annotate trinityrnaseq.xml @ 4:f98f80675d60 draft

Corrected perl module name and improved output handling for better performance from Phil Blood.
author nate
date Fri, 10 Mar 2017 10:42:24 -0500
parents 3d072b99688e
children 1de64ac61b4e
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
1 <tool id="trinity_psc" name="Trinity" version="0.0.1">
d0c258caafaf Uploaded
nate
parents:
diff changeset
2
d0c258caafaf Uploaded
nate
parents:
diff changeset
3 <!-- Written by Jeremy Goecks, now maintained here by bhaas and additional
d0c258caafaf Uploaded
nate
parents:
diff changeset
4 modifications by Nate Coraor -->
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
5 <description>(Beta) De novo assembly of RNA-Seq data Using Trinity on PSC's Bridges</description>
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
6 <requirements>
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
7 <!-- These are versions available as modules on Bridges -->
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
8 <requirement type="package" version="1.1.2">bowtie</requirement>
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
9 <requirement type="package" version="1.3">samtools</requirement>
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
10 <requirement type="package" version="jre7">java</requirement>
4
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
11 <requirement type="package" version="5.18.4-threads">perl</requirement>
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
12 <requirement type="package" version="2.2.0">trinity</requirement>
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
13 </requirements>
d0c258caafaf Uploaded
nate
parents:
diff changeset
14 <command>
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
15 MEM=`expr "\${GALAXY_SLOTS:-16}" \* 48 - 16` ;
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
16
2
53b890343b67 Uploaded
nate
parents: 1
diff changeset
17 workdir=`pwd`;
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
18 echo "workdir is \$workdir";
2
53b890343b67 Uploaded
nate
parents: 1
diff changeset
19 cd \$LOCAL;
53b890343b67 Uploaded
nate
parents: 1
diff changeset
20 echo "Running Trinity from `pwd`";
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
21
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
22 Trinity --max_memory "\${MEM}G"
d0c258caafaf Uploaded
nate
parents:
diff changeset
23 --CPU "\${GALAXY_SLOTS:-16}"
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
24 --bflyHeapSpaceMax "32G"
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
25 --bflyHeapSpaceInit "2G"
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
26 --bflyGCThreads "6"
2
53b890343b67 Uploaded
nate
parents: 1
diff changeset
27
53b890343b67 Uploaded
nate
parents: 1
diff changeset
28 #if $additional_params.use_additional == "yes" and $additional_params.normalize_reads == "yes":
53b890343b67 Uploaded
nate
parents: 1
diff changeset
29 --normalize_reads
53b890343b67 Uploaded
nate
parents: 1
diff changeset
30 #end if
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
31
d0c258caafaf Uploaded
nate
parents:
diff changeset
32 ## Inputs.
d0c258caafaf Uploaded
nate
parents:
diff changeset
33 #if str($inputs.paired_or_single) == "paired":
d0c258caafaf Uploaded
nate
parents:
diff changeset
34 --left $inputs.left_input --right $inputs.right_input
d0c258caafaf Uploaded
nate
parents:
diff changeset
35 #if $inputs.left_input.ext == 'fa':
d0c258caafaf Uploaded
nate
parents:
diff changeset
36 --seqType fa
d0c258caafaf Uploaded
nate
parents:
diff changeset
37 #else:
d0c258caafaf Uploaded
nate
parents:
diff changeset
38 --seqType fq
d0c258caafaf Uploaded
nate
parents:
diff changeset
39 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
40 #if str($inputs.library_type) != "undefined":
d0c258caafaf Uploaded
nate
parents:
diff changeset
41 --SS_lib_type $inputs.library_type
d0c258caafaf Uploaded
nate
parents:
diff changeset
42 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
43 --group_pairs_distance $inputs.group_pairs_distance
d0c258caafaf Uploaded
nate
parents:
diff changeset
44 #else:
d0c258caafaf Uploaded
nate
parents:
diff changeset
45 --single $inputs.input
d0c258caafaf Uploaded
nate
parents:
diff changeset
46 #if str($inputs.input.ext) == 'fa':
d0c258caafaf Uploaded
nate
parents:
diff changeset
47 --seqType fa
d0c258caafaf Uploaded
nate
parents:
diff changeset
48 #else:
d0c258caafaf Uploaded
nate
parents:
diff changeset
49 --seqType fq
d0c258caafaf Uploaded
nate
parents:
diff changeset
50 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
51 #if str($inputs.library_type) != "undefined":
d0c258caafaf Uploaded
nate
parents:
diff changeset
52 --SS_lib_type $inputs.library_type
d0c258caafaf Uploaded
nate
parents:
diff changeset
53 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
54 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
55
d0c258caafaf Uploaded
nate
parents:
diff changeset
56 ## Additional parameters.
d0c258caafaf Uploaded
nate
parents:
diff changeset
57 #if str($additional_params.use_additional) == "yes":
d0c258caafaf Uploaded
nate
parents:
diff changeset
58 --min_kmer_cov $additional_params.min_kmer_cov --max_reads_per_graph $additional_params.max_reads_per_graph
d0c258caafaf Uploaded
nate
parents:
diff changeset
59 #if $additional_params.bfly_opts != 'None':
d0c258caafaf Uploaded
nate
parents:
diff changeset
60 --bfly_opts " $additional_params.bfly_opts "
d0c258caafaf Uploaded
nate
parents:
diff changeset
61 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
62 #end if
d0c258caafaf Uploaded
nate
parents:
diff changeset
63
d0c258caafaf Uploaded
nate
parents:
diff changeset
64 ## direct to output
d0c258caafaf Uploaded
nate
parents:
diff changeset
65 > $trinity_log 2>&amp;1
d0c258caafaf Uploaded
nate
parents:
diff changeset
66
4
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
67 ## if Trinity fails, output the end of the log to stderr for Galaxy, and touch the output file for Pulsar
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
68 || (ec=\$? ; cp -p $trinity_log \$workdir; cd \$workdir; cat $trinity_log >&amp;2 ; mkdir -p trinity_out_dir ; touch trinity_out_dir/Trinity.fasta ; exit \$ec);
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
69
4
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
70 mkdir -p \$workdir/trinity_out_dir;
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
71 cp -p trinity_out_dir/Trinity* \$workdir/trinity_out_dir;
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
72 cd \$workdir;
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
73 </command>
d0c258caafaf Uploaded
nate
parents:
diff changeset
74 <stdio>
d0c258caafaf Uploaded
nate
parents:
diff changeset
75 <exit_code range="1:" level="fatal" description="Program failed" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
76 <exit_code range=":-1" level="fatal" description="DRM killed job" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
77 </stdio>
d0c258caafaf Uploaded
nate
parents:
diff changeset
78 <inputs>
d0c258caafaf Uploaded
nate
parents:
diff changeset
79 <conditional name="inputs">
d0c258caafaf Uploaded
nate
parents:
diff changeset
80 <param name="paired_or_single" type="select" label="Paired or Single-end data?">
d0c258caafaf Uploaded
nate
parents:
diff changeset
81 <option value="paired">Paired</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
82 <option value="single">Single</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
83 </param>
d0c258caafaf Uploaded
nate
parents:
diff changeset
84 <when value="paired">
d0c258caafaf Uploaded
nate
parents:
diff changeset
85 <param format="fasta,fastq" name="left_input" type="data" label="Left/Forward strand reads" help=""/>
d0c258caafaf Uploaded
nate
parents:
diff changeset
86 <param format="fasta,fastq" name="right_input" type="data" label="Right/Reverse strand reads" help=""/>
d0c258caafaf Uploaded
nate
parents:
diff changeset
87 <param name="library_type" type="select" label="Strand-specific Library Type">
d0c258caafaf Uploaded
nate
parents:
diff changeset
88 <option value="undefined">Not set</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
89 <option value="FR">FR</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
90 <option value="RF">RF</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
91 </param>
d0c258caafaf Uploaded
nate
parents:
diff changeset
92 <param name="group_pairs_distance" type="integer" value="500" min="1" label="Group pairs distance" help="Maximum length expected between fragment pairs"/>
d0c258caafaf Uploaded
nate
parents:
diff changeset
93 <param name="path_reinforcement_distance" type="integer" value="75" min="1" label="Path reinforcement distance" help="Minimum read overlap required for path extension in the graph" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
94 </when>
d0c258caafaf Uploaded
nate
parents:
diff changeset
95 <when value="single">
d0c258caafaf Uploaded
nate
parents:
diff changeset
96 <param format="fasta,fastq" name="input" type="data" label="Single-end reads" help=""/>
d0c258caafaf Uploaded
nate
parents:
diff changeset
97 <param name="library_type" type="select" label="Strand-specific Library Type">
d0c258caafaf Uploaded
nate
parents:
diff changeset
98 <option value="undefined">Not set</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
99 <option value="F">F</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
100 <option value="R">R</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
101 </param>
d0c258caafaf Uploaded
nate
parents:
diff changeset
102 <param name="path_reinforcement_distance" type="integer" value="40" min="1" label="Path reinforcement distance" help="Minimum read overlap required for path extension in the graph" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
103 </when>
d0c258caafaf Uploaded
nate
parents:
diff changeset
104 </conditional>
d0c258caafaf Uploaded
nate
parents:
diff changeset
105
d0c258caafaf Uploaded
nate
parents:
diff changeset
106 <conditional name="additional_params">
d0c258caafaf Uploaded
nate
parents:
diff changeset
107 <param name="use_additional" type="select" label="Use Additional Params?">
d0c258caafaf Uploaded
nate
parents:
diff changeset
108 <option value="no">No</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
109 <option value="yes">Yes</option>
d0c258caafaf Uploaded
nate
parents:
diff changeset
110 </param>
d0c258caafaf Uploaded
nate
parents:
diff changeset
111 <when value="no">
d0c258caafaf Uploaded
nate
parents:
diff changeset
112 </when>
d0c258caafaf Uploaded
nate
parents:
diff changeset
113 <when value="yes">
d0c258caafaf Uploaded
nate
parents:
diff changeset
114 <param name="min_kmer_cov" type="integer" value="1" min="1" label="inchworm_min_kmer_cov" help="Minimum kmer coverage required by Inchworm for initial contig construction" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
115 <param name="max_reads_per_graph" type="integer" value="20000000" min="10000" label="chrysalis_max_reads_per_graph" help="Maximum number of reads to be anchored within each transcript graph by Chrysalis" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
116 <param name="bfly_opts" type="text" value="None" label="bfly_opts" help="Options to pass on to Butterfly" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
117 <param name="min_contig_length" type="integer" value="200" min="1" label="Minimum Contig Length" help=""/>
2
53b890343b67 Uploaded
nate
parents: 1
diff changeset
118 <param name="normalize_reads" type="boolean" truevalue="yes" falsevalue="no" help="(--normalize_reads) Normalize reads, can decrease runtime and memory requirements for datasets exceeding 300M pairs"/>
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
119 </when>
d0c258caafaf Uploaded
nate
parents:
diff changeset
120 </conditional>
d0c258caafaf Uploaded
nate
parents:
diff changeset
121 </inputs>
d0c258caafaf Uploaded
nate
parents:
diff changeset
122 <outputs>
d0c258caafaf Uploaded
nate
parents:
diff changeset
123 <data format="txt" name="trinity_log" label="${tool.name} on ${on_string}: log" />
d0c258caafaf Uploaded
nate
parents:
diff changeset
124 <data format="fasta" name="assembled_transcripts" label="${tool.name} on ${on_string}: Assembled Transcripts" from_work_dir="trinity_out_dir/Trinity.fasta"/>
d0c258caafaf Uploaded
nate
parents:
diff changeset
125 </outputs>
d0c258caafaf Uploaded
nate
parents:
diff changeset
126 <tests>
d0c258caafaf Uploaded
nate
parents:
diff changeset
127 </tests>
d0c258caafaf Uploaded
nate
parents:
diff changeset
128 <help>
4
f98f80675d60 Corrected perl module name and improved output handling for better performance from Phil Blood.
nate
parents: 3
diff changeset
129 Trinity is a de novo transcript assembler that uses RNA-seq data as input. This tool runs all Trinity_ commands--Inchworm, Chrysalis, and Butterfly--in a single pass. This version of Trinity runs on Bridges_ at the `Pittsburgh Supercomputing Center`_ using a version of Trinity 2.2.0 optimized for the unique memory profile of that system.
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
130
d0c258caafaf Uploaded
nate
parents:
diff changeset
131 .. _Trinity: http://trinityrnaseq.github.io
d0c258caafaf Uploaded
nate
parents:
diff changeset
132 .. _Pittsburgh Supercomputing Center: http://www.psc.edu
1
976e99dd3c2b New version for Bridges
nate
parents: 0
diff changeset
133 .. _Bridges: http://www.psc.edu/bridges
0
d0c258caafaf Uploaded
nate
parents:
diff changeset
134 </help>
d0c258caafaf Uploaded
nate
parents:
diff changeset
135 </tool>