annotate rsem_prepare_reference.xml @ 2:5949673f9e3e

rename test data RSEM_ref_reference.rsem_ref
author Jim Johnson <jj@umn.edu>
date Fri, 07 Feb 2014 07:34:29 -0600
parents ca988deacfd1
children 59459de65740
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
1 <tool id="rsem_prepare_reference" name="RSEM prepare reference" version="1.1.17">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
2 <description></description>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
3 <requirements>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
4 <requirement type="package" version="1.1.17">rsem</requirement>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
5 <requirement type="package" version="1.0.0">bowtie</requirement>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
6 </requirements>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
7 <command>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
8 mkdir $reference_file.extra_files_path &amp;&amp;
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
9 cd $reference_file.extra_files_path &amp;&amp;
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
10 rsem-prepare-reference
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
11 #if $polya.polya_use == 'add':
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
12 #if $polya.polya_length:
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
13 --polyA-length $polya.polya_length
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
14 #end if
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
15 #elif $polya.polya_use == 'subset':
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
16 --no-polyA-subset $polya.no_polya_subset
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
17 #if $polya.polya_length:
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
18 --polyA-length $polya.polya_length
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
19 #end if
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
20 #elif $polya.polya_use == 'none':
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
21 --no-polyA
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
22 #end if
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
23 $ntog
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
24 #if $transcript_to_gene_map:
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
25 --transcript-to-gene-map $transcript_to_gene_map
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
26 #end if
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
27 #if $reference.ref_type == 'transcripts':
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
28 $reference.reference_fasta_file
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
29 #else:
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
30 --gtf $reference.gtf
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
31 $reference.reference_fasta_file
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
32 #end if
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
33 $reference_name
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
34 </command>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
35 <inputs>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
36 <conditional name="reference">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
37 <param name="ref_type" type="select" label="Reference transcript source">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
38 <option value="transcripts">transcript fasta</option>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
39 <option value="genomic">reference genome and gtf</option>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
40 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
41 <when value="transcripts">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
42 <param name="reference_fasta_file" type="data" format="fasta" label="reference fasta file"
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
43 help="The files should contain the sequences of transcripts."/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
44 </when>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
45 <when value="genomic">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
46 <param name="reference_fasta_file" type="data" format="fasta" label="reference fasta file"
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
47 help="The file should contain the sequence of an entire genome."/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
48 <param name="gtf" type="data" format="gtf" label="gtf"
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
49 help="extract transcript reference sequences using the gene annotations specified in this GTF" />
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
50 </when>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
51 </conditional>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
52 <param name="transcript_to_gene_map" type="data" format="tabular" optional="true" label="Map of gene ids to transcript (isoform) ids" >
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
53 <help>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
54 Each line of should be of the form: gene_id transcript_id ( with the two fields separated by a tab character )
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
55 The map can be obtained from the UCSC table browser
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
56 group: Genes and Gene Prediction Tracks
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
57 table: knownIsoforms
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
58 Without a map:
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
59 If a reference genome and gtf is used, then RSEM uses the "gene_id" and "transcript_id" attributes in the GTF file.
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
60 Otherwise, RSEM assumes that each sequence in the reference sequence files is a separate gene.
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
61 </help>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
62 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
63 <param name="reference_name" type="text" value="rsem_ref_name" label="reference name">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
64 <help>A one work name for this RSEM reference containing only letters, digits, and underscore characters</help>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
65 <validator type="regex" message="Use only letters, digits, and underscore characters">^\w+$</validator>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
66 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
67 <conditional name="polya">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
68 <param name="polya_use" type="select" label="PolyA ">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
69 <option value="add" selected="true">Add poly(A) tails to all transcripts</option>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
70 <option value="subset">Exclude poly(A) tails from selected transcripts</option>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
71 <option value="none">Do not add poly(A) tails to any transcripts</option>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
72 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
73 <when value="add">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
74 <param name="polya_length" type="integer" value="125" optional="true" label="The length of the poly(A) tails to be added. (Default: 125)">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
75 <validator type="in_range" message="must be positive " min="1"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
76 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
77 </when>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
78 <when value="subset">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
79 <param name="no_polya_subset" type="data" format="tabular" optional="true" label="List of transcript IDs (one per line) that should should not have polyA tails added."/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
80 <param name="polya_length" type="integer" value="125" optional="true" label="The length of the poly(A) tails to be added. (Default: 125)">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
81 <validator type="in_range" message="must be positive " min="1"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
82 </param>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
83 </when>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
84 <when value="none"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
85 </conditional>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
86 <param name="ntog" type="boolean" truevalue="--no-ntog" falsevalue="" checked="false" label="Disable the conversion of 'N' characters to 'G' characters in the reference sequences" help="Bowite uses the automatic N to G conversion to to align against all positions in the reference."/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
87 </inputs>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
88 <stdio>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
89 <exit_code range="1:" level="fatal" description="Error Running RSEM" />
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
90 </stdio>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
91 <outputs>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
92 <data format="rsem_ref" name="reference_file" label="RSEM ${reference_name} reference"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
93 </outputs>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
94 <tests>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
95 <test>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
96 <param name="ref_type" value="genomic"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
97 <param name="reference_fasta_file" value="ref.fasta" ftype="fasta"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
98 <param name="gtf" value="ref.gtf" ftype="gtf"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
99 <param name="reference_name" value="ref"/>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
100 <output name="rsem_ref">
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
101 <assert_contents>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
102 <has_text text="ref.grp" />
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
103 </assert_contents>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
104 </output>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
105 </test>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
106 </tests>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
107 <help>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
108
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
109 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
110
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
111 NAME
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
112 rsem-prepare-reference
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
113
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
114 SYNOPSIS
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
115 rsem-prepare-reference [options] reference_fasta_file(s) reference_name
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
116
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
117 DESCRIPTION
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
118 The rsem-prepare-reference program extracts/preprocesses the reference sequences and builds Bowtie indices using default parameters.
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
119 This program is used in conjunction with the 'rsem-calculate-expression' program.
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
120
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
121 INPUTS
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
122 A fasta file of transcripts
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
123 or
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
124 A genome sequence fasta file and a GTF gene annotation file. (When using UCSC data, include the related knownIsoforms.txt)
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
125
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
126 </help>
ca988deacfd1 Uploaded
jjohnson
parents:
diff changeset
127 </tool>