**Settings** + +All of the options have a default value. You can change any of them. Most of the options in Cuffdiff have been implemented here. + +------ + +**Cuffdiff parameter list** + +This is a list of implemented Cuffdiff options:: + + -m INT Average fragement length; default 200 + -s INT Fragment legnth standard deviation; default 80 + -c INT The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples. If no testing is performed, changes in the locus are deemed not significant, and the locus' observed changes don't contribute to correction for multiple testing. The default is 1,000 fragment alignments (up to 2,000 paired reads). + --FDR FLOAT The allowed false discovery rate. The default is 0.05. + --num-importance-samples INT Sets the number of importance samples generated for each locus during abundance estimation. Default: 1000 + --max-mle-iterations INT Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000 + -N With this option, Cufflinks excludes the contribution of the top 25 percent most highly expressed genes from the number of mapped fragments used in the FPKM denominator. This can improve robustness of differential expression calls for less abundant genes and transcripts. + + + diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cummerbund_wrapper.py --- a/cummerbund_wrapper.py Mon Oct 01 14:08:13 2012 -0400 +++ b/cummerbund_wrapper.py Mon Oct 08 15:26:47 2012 -0500 @@ -13,7 +13,8 @@ def html_report_from_directory( html_out, dir ): html_out.write( '\n\nGalaxy - cummeRbund Output\n\n\n

\n\n\n' ) def __main__(): diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 cummerbund_wrapper.xml --- a/cummerbund_wrapper.xml Mon Oct 01 14:08:13 2012 -0400 +++ b/cummerbund_wrapper.xml Mon Oct 08 15:26:47 2012 -0500 @@ -29,7 +29,7 @@ - + @@ -38,6 +38,9 @@ + + + @@ -48,6 +51,13 @@ + + + + + + + @@ -220,7 +230,22 @@ ## Density plot ## #if $p.plot['type'] == "density": -csDensity(genes(cuff)) +csDensity(genes(cuff),replicates=$p.plot.replicates) +devname = dev.off() + + ## Dispersion plot ## + #elif $p.plot['type'] == "dispersion": +dispersionPlot(genes(cuff)) +devname = dev.off() + + ## Squared Coefficient of Variation plot ## + #elif $p.plot['type'] == "fpkmSCV": +fpkmSCVPlot(genes(cuff)) +devname = dev.off() + + ## Scatter Matrix ## + #elif $p.plot['type'] == "scatterMatrix": +csScatterMatrix(genes(cuff)) devname = dev.off() ## Boxplot ## diff -r 8ba5f0460b1e -r 6a9bc26ab8d9 datatypes_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datatypes_conf.xml Mon Oct 08 15:26:47 2012 -0500 @@ -0,0 +1,13 @@ + + + + + + + + + + + + +