1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/cfd6428269c8/ changeset: cfd6428269c8 user: jgoecks date: 2012-09-26 15:35:18 summary: Cufflinks wrapper: add support for v2.0, add multiread correction parameter, and remove unused parameters. affected #: 2 files diff -r 20144ac9ffa7d15a9738cee2a5c8cb2b4cf1c401 -r cfd6428269c88c4690d644929969e852af672f45 tools/ngs_rna/cufflinks_wrapper.py --- a/tools/ngs_rna/cufflinks_wrapper.py +++ b/tools/ngs_rna/cufflinks_wrapper.py @@ -1,5 +1,7 @@ #!/usr/bin/env python +# Supports Cufflinks versions 1.3 and newer. + import optparse, os, shutil, subprocess, sys, tempfile from galaxy import eggs from galaxy.datatypes.util.gff_util import parse_gff_attributes, gff_attributes_to_str @@ -36,6 +38,7 @@ where each end is 50bp, you should set -r to be 200. The default is 45bp.') parser.add_option( '-G', '--GTF', dest='GTF', help='Tells Cufflinks to use the supplied reference annotation to estimate isoform expression. It will not assemble novel transcripts, and the program will ignore alignments not structurally compatible with any reference transcript.' ) parser.add_option( '-g', '--GTF-guide', dest='GTFguide', help='use reference transcript annotation to guide assembly' ) + 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') # Normalization options. parser.add_option( "-N", "--quartile-normalization", dest="do_normalization", action="store_true" ) @@ -116,7 +119,9 @@ if options.GTF: cmd += ( " -G %s" % options.GTF ) if options.GTFguide: - cmd += ( " -g %s" % options.GTFguide ) + cmd += ( " -g %s" % options.GTFguide ) + 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: @@ -157,7 +162,7 @@ total_map_mass = -1 tmp_stderr = open( tmp_name, 'r' ) for line in tmp_stderr: - if line.lower().find( "total map mass" ) >= 0 or line.lower().find( "upper quartile" ) >= 0: + if line.lower().find( "map mass" ) >= 0 or line.lower().find( "upper quartile" ) >= 0: total_map_mass = float( line.split(":")[1].strip() ) break tmp_stderr.close() diff -r 20144ac9ffa7d15a9738cee2a5c8cb2b4cf1c401 -r cfd6428269c88c4690d644929969e852af672f45 tools/ngs_rna/cufflinks_wrapper.xml --- a/tools/ngs_rna/cufflinks_wrapper.xml +++ b/tools/ngs_rna/cufflinks_wrapper.xml @@ -1,5 +1,5 @@ <tool id="cufflinks" name="Cufflinks" version="0.0.5"> - <!-- Wrapper supports Cufflinks versions v1.0.0-v1.3.0 --> + <!-- Wrapper supports Cufflinks versions v1.3.0 and newer --><description>transcript assembly and FPKM (RPKM) estimates for RNA-Seq data</description><requirements><requirement type="package">cufflinks</requirement> @@ -20,12 +20,6 @@ #if $reference_annotation.use_ref == "Use reference annotation guide": -g $reference_annotation.reference_annotation_guide_file #end if - - ## Set paired-end parameters? - #if $singlePaired.sPaired == "Yes": - -m $singlePaired.mean_inner_distance - -s $singlePaired.inner_distance_std_dev - #end if ## Normalization? #if str($do_normalization) == "Yes": @@ -34,7 +28,7 @@ ## Bias correction? #if $bias_correction.do_bias_correction == "Yes": - -b + -b #if $bias_correction.seq_source.index_source == "history": --ref_file=$bias_correction.seq_source.ref_file #else: @@ -44,6 +38,11 @@ --index_dir=${GALAXY_DATA_INDEX_DIR} #end if + ## Multi-read correct? + #if str($multiread_correct) == "Yes": + -u + #end if + ## Include global model if available. #if $global_model: --global_model=$global_model @@ -55,12 +54,12 @@ <param name="min_isoform_fraction" type="float" value="0.10" min="0" max="1" label="Min Isoform Fraction" help=""/><param name="pre_mrna_fraction" type="float" value="0.15" min="0" max="1" label="Pre MRNA Fraction" help=""/><param name="do_normalization" type="select" label="Perform quartile normalization" help="Removes top 25% of genes from FPKM denominator to improve accuracy of differential expression calls for low abundance transcripts."> - <option value="No">No</option> + <option value="No" selected="true">No</option><option value="Yes">Yes</option></param><conditional name="reference_annotation"><param name="use_ref" type="select" label="Use Reference Annotation"> - <option value="No">No</option> + <option value="No" selected="true">No</option><option value="Use reference annotation">Use reference annotation</option><option value="Use reference annotation guide">Use reference annotation as guide</option></param> @@ -74,13 +73,13 @@ </conditional><conditional name="bias_correction"><param name="do_bias_correction" type="select" label="Perform Bias Correction" help="Bias detection and correction can significantly improve accuracy of transcript abundance estimates."> - <option value="No">No</option> - <option value="Yes">Yes</option> + <option value="No" selected="true">No</option> + <option value="Yes">Yes</option></param><when value="Yes"><conditional name="seq_source"><param name="index_source" type="select" label="Reference sequence data"> - <option value="cached">Locally cached</option> + <option value="cached" selected="true">Locally cached</option><option value="history">History</option></param><when value="cached"></when> @@ -91,17 +90,12 @@ </when><when value="No"></when></conditional> - <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Set Parameters for Paired-end Reads? (not recommended)"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No"></when> - <when value="Yes"> - <param name="mean_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs"/> - <param name="inner_distance_std_dev" type="integer" value="20" label="Standard Deviation for Inner Distance between Mate Pairs"/> - </when> - </conditional> + + <param name="multiread_correct" type="select" label="Use multi-read correct" help="Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome."> + <option value="No" selected="true">No</option> + <option value="Yes">Yes</option> + </param> + <param name="global_model" type="hidden_data" label="Global model (for use in Trackster)" optional="True"/></inputs> @@ -121,7 +115,6 @@ Simple test that uses test data included with cufflinks. --><test> - <param name="sPaired" value="No"/><param name="input" value="cufflinks_in.bam"/><param name="max_intron_len" value="300000"/><param name="min_isoform_fraction" value="0.05"/> @@ -129,6 +122,7 @@ <param name="use_ref" value="No"/><param name="do_normalization" value="No" /><param name="do_bias_correction" value="No"/> + <param name="multiread_correct" value="No"/><output name="genes_expression" format="tabular" lines_diff="2" file="cufflinks_out3.fpkm_tracking"/><output name="transcripts_expression" format="tabular" lines_diff="2" file="cufflinks_out2.fpkm_tracking"/><output name="assembled_isoforms" file="cufflinks_out1.gtf"/> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.