Mercurial > repos > jjohnson > rsem
annotate rsem_prepare_reference.xml @ 5:14267d364365 default tip
Update for dataset files_path - use model from BB pull request 532
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Thu, 04 Feb 2016 06:50:26 -0600 |
parents | 30a8343fb0e7 |
children |
rev | line source |
---|---|
0 | 1 <tool id="rsem_prepare_reference" name="RSEM prepare reference" version="1.1.17"> |
2 <description></description> | |
3 <requirements> | |
4 <requirement type="package" version="1.1.17">rsem</requirement> | |
5 <requirement type="package" version="1.0.0">bowtie</requirement> | |
6 </requirements> | |
7 <command> | |
3
59459de65740
mv RSEM datatypes to separate repository, remove samtools dependency
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
8 echo $reference_name " " | tee $reference_file && |
5
14267d364365
Update for dataset files_path - use model from BB pull request 532
Jim Johnson <jj@umn.edu>
parents:
4
diff
changeset
|
9 mkdir $reference_file.files_path && |
14267d364365
Update for dataset files_path - use model from BB pull request 532
Jim Johnson <jj@umn.edu>
parents:
4
diff
changeset
|
10 cd $reference_file.files_path && |
0 | 11 rsem-prepare-reference |
12 #if $polya.polya_use == 'add': | |
13 #if $polya.polya_length: | |
14 --polyA-length $polya.polya_length | |
15 #end if | |
16 #elif $polya.polya_use == 'subset': | |
17 --no-polyA-subset $polya.no_polya_subset | |
18 #if $polya.polya_length: | |
19 --polyA-length $polya.polya_length | |
20 #end if | |
21 #elif $polya.polya_use == 'none': | |
22 --no-polyA | |
23 #end if | |
24 $ntog | |
25 #if $transcript_to_gene_map: | |
26 --transcript-to-gene-map $transcript_to_gene_map | |
27 #end if | |
28 #if $reference.ref_type == 'transcripts': | |
29 $reference.reference_fasta_file | |
30 #else: | |
31 --gtf $reference.gtf | |
32 $reference.reference_fasta_file | |
33 #end if | |
34 $reference_name | |
3
59459de65740
mv RSEM datatypes to separate repository, remove samtools dependency
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
35 > ${reference_name}.log |
0 | 36 </command> |
37 <inputs> | |
38 <conditional name="reference"> | |
39 <param name="ref_type" type="select" label="Reference transcript source"> | |
40 <option value="transcripts">transcript fasta</option> | |
41 <option value="genomic">reference genome and gtf</option> | |
42 </param> | |
43 <when value="transcripts"> | |
44 <param name="reference_fasta_file" type="data" format="fasta" label="reference fasta file" | |
45 help="The files should contain the sequences of transcripts."/> | |
46 </when> | |
47 <when value="genomic"> | |
48 <param name="reference_fasta_file" type="data" format="fasta" label="reference fasta file" | |
49 help="The file should contain the sequence of an entire genome."/> | |
50 <param name="gtf" type="data" format="gtf" label="gtf" | |
51 help="extract transcript reference sequences using the gene annotations specified in this GTF" /> | |
52 </when> | |
53 </conditional> | |
54 <param name="transcript_to_gene_map" type="data" format="tabular" optional="true" label="Map of gene ids to transcript (isoform) ids" > | |
55 <help> | |
56 Each line of should be of the form: gene_id transcript_id ( with the two fields separated by a tab character ) | |
57 The map can be obtained from the UCSC table browser | |
58 group: Genes and Gene Prediction Tracks | |
59 table: knownIsoforms | |
60 Without a map: | |
61 If a reference genome and gtf is used, then RSEM uses the "gene_id" and "transcript_id" attributes in the GTF file. | |
62 Otherwise, RSEM assumes that each sequence in the reference sequence files is a separate gene. | |
63 </help> | |
64 </param> | |
65 <param name="reference_name" type="text" value="rsem_ref_name" label="reference name"> | |
3
59459de65740
mv RSEM datatypes to separate repository, remove samtools dependency
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
66 <help>A one word name for this RSEM reference containing only letters, digits, and underscore characters</help> |
0 | 67 <validator type="regex" message="Use only letters, digits, and underscore characters">^\w+$</validator> |
68 </param> | |
69 <conditional name="polya"> | |
70 <param name="polya_use" type="select" label="PolyA "> | |
71 <option value="add" selected="true">Add poly(A) tails to all transcripts</option> | |
72 <option value="subset">Exclude poly(A) tails from selected transcripts</option> | |
73 <option value="none">Do not add poly(A) tails to any transcripts</option> | |
74 </param> | |
75 <when value="add"> | |
76 <param name="polya_length" type="integer" value="125" optional="true" label="The length of the poly(A) tails to be added. (Default: 125)"> | |
77 <validator type="in_range" message="must be positive " min="1"/> | |
78 </param> | |
79 </when> | |
80 <when value="subset"> | |
81 <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."/> | |
82 <param name="polya_length" type="integer" value="125" optional="true" label="The length of the poly(A) tails to be added. (Default: 125)"> | |
83 <validator type="in_range" message="must be positive " min="1"/> | |
84 </param> | |
85 </when> | |
86 <when value="none"/> | |
87 </conditional> | |
88 <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."/> | |
89 </inputs> | |
90 <stdio> | |
91 <exit_code range="1:" level="fatal" description="Error Running RSEM" /> | |
92 </stdio> | |
93 <outputs> | |
94 <data format="rsem_ref" name="reference_file" label="RSEM ${reference_name} reference"/> | |
95 </outputs> | |
96 <tests> | |
97 <test> | |
98 <param name="ref_type" value="genomic"/> | |
99 <param name="reference_fasta_file" value="ref.fasta" ftype="fasta"/> | |
100 <param name="gtf" value="ref.gtf" ftype="gtf"/> | |
101 <param name="reference_name" value="ref"/> | |
102 <output name="rsem_ref"> | |
103 <assert_contents> | |
104 <has_text text="ref.grp" /> | |
105 </assert_contents> | |
106 </output> | |
107 </test> | |
108 </tests> | |
109 <help> | |
110 | |
111 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/ | |
112 | |
113 NAME | |
114 rsem-prepare-reference | |
115 | |
116 SYNOPSIS | |
117 rsem-prepare-reference [options] reference_fasta_file(s) reference_name | |
118 | |
119 DESCRIPTION | |
120 The rsem-prepare-reference program extracts/preprocesses the reference sequences and builds Bowtie indices using default parameters. | |
121 This program is used in conjunction with the 'rsem-calculate-expression' program. | |
122 | |
123 INPUTS | |
124 A fasta file of transcripts | |
125 or | |
126 A genome sequence fasta file and a GTF gene annotation file. (When using UCSC data, include the related knownIsoforms.txt) | |
127 | |
128 </help> | |
129 </tool> |