cuffcompare: cuffcompare_wrapper.xml comparison

comparison cuffcompare_wrapper.xml @ 6:8e534225baa9 draft

Uploaded

author	devteam
date	Fri, 19 Dec 2014 11:55:55 -0500
parents	8b22e9adae34
children	b77178f66fc3

comparison

equal deleted inserted replaced

-:67695d7ff787
+:8e534225baa9
-<tool id="cuffcompare" name="Cuffcompare" version="0.0.6">
+<tool id="cuffcompare" name="Cuffcompare" version="2.2.1.0">
-<!-- Wrapper supports Cuffcompare versions v1.3.0 and newer -->
 <description>compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments</description>
-<requirements>
+<expand macro="requirements" />
-<requirement type="package" version="2.1.1">cufflinks</requirement>
+<expand macro="stdio" />
-</requirements>
+<macros>
+<import>cuff_macros.xml</import>
+</macros>
 <version_command>cuffcompare 2>&amp;1 | head -n 1</version_command>
 <command interpreter="python">
 cuffcompare_wrapper.py
 ## Use annotation reference?
 #if $annotation.use_ref_annotation == "Yes":
 -r $annotation.reference_annotation
 #if $annotation.ignore_nonoverlapping_reference:
 -R
 #end if
+#if $annotation.ignore_nonoverlapping_transfrags:
+-Q
+#end if
 #end if
 ## Use sequence data?
 #if $seq_data.use_seq_data == "Yes":
 -s
 #else:
 --index=${seq_data.seq_source.index.fields.path}
 #end if
 #end if
+$discard_single_exon
+-e $max_dist_exon
+-d $max_dist_group
+#if $discard_intron_redundant_transfrags:
+-F
+#end if
 ## Outputs.
 --combined-transcripts=${transcripts_combined}
-## Inputs.
+@CUFFLINKS_GTF_INPUTS@
-${first_input}
-#for $input_file in $input_files:
-${input_file.additional_input}
-#end for
 </command>
 <inputs>
-<param format="gtf" name="first_input" type="data" label="GTF file produced by Cufflinks" help=""/>
+<expand macro="cufflinks_gtf_inputs" />
-<repeat name="input_files" title="Additional GTF Input Files">
-<param format="gtf" name="additional_input" type="data" label="GTF file produced by Cufflinks" help=""/>
-</repeat>
 <conditional name="annotation">
 <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
 <option value="No">No</option>
 <option value="Yes">Yes</option>
 </param>
 <when value="Yes">
 <param format="gff3,gtf" name="reference_annotation" type="data" label="Reference Annotation" help="Requires an annotation file in GFF3 or GTF format."/>
-<param name="ignore_nonoverlapping_reference" type="boolean" label="Ignore reference transcripts that are not overlapped by any transcript in input files"/>
+<param name="ignore_nonoverlapping_reference" type="boolean" label="Ignore reference transcripts that are not overlapped by any input transfrags" help="consider only the reference transcripts that overlap any of the input transfrags (Sn correction)" />
+<param name="ignore_nonoverlapping_transfrags" type="boolean" label="Ignore input transcripts that are not overlapped by any reference transcripts" help="consider only the input transcripts that overlap any of the reference transcripts (Sp correction). Warning: this will discard all 'novel' loci!" />
 </when>
 <when value="No">
 </when>
 </conditional>
 <conditional name="seq_data">
-<param name="use_seq_data" type="select" label="Use Sequence Data" help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff.">
+<param name="use_seq_data" type="select" label="Use Sequence Data"
+help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff.">
 <option value="Yes">Yes</option>
 <option value="No">No</option>
 </param>
 <when value="No"></when>
 <when value="Yes">
 <option value="history">History</option>
 </param>
 <when value="cached">
 <param name="index" type="select" label="Using reference genome">
 <options from_data_table="fasta_indexes">
-<filter type="data_meta" ref="first_input" key="dbkey" column="1" />
+<filter type="data_meta" ref="inputs" key="dbkey" column="1" />
 <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
 </options>
 </param>
 </when>
 <when value="history">
 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
 </when>
 </conditional>
 </when>
 </conditional>
+<param type="select" name="discard_single_exon" label="discard (ignore) single-exon transcripts">
+<option value="" selected="True">No</option>
+<option value="-M">Discard single-exon transfrags and reference transcripts</option>
+<option value="-N">Discard single-exon reference transcripts</option>
+</param>
+<param type="integer" name="max_dist_exon" value="100" label="Max. Distance for assessing exon accuracy"
+help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" />
+<param type="integer" name="max_dist_group" value="100" label="Max.Distance for transcript grouping"
+help="max. distance (range) for grouping transcript start sites. Default: 100" />
+<param type="boolean" name="discard_intron_redundant_transfrags" label="discard intron-redundant transfrags sharing 5'"
+help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" />
 </inputs>
 <outputs>
 <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy"
 from_work_dir="cc_output.stats" />
-<data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${first_input.hid} tmap file"
+<data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${inputs[0].hid} tmap file"
 from_work_dir="cc_output.input1.tmap" />
 <data format="tabular" name="input1_refmap"
-label="${tool.name} on ${on_string}: data ${first_input.hid} refmap file"
+label="${tool.name} on ${on_string}: data ${inputs[0].hid} refmap file"
 from_work_dir="cc_output.input1.refmap">
 <filter>annotation['use_ref_annotation'] == 'Yes'</filter>
 </data>
-<data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${input_files[0]['additional_input'].hid} tmap file" from_work_dir="cc_output.input2.tmap">
+<data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${inputs[1].hid} tmap file" from_work_dir="cc_output.input2.tmap">
-<filter>len( input_files ) >= 1</filter>
+<filter>@HAS_MULTIPLE_INPUTS@</filter>
 </data>
 <data format="tabular" name="input2_refmap"
-label="${tool.name} on ${on_string}: data ${input_files[0]['additional_input'].hid} refmap file"
+label="${tool.name} on ${on_string}: data ${inputs[1].hid} refmap file"
 from_work_dir="cc_output.input2.refmap">
-<filter>annotation['use_ref_annotation'] == 'Yes' and len( input_files ) >= 1</filter>
+<filter>annotation['use_ref_annotation'] == 'Yes' and @HAS_MULTIPLE_INPUTS@</filter>
 </data>
 <data format="tabular" name="transcripts_tracking" label="${tool.name} on ${on_string}: transcript tracking" from_work_dir="cc_output.tracking">
-<filter>len( input_files ) > 0</filter>
+<filter>@HAS_MULTIPLE_INPUTS@</filter>
 </data>
 <data format="gtf" name="transcripts_combined" label="${tool.name} on ${on_string}: combined transcripts"/>
 </outputs>
 <tests>
 <!--
 cuffcompare -r cuffcompare_in3.gtf -R cuffcompare_in1.gtf cuffcompare_in2.gtf
 -->
 <test>
-<param name="first_input" value="cuffcompare_in1.gtf" ftype="gtf"/>
+<param name="inputs" value="cuffcompare_in1.gtf,cuffcompare_in2.gtf" ftype="gtf"/>
-<param name="additional_input" value="cuffcompare_in2.gtf" ftype="gtf"/>
 <param name="use_ref_annotation" value="Yes"/>
 <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
 <param name="ignore_nonoverlapping_reference" value="Yes"/>
+<param name="ignore_nonoverlapping_transfrags" value="No"/>
 <param name="use_seq_data" value="No"/>
+<param name="discard_single_exon" value="" />
+<param name="max_dist_exon" value="100" />
+<param name="max_dist_group" value="100" />
+<param name="discard_intron_redundant_transfrags" value="No" />
 <!-- Line diffs are the result of different locations for input files; this cannot be fixed as cuffcompare outputs
 full input path for each input. -->
-<output name="transcripts_accuracy" file="cuffcompare_out7.txt" lines_diff="16"/>
+<output name="transcripts_accuracy" file="cuffcompare_out7.txt" lines_diff="2"/>
 <output name="input1_tmap" file="cuffcompare_out1.tmap"/>
 <output name="input1_refmap" file="cuffcompare_out2.refmap"/>
 <output name="input2_tmap" file="cuffcompare_out3.tmap"/>
 <output name="input2_refmap" file="cuffcompare_out4.refmap"/>
 <output name="transcripts_tracking" file="cuffcompare_out6.tracking"/>
 <help>
 **Cuffcompare Overview**
 Cuffcompare is part of Cufflinks_. Cuffcompare helps you: (a) compare your assembled transcripts to a reference annotation and (b) track Cufflinks transcripts across multiple experiments (e.g. across a time course). 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/
+.. _Cufflinks: http://cole-trapnell-lab.github.io/cufflinks/
 ------
 **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#cuffcompare
+.. __: http://cole-trapnell-lab.github.io/cufflinks/cuffcompare/
 ------
 **Input format**
 This file matches transcripts up between samples. Each row contains a transcript structure that is present in one or more input GTF files. Because the transcripts will generally have different IDs (unless you assembled your RNA-Seq reads against a reference transcriptome), cuffcompare examines the structure of each the transcripts, matching transcripts that agree on the coordinates and order of all of their introns, as well as strand. Matching transcripts are allowed to differ on the length of the first and last exons, since these lengths will naturally vary from sample to sample due to the random nature of sequencing.
 If you ran cuffcompare with the -r option, the first and second columns contain the closest matching reference transcript to the one described by each row.
 Here's an example of a line from the tracking file::
-TCONS_00000045 XLOC_000023 Tcea|uc007afj.1	j	\
+TCONS_00000045 XLOC_000023 Tcea|uc007afj.1        j        \
 q1:exp.115|exp.115.0|100|3.061355|0.350242|0.350207 \
 q2:60hr.292|60hr.292.0|100|4.094084|0.000000|0.000000
 In this example, a transcript present in the two input files, called exp.115.0 in the first and 60hr.292.0 in the second, doesn't match any reference transcript exactly, but shares exons with uc007afj.1, an isoform of the gene Tcea, as indicated by the class code j. The first three columns are as follows::
 Class Codes
 If you ran cuffcompare with the -r option, tracking rows will contain the following values. If you did not use -r, the rows will all contain "-" in their class code column::
-Priority	 Code	   Description
+Priority         Code           Description
 ---------------------------------
-1	         =	       Match
+1                 =               Match
-2	         c	       Contained
+2                 c               Contained
-3	         j	       New isoform
+3                 j               New isoform
-4	         e	       A single exon transcript overlapping a reference exon and at least 10 bp of a reference intron, indicating a possible pre-mRNA fragment.
+4                 e               A single exon transcript overlapping a reference exon and at least 10 bp of a reference intron, indicating a possible pre-mRNA fragment.
-5	         i	       A single exon transcript falling entirely with a reference intron
+5                 i               A single exon transcript falling entirely with a reference intron
-6	         r	       Repeat. Currently determined by looking at the reference sequence and applied to transcripts where at least 50% of the bases are lower case
+6                 r               Repeat. Currently determined by looking at the reference sequence and applied to transcripts where at least 50% of the bases are lower case
-7	         p	       Possible polymerase run-on fragment
+7                 p               Possible polymerase run-on fragment
-8	         u	       Unknown, intergenic transcript
+8                 u               Unknown, intergenic transcript
-9	         o	       Unknown, generic overlap with reference
+9                 o               Unknown, generic overlap with reference
-10             .	       (.tracking file only, indicates multiple classifications)
+10             .               (.tracking file only, indicates multiple classifications)
 -------
 **Settings**
 This is a list of implemented Cuffcompare options::
 -r    An optional "reference" annotation GTF. Each sample is matched against this file, and sample isoforms are tagged as overlapping, matching, or novel where appropriate. See the refmap and tmap output file descriptions below.
 -R    If -r was specified, this option causes cuffcompare to ignore reference transcripts that are not overlapped by any transcript in one of cuff1.gtf,...,cuffN.gtf. Useful for ignoring annotated transcripts that are not present in your RNA-Seq samples and thus adjusting the "sensitivity" calculation in the accuracy report written in the transcripts_accuracy file
 </help>
+<citations>
+<citation type="doi">10.1038/nbt.1621</citation>
+</citations>
 </tool>

Mercurial > repos > devteam > cuffcompare

comparison cuffcompare_wrapper.xml @ 6:8e534225baa9 draft