Mercurial > repos > devteam > cuffcompare

comparison cuffcompare_wrapper.xml @ 0:9d35cf35634e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded tool tarball.
author devteam
date Tue, 01 Oct 2013 12:49:41 -0400
parents
children 8b22e9adae34
comparison
equal deleted inserted replaced
-1:000000000000 0:9d35cf35634e
1 <tool id="cuffcompare" name="Cuffcompare" version="0.0.5">
2 <!-- Wrapper supports Cuffcompare versions v1.3.0 and newer -->
3 <description>compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments</description>
4 <requirements>
5 <requirement type="package" version="2.1.1">cufflinks</requirement>
6 </requirements>
7 <version_command>cuffcompare 2>&amp;1 | head -n 1</version_command>
8 <command interpreter="python">
9 cuffcompare_wrapper.py
10
11 ## Use annotation reference?
12 #if $annotation.use_ref_annotation == "Yes":
13 -r $annotation.reference_annotation
14 #if $annotation.ignore_nonoverlapping_reference:
15 -R
16 #end if
17 #end if
18
19 ## Use sequence data?
20 #if $seq_data.use_seq_data == "Yes":
21 -s
22 #if $seq_data.seq_source.index_source == "history":
23 --ref_file=$seq_data.seq_source.ref_file
24 #else:
25 --ref_file="None"
26 #end if
27 --dbkey=${first_input.metadata.dbkey}
28 --index_dir=${GALAXY_DATA_INDEX_DIR}
29 #end if
30
31 ## Outputs.
32 --combined-transcripts=${transcripts_combined}
33
34 ## Inputs.
35 ${first_input}
36 #for $input_file in $input_files:
37 ${input_file.additional_input}
38 #end for
39
40 </command>
41 <inputs>
42 <param format="gtf" name="first_input" type="data" label="GTF file produced by Cufflinks" help=""/>
43 <repeat name="input_files" title="Additional GTF Input Files">
44 <param format="gtf" name="additional_input" type="data" label="GTF file produced by Cufflinks" help=""/>
45 </repeat>
46 <conditional name="annotation">
47 <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
48 <option value="No">No</option>
49 <option value="Yes">Yes</option>
50 </param>
51 <when value="Yes">
52 <param format="gff3,gtf" name="reference_annotation" type="data" label="Reference Annotation" help="Requires an annotation file in GFF3 or GTF format."/>
53 <param name="ignore_nonoverlapping_reference" type="boolean" label="Ignore reference transcripts that are not overlapped by any transcript in input files"/>
54 </when>
55 <when value="No">
56 </when>
57 </conditional>
58 <conditional name="seq_data">
59 <param name="use_seq_data" type="select" label="Use Sequence Data" help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff.">
60 <option value="Yes">Yes</option>
61 <option value="No">No</option>
62 </param>
63 <when value="No"></when>
64 <when value="Yes">
65 <conditional name="seq_source">
66 <param name="index_source" type="select" label="Choose the source for the reference list">
67 <option value="cached">Locally cached</option>
68 <option value="history">History</option>
69 </param>
70 <when value="cached"></when>
71 <when value="history">
72 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
73 </when>
74 </conditional>
75 </when>
76 </conditional>
77 </inputs>
78
79 <outputs>
80 <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy"
81 from_work_dir="cc_output.stats" />
82 <data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${first_input.hid} tmap file"
83 from_work_dir="cc_output.input1.tmap" />
84 <data format="tabular" name="input1_refmap"
85 label="${tool.name} on ${on_string}: data ${first_input.hid} refmap file"
86 from_work_dir="cc_output.input1.refmap">
87 <filter>annotation['use_ref_annotation'] == 'Yes'</filter>
88 </data>
89 <data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${input_files[0]['additional_input'].hid} tmap file" from_work_dir="cc_output.input2.tmap">
90 <filter>len( input_files ) >= 1</filter>
91 </data>
92 <data format="tabular" name="input2_refmap"
93 label="${tool.name} on ${on_string}: data ${input_files[0]['additional_input'].hid} refmap file"
94 from_work_dir="cc_output.input2.refmap">
95 <filter>annotation['use_ref_annotation'] == 'Yes' and len( input_files ) >= 1</filter>
96 </data>
97 <data format="tabular" name="transcripts_tracking" label="${tool.name} on ${on_string}: transcript tracking" from_work_dir="cc_output.tracking">
98 <filter>len( input_files ) > 0</filter>
99 </data>
100 <data format="gtf" name="transcripts_combined" label="${tool.name} on ${on_string}: combined transcripts"/>
101 </outputs>
102
103 <tests>
104 <!--
105 cuffcompare -r cuffcompare_in3.gtf -R cuffcompare_in1.gtf cuffcompare_in2.gtf
106 -->
107 <test>
108 <param name="first_input" value="cuffcompare_in1.gtf" ftype="gtf"/>
109 <param name="additional_input" value="cuffcompare_in2.gtf" ftype="gtf"/>
110 <param name="use_ref_annotation" value="Yes"/>
111 <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
112 <param name="ignore_nonoverlapping_reference" value="Yes"/>
113 <param name="use_seq_data" value="No"/>
114 <!-- Line diffs are the result of different locations for input files; this cannot be fixed as cuffcompare outputs
115 full input path for each input. -->
116 <output name="transcripts_accuracy" file="cuffcompare_out7.txt" lines_diff="16"/>
117 <output name="input1_tmap" file="cuffcompare_out1.tmap"/>
118 <output name="input1_refmap" file="cuffcompare_out2.refmap"/>
119 <output name="input2_tmap" file="cuffcompare_out3.tmap"/>
120 <output name="input2_refmap" file="cuffcompare_out4.refmap"/>
121 <output name="transcripts_tracking" file="cuffcompare_out6.tracking"/>
122 <output name="transcripts_combined" file="cuffcompare_out5.gtf"/>
123 </test>
124 </tests>
125
126 <help>
127 **Cuffcompare Overview**
128
129 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
130
131 .. _Cufflinks: http://cufflinks.cbcb.umd.edu/
132
133 ------
134
135 **Know what you are doing**
136
137 .. class:: warningmark
138
139 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.
140
141 .. __: http://cufflinks.cbcb.umd.edu/manual.html#cuffcompare
142
143 ------
144
145 **Input format**
146
147 Cuffcompare takes Cufflinks' GTF output as input, and optionally can take a "reference" annotation (such as from Ensembl_)
148
149 .. _Ensembl: http://www.ensembl.org
150
151 ------
152
153 **Outputs**
154
155 Cuffcompare produces the following output files:
156
157 Transcripts Accuracy File:
158
159 Cuffcompare reports various statistics related to the "accuracy" of the transcripts in each sample when compared to the reference annotation data. The typical gene finding measures of "sensitivity" and "specificity" (as defined in Burset, M., Guigó, R. : Evaluation of gene structure prediction programs (1996) Genomics, 34 (3), pp. 353-367. doi: 10.1006/geno.1996.0298) are calculated at various levels (nucleotide, exon, intron, transcript, gene) for each input file and reported in this file. The Sn and Sp columns show specificity and sensitivity values at each level, while the fSn and fSp columns are "fuzzy" variants of these same accuracy calculations, allowing for a very small variation in exon boundaries to still be counted as a "match".
160
161 Transcripts Combined File:
162
163 Cuffcompare reports a GTF file containing the "union" of all transfrags in each sample. If a transfrag is present in both samples, it is thus reported once in the combined gtf.
164
165 Transcripts Tracking File:
166
167 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.
168 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.
169
170 Here's an example of a line from the tracking file::
171
172 TCONS_00000045 XLOC_000023 Tcea|uc007afj.1 j \
173 q1:exp.115|exp.115.0|100|3.061355|0.350242|0.350207 \
174 q2:60hr.292|60hr.292.0|100|4.094084|0.000000|0.000000
175
176 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::
177
178 Column number Column name Example Description
179 -----------------------------------------------------------------------
180 1 Cufflinks transfrag id TCONS_00000045 A unique internal id for the transfrag
181 2 Cufflinks locus id XLOC_000023 A unique internal id for the locus
182 3 Reference gene id Tcea The gene_name attribute of the reference GTF record for this transcript, or '-' if no reference transcript overlaps this Cufflinks transcript
183 4 Reference transcript id uc007afj.1 The transcript_id attribute of the reference GTF record for this transcript, or '-' if no reference transcript overlaps this Cufflinks transcript
184 5 Class code c The type of match between the Cufflinks transcripts in column 6 and the reference transcript. See class codes
185
186 Each of the columns after the fifth have the following format:
187 qJ:gene_id|transcript_id|FMI|FPKM|conf_lo|conf_hi
188
189 A transcript need be present in all samples to be reported in the tracking file. A sample not containing a transcript will have a "-" in its entry in the row for that transcript.
190
191 Class Codes
192
193 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::
194
195 Priority Code Description
196 ---------------------------------
197 1 = Match
198 2 c Contained
199 3 j New isoform
200 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.
201 5 i A single exon transcript falling entirely with a reference intron
202 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
203 7 p Possible polymerase run-on fragment
204 8 u Unknown, intergenic transcript
205 9 o Unknown, generic overlap with reference
206 10 . (.tracking file only, indicates multiple classifications)
207
208 -------
209
210 **Settings**
211
212 All of the options have a default value. You can change any of them. Most of the options in Cuffcompare have been implemented here.
213
214 ------
215
216 **Cuffcompare parameter list**
217
218 This is a list of implemented Cuffcompare options::
219
220 -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.
221 -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
222 </help>
223 </tool>