Mercurial > repos > iuc > stringtie

comparison stringtie.xml @ 1:9f80c71f1779 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded updated tool wrapper for stringtie 1.0.1
author iuc
date Thu, 05 Mar 2015 11:41:12 -0500
parents 62d212192002
children 520e0988ec1c
comparison
equal deleted inserted replaced
0:62d212192002 1:9f80c71f1779
1 <?xml version="1.0"?> 1 <tool id="stringtie" name="StringTie" version="1.0.1">
2 <tool name="StringTie" id="stringtie" version="1.0.0">
3 <description>RNA-Seq assembler</description> 2 <description>RNA-Seq assembler</description>
4 <requirements> 3 <requirements>
5 <requirement type="package" version="0.97">stringtie</requirement> 4 <requirement type="package" version="1.0.1">stringtie</requirement>
6 </requirements> 5 </requirements>
7 <command> 6 <command><![CDATA[
8 <![CDATA[
9 stringtie "$input_bam" 7 stringtie "$input_bam"
10 -o "$output_gtf" 8 -o "$output_gtf"
11 -p "\${GALAXY_SLOTS:-1}" 9 -p "\${GALAXY_SLOTS:-1}"
12 #if str($guide.use_guide) == 'yes': 10 #if str($guide.use_guide) == 'yes':
13 -G "$guide.guide_gff" $guide.input_estimation 11 -C "$coverage" -G "$guide.guide_gff" $guide.input_estimation
14 -C "$coverage" 12 #if str($guide.output_ballgown) == '-b':
13 $guide.output_ballgown `pwd`
14 #end if
15 #end if 15 #end if
16 #if str($option_set.options) == 'advanced': 16 #if str($option_set.options) == 'advanced':
17 -l "$option_set.name_prefix"
17 -f "$option_set.fraction" 18 -f "$option_set.fraction"
18 -m "$option_set.min_tlen" 19 -m "$option_set.min_tlen"
19 -a "$option_set.min_anchor_len" 20 -a "$option_set.min_anchor_len"
20 -j "$option_set.min_anchor_cov" 21 -j "$option_set.min_anchor_cov"
21 -c "$option_set.min_bundle_cov" 22 -c "$option_set.min_bundle_cov"
24 -M "$option_set.bundle_fraction" $option_set.sensitive $option_set.disable_trimming 25 -M "$option_set.bundle_fraction" $option_set.sensitive $option_set.disable_trimming
25 #end if 26 #end if
26 ]]> 27 ]]>
27 </command> 28 </command>
28 <inputs> 29 <inputs>
29 <param name="input_bam" type="data" format="bam" label="BAM file to assemble" /> 30 <param format="bam" label="BAM file to assemble" name="input_bam" type="data" />
30 <conditional name="guide"> 31 <conditional name="guide">
31 <param name="use_guide" type="select" label="Use GFF file to guide assembly"> 32 <param label="Use GFF file to guide assembly" name="use_guide" type="select">
32 <option value="yes">Use GFF</option> 33 <option value="yes">Use GFF</option>
33 <option value="no" selected="True">Do not use GFF</option> 34 <option selected="True" value="no">Do not use GFF</option>
34 </param> 35 </param>
35 <when value="no" /> 36 <when value="no" />
36 <when value="yes"> 37 <when value="yes">
37 <param name="guide_gff" type="data" format="gtf,gff3" label="Reference annotation to use for guiding the assembly process" /> 38 <param format="gtf,gff3" help="(-G)" label="Reference annotation to use for guiding the assembly process" name="guide_gff" type="data" />
38 <param name="input_estimation" type="boolean" truevalue="-e" falsevalue="" label="Perform abundance estimation only of input transcripts" /> 39 <param falsevalue="" help="(-e)" label="Perform abundance estimation only of input transcripts" name="input_estimation" truevalue="-e" type="boolean" />
40 <param falsevalue="" help="(-b)" label="Output additional files for use in Ballgown" name="output_ballgown" truevalue="-b" type="boolean" />
39 </when> 41 </when>
40 </conditional> 42 </conditional>
41 <conditional name="option_set"> 43 <conditional name="option_set">
42 <param name="options" type="select" label="Options"> 44 <param label="Options" name="options" type="select">
43 <option value="default" selected="True">Use defaults</option> 45 <option selected="True" value="default">Use defaults</option>
44 <option value="advanced">Specify advanced options</option> 46 <option value="advanced">Specify advanced options</option>
45 </param> 47 </param>
46 <when value="default" /> 48 <when value="default" />
47 <when value="advanced"> 49 <when value="advanced">
48 <param name="disable_trimming" type="boolean" falsevalue="" truevalue="-t" label="Disable trimming of predicted transcripts based on coverage" /> 50 <param falsevalue="" help="(-t)" label="Disable trimming of predicted transcripts based on coverage" name="disable_trimming" truevalue="-t" type="boolean" />
49 <param name="sensitive" type="boolean" truevalue="-S" falsevalue="" label="Increase sensitivity" /> 51 <param falsevalue="" help="(-S)" label="Increase sensitivity" name="sensitive" truevalue="-S" type="boolean" />
50 <param name="label" type="text" value="STRG" label="Name prefix for output transcripts" /> 52 <param help="(-l)" label="Name prefix for output transcripts" name="name_prefix" type="text" value="STRG" />
51 <param name="fraction" type="float" value="0.15" min="0.0" max="1.0" label="Minimum isoform fraction" /> 53 <param help="(-f)" label="Minimum isoform fraction" max="1.0" min="0.0" name="fraction" type="float" value="0.15" />
52 <param name="min_tlen" type="integer" value="200" label="Minimum assembled transcript length" /> 54 <param help="(-m)" label="Minimum assembled transcript length" name="min_tlen" type="integer" value="200" />
53 <param name="min_anchor_len" type="integer" value="10" label="Minimum anchor length for junctions" /> 55 <param help="(-a)" label="Minimum anchor length for junctions" name="min_anchor_len" type="integer" value="10" />
54 <param name="min_anchor_cov" type="integer" value="1" label="Minimum junction coverage" /> 56 <param help="(-j)" label="Minimum junction coverage" name="min_anchor_cov" type="integer" value="1" />
55 <param name="min_bundle_cov" type="integer" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" /> 57 <param help="(-c)" label="Minimum bundle reads per bp coverage to consider for assembly" name="min_bundle_cov" type="integer" value="2" />
56 <param name="maxcov" type="integer" value="1000000" label="Coverage saturation threshold" /> 58 <param help="(-s)" label="Coverage saturation threshold" name="maxcov" type="integer" value="1000000" />
57 <param name="bdist" type="integer" value="50" label="Gap between read mappings triggering a new bundle" /> 59 <param help="(-g)" label="Gap between read mappings triggering a new bundle" name="bdist" type="integer" value="50" />
58 <param name="bundle_fraction" type="float" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads" /> 60 <param help="(-M)" label="Fraction of bundle allowed to be covered by multi-hit reads" name="bundle_fraction" type="float" value="0.95" />
59 </when> 61 </when>
60 </conditional> 62 </conditional>
61 </inputs> 63 </inputs>
62 <outputs> 64 <outputs>
63 <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts"/> 65 <data format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" name="output_gtf" />
64 <data name="coverage" format="gff3" label="${tool.name} on ${on_string}: Coverage"> 66 <data format="gff3" label="${tool.name} on ${on_string}: Coverage" name="coverage">
65 <filter>guide['use_guide'] == "yes"</filter> 67 <filter>guide['use_guide'] == "yes"</filter>
68 </data>
69 <data format="tabular" from_work_dir="e_data.ctab" label="${tool.name} on ${on_string}: exon-level expression measurements" name="exon_expression">
70 <filter>guide['output_ballgown']</filter>
71 </data>
72 <data format="tabular" from_work_dir="i_data.ctab" label="${tool.name} on ${on_string}: intron-level expression measurements" name="intron_expression">
73 <filter>guide['output_ballgown']</filter>
74 </data>
75 <data format="tabular" from_work_dir="t_data.ctab" label="${tool.name} on ${on_string}: transcript-level expression measurements" name="transcript_expression">
76 <filter>guide['output_ballgown']</filter>
77 </data>
78 <data format="tabular" from_work_dir="e2t.ctab" label="${tool.name} on ${on_string}: exon to transcript mapping" name="exon_transcript_mapping">
79 <filter>guide['output_ballgown']</filter>
80 </data>
81 <data format="tabular" from_work_dir="i2t.ctab" label="${tool.name} on ${on_string}: intron to transcript mapping" name="intron_transcript_mapping">
82 <filter>guide['output_ballgown']</filter>
66 </data> 83 </data>
67 </outputs> 84 </outputs>
68 <tests> 85 <tests>
69 <test> 86 <test>
70 <param name="input_bam" value="stringtie_in1.bam" ftype="bam" /> 87 <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
71 <param name="use_guide" value="no" /> 88 <param name="use_guide" value="no" />
72 <param name="options" value="default" /> 89 <param name="options" value="default" />
73 <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" /> 90 <output file="stringtie_out1.gtf" ftype="gtf" name="output_gtf" />
74 </test> 91 </test>
75 <test> 92 <test>
76 <param name="input_bam" value="stringtie_in1.bam" ftype="bam" /> 93 <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
77 <param name="use_guide" value="no" /> 94 <param name="use_guide" value="no" />
78 <param name="options" value="advanced" /> 95 <param name="options" value="advanced" />
79 <param name="fraction" value="0.17" /> 96 <param name="fraction" value="0.17" />
80 <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" /> 97 <output file="stringtie_out2.gtf" ftype="gtf" name="output_gtf" />
98 </test>
99 <test>
100 <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
101 <param name="use_guide" value="yes" />
102 <param name="guide_gff" value="stringtie_in.gtf" />
103 <param name="options" value="default" />
104 <output file="stringtie_out3.gtf" ftype="gtf" name="output_gtf" />
105 </test>
106 <test>
107 <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
108 <param name="use_guide" value="yes" />
109 <param name="guide_gff" value="stringtie_in.gtf" />
110 <param name="options" value="advanced" />
111 <param name="fraction" value="0.17" />
112 <output file="stringtie_out4.gtf" ftype="gtf" name="output_gtf" />
113 </test>
114 <test>
115 <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
116 <param name="use_guide" value="yes" />
117 <param name="output_ballgown" value="yes" />
118 <param name="guide_gff" value="stringtie_in.gtf" />
119 <param name="options" value="default" />
120 <output file="ballgown/e_data.ctab" ftype="tabular" name="exon_expression" />
121 <output file="ballgown/i_data.ctab" ftype="tabular" name="intron_expression" />
122 <output file="ballgown/t_data.ctab" ftype="tabular" name="transcript_expression" />
123 <output file="ballgown/e2t.ctab" ftype="tabular" name="exon_transcript_mapping" />
124 <output file="ballgown/i2t.ctab" ftype="tabular" name="intron_transcript_mapping" />
125 <output file="stringtie_out5.gtf" ftype="gtf" name="output_gtf" />
126 <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
81 </test> 127 </test>
82 </tests> 128 </tests>
83 <help> 129 <help>
84 <![CDATA[ 130 <![CDATA[
85 StringTie v0.97 usage:: 131 StringTie v1.0.1 usage:
132 stringtie <input.bam> [-G <guide_gff>] [-l <label>] [-o <out_gtf>] [-p <cpus>]
133 [-v] [-a <min_anchor_len>] [-m <min_tlen>] [-j <min_anchor_cov>] [-n sens]
134 [-C <coverage_file_name>] [-s <maxcov>] [-c <min_bundle_cov>] [-g <bdist>]
135 {-B | -b <dir_path>} [-e]
86 136
87 stringtie <input.bam> [-G <guide_gff>] [-l <label>] [-o <out_gff>] [-p <cpus>] 137 Assemble RNA-Seq alignments into potential transcripts.
88 [-v] [-a <min_anchor_len>] [-m <min_tlen>] [-j <min_anchor_cov>] [-n sens] 138
89 [-C <coverage_file_name>] [-s <maxcov>] [-c <min_bundle_cov>] [-g <bdist>] 139 Options:
90 140 -G reference annotation to use for guiding the assembly process (GTF/GFF3)
91 Assemble RNA-Seq alignments into potential transcripts. 141 -l name prefix for output transcripts (default: STRG)
92 142 -f minimum isoform fraction (default: 0.1)
93 Options: 143 -m minimum assembled transcript length to report (default 200bp)
94 -G reference annotation to use for guiding the assembly process (GTF/GFF3) 144 -o output path/file name for the assembled transcripts GTF (default: stdout)
95 -l name prefix for output transcripts (default: STRG) 145 -a minimum anchor length for junctions (default: 10)
96 -f minimum isoform fraction (default: 0.15) 146 -j minimum junction coverage (default: 1)
97 -m minimum assembled transcript length to report (default 200bp) 147 -t disable trimming of predicted transcripts based on coverage
98 -o output file with the assembled transcripts (default: stdout) 148 (default: coverage trimming is enabled)
99 -a minimum anchor length for junctions (default: 10) 149 -c minimum reads per bp coverage to consider for transcript assembly (default: 2.5)
100 -j minimum junction coverage (default: 1) 150 -s coverage saturation threshold; further read alignments will be
101 -t disable trimming of predicted transcripts based on coverage (default: trimming enabled) 151 ignored in a region where a local coverage depth of <maxcov>
102 -c minimum bundle reads per bp coverage to consider for assembly (default: 2) 152 is reached (default: 1,000,000);
103 -s coverage saturation threshold; further read alignments will be 153 -v verbose (log bundle processing details)
104 ignored in a region where a local coverage depth of <maxcov> 154 -g gap between read mappings triggering a new bundle (default: 50)
105 is reached (default: 1,000,000); 155 -C output file with reference transcripts that are covered by reads
106 -v verbose (log bundle processing details) 156 -M fraction of bundle allowed to be covered by multi-hit reads (default:0.95)
107 -e abundance estimation only of input transcripts (for -G option) 157 -p number of threads (CPUs) to use (default: 1)
108 -g gap between read mappings triggering a new bundle (default: 50) 158 -B enable output of Ballgown table files which will be created in the
109 -S more sensitive run (default: no) 159 same directory as the output GTF (requires -G, -o recommended)
110 -C output file with all transcripts in reference that are fully 160 -b enable output of Ballgown table files but these files will be
111 covered by reads 161 created under the directory path given as <dir_path>
112 -M fraction of bundle allowed to be covered by multi-hit reads (default:0.95) 162 -e only estimates the abundance of given reference transcripts (requires -G)
113 -p number of threads (CPUs) to use (default: 1) 163 ]]>
114 164 </help>
115 ]]> 165 <citations>
116 </help> 166 <citation type="doi">doi:10.1038/nbt.3122</citation>
167 </citations>
117 </tool> 168 </tool>