Mercurial > repos > yhoogstrate > fuma

comparison fuma.xml @ 2:86526900cb8f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/fuma_galaxy_wrapper commit 3da3fcc0204205d4899763f9fe63edf9aa16d5a2
author yhoogstrate
date Mon, 12 Oct 2015 04:17:07 -0400
parents 54ce44828e1b
children 4966079d474b
comparison
equal deleted inserted replaced
1:54ce44828e1b 2:86526900cb8f
1 <?xml version="1.0" encoding="UTF-8"?> 1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="fuma" name="FuMa" version="2.7.1.b"> 2 <tool id="fuma" name="FuMa" version="2.10.0.a">
3 <description>FuMa (FusionMatcher) matches detected fusion genes based on gene name subset matching (designed in particular for RNA-Seq).</description> 3 <description>match detected fusion genes based on gene names (in particular for RNA-Seq).</description>
4 4
5 <requirements> 5 <requirements>
6 <requirement type="package" version="2.7.1">fuma</requirement> 6 <requirement type="package" version="2.7">python</requirement>
7 </requirements> 7 <requirement type="package" version="2.10.0">fuma</requirement>
8 8 </requirements>
9 <version_command>fuma --version 2>&amp;1 | head -n 1</version_command><!-- -V also works, but is not GNU standard --> 9
10 10 <version_command>fuma --version 2>&amp;1 | head -n 1</version_command><!-- -V also works, but is not GNU standard -->
11 <command> 11
12 #import pipes 12 <command><![CDATA[
13 13 #import pipes
14 #set $gene_annotations = [] 14
15 #set $samples = [] 15 #set $gene_annotations = []
16 #set $links = [] 16 #set $samples = []
17 17 #set $links = []
18 #for $i, $d in enumerate( $datasets ) 18
19 19 #for $i, $d in enumerate( $datasets )
20 #set $sample_name = pipes.quote(str($d['sample'].name)) 20 #set $sample_name = pipes.quote(str($d['sample'].name))
21 21
22 #set $gene_annotations = $gene_annotations + [ "ga_" + str($i) + ":" + str($d['gene_annotation'].file_name) ] 22 #set $gene_annotations = $gene_annotations + [ "ga_" + str($i) + ":" + str($d['gene_annotation'].file_name) ]
23 23
24 #set $samples = $samples + [ $sample_name + ":" + str($d['format']) + ":" + str($d['sample'].file_name) ] 24 #set $samples = $samples + [ $sample_name + ":" + str($d['format']) + ":" + str($d['sample'].file_name) ]
25 #set $links = $links + [ $sample_name + ":" + str("ga_") + str($i) ] 25 #set $links = $links + [ $sample_name + ":" + str("ga_") + str($i) ]
26 #end for 26 #end for
27 27
28 #set $gene_annotations_str = " ".join(gene_annotations) 28 #set $gene_annotations_str = " ".join(gene_annotations)
29 #set $samples_str = " ".join(samples) 29 #set $samples_str = " ".join(samples)
30 #set $links_str = " ".join(links) 30 #set $links_str = " ".join(links)
31 31
32 fuma 32 fuma
33 -a 33 -m
34 $gene_annotations_str 34 $params.matching_method
35 -s 35
36 $samples_str 36 $params.strand_specific_matching
37 -l 37 $params.acceptor_donor_order_specific_matchig
38 $links_str 38
39 #if $output_format.value == "list_boolean" 39 -a
40 -f list 40 $gene_annotations_str
41 #else 41 -s
42 -f $output_format.value 42 $samples_str
43 #end if 43 -l
44 -o $fuma_overview ; 44 $links_str
45 45 #if $params.output_format.value == "list_boolean"
46 46 -f list
47 47 #else
48 #if $output_format.value == "list_boolean" 48 -f $params.output_format.value
49 fuma-list-to-boolean-list -o tmp.txt $fuma_overview &amp;&amp; 49 #end if
50 mv tmp.txt $fuma_overview 50 -o $fuma_overview ;
51 #end if 51
52 </command> 52
53 53 #if $params.output_format.value == "list_boolean"
54 <inputs> 54 fuma-list-to-boolean-list -o tmp.txt $fuma_overview ;
55 <repeat name="datasets" title="FusionGene Datasets" min="2"> 55 mv tmp.txt $fuma_overview
56 <param name="sample" type="data" format="txt,tabular" label="Dataset (RNA-Seq fusion gene detection experiment)" /> 56 #end if
57 <param name="format" type="select" label="Format of dataset"> 57 ]]></command>
58 <option value="chimerascan">ChimeraScan</option> 58
59 <option value="defuse">DeFuse</option> 59 <inputs>
60 <option value="complete-genomics">Complete Genomics</option> 60 <repeat name="datasets" title="FusionGene Datasets" min="2">
61 <option value="fusion-catcher_final">Fusion Catcher (final-list file)</option> 61 <param name="sample" type="data" format="txt,tabular" label="Dataset (RNA-Seq fusion gene detection experiment)" />
62 <option value="fusionmap">FusionMap</option> 62 <param name="format" type="select" label="Format of dataset">
63 <option value="trinity-gmap">GMAP (As step after Trinity)</option> 63 <option value="chimera">Chimera prettyPrint()</option>
64 <option value="oncofuse">OncoFuse</option> 64 <option value="chimerascan">ChimeraScan</option>
65 <option value="rna-star_chimeric">STAR (chimeric file)</option> 65 <option value="defuse">DeFuse</option>
66 <option value="tophat-fusion_pre">Tophat Fusion Pre (fusions.out)</option> 66 <option value="complete-genomics">Complete Genomics var/mastervar</option>
67 <option value="tophat-fusion_post_potential_fusion">Tophat Fusion Post (potential_fusion.txt)</option> 67 <option value="fusion-catcher_final">Fusion Catcher (final-list file)</option>
68 <option value="tophat-fusion_post_result">Tophat Fusion Post (result.txt)</option> 68 <option value="fusionmap">FusionMap</option>
69 </param> 69 <option value="trinity-gmap">GMAP (As step after Trinity)</option>
70 <param name="gene_annotation" type="data" format="bed" label="Corresponding gene-name annotation file (BED format)" help="Make use of persistent gene annotations! Gene annotations should only be different if different reference genome builds were used." /> 70 <option value="oncofuse">OncoFuse</option>
71 </repeat> 71 <option value="rna-star_chimeric">STAR (chimeric file)</option>
72 72 <option value="star-fusion_final">STAR-Fusion (candidates.final)</option>
73 <param name="output_format" type="select" label="Output format"> 73 <option value="tophat-fusion_pre">Tophat Fusion Pre (fusions.out)</option>
74 <option value="list_boolean" selected="true">List (Boolean)</option> 74 <option value="tophat-fusion_post_potential_fusion">Tophat Fusion Post (potential_fusion.txt)</option>
75 <option value="list">List</option> 75 <option value="tophat-fusion_post_result">Tophat Fusion Post (result.txt)</option>
76 <option value="summary">Count summary</option> 76 <option value="tophat-fusion_post_result_html">Tophat Fusion Post (result.html)</option>
77 </param> 77 </param>
78 </inputs> 78 <param name="gene_annotation" type="data" format="bed" label="Corresponding gene-name annotation file (BED format)" help="Make use of persistent gene annotations! Gene annotations should only be different if different reference genome builds were used." />
79 79 </repeat>
80 <outputs> 80
81 <data format="tabular" name="fuma_overview" label="${tool.name} on ${', '.join([ str(d['sample'].hid)+': '+d['sample'].name for d in $datasets ])}" /> 81 <conditional name="params">
82 </outputs> 82 <param name="settingsType" type="select" label="Settings to use" help="You can use the default settings or set custom values for any FuMa parameter.">
83 83 <option value="preSet" selected="true">Use Defaults</option>
84 <tests> 84 <option value="full">Full parameter list</option>
85 <test> 85 </param>
86 <!-- <repeat name="datasets"> --> 86 <when value="preSet">
87 <param name="datasets_0|sample" value="chimerascan.txt" ftype="tabular" /> 87 <param name="strand_specific_matching" type="hidden" value="--strand-specific-matching" />
88 <param name="datasets_0|format" value="chimerascan" /> 88 <param name="acceptor_donor_order_specific_matchig" type="hidden" value="--acceptor-donor-order-specific-matching" />
89 <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" /> 89 </when>
90 <!-- </repeat> --> 90 <when value="full">
91 <!-- <repeat name="datasets"> --> 91 <param name="matching_method" type="select" label="Matching method: technique used to match fusion genes based on annotated gene sets" help="Overlap is the most sensitive but also more sensitive for long gene artefacts; subset is the recommended technique and EGM is conservative.">
92 <param name="datasets_1|sample" value="defuse.txt" ftype="tabular" /> 92 <option value="overlap">Overlap</option>
93 <param name="datasets_1|format" value="defuse" /> 93 <option value="subset" selected="True">Subset</option>
94 <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" /> 94 <option value="egm">Exact Geneset Matching (EGM)</option>
95 <!-- </repeat> --> 95 </param>
96 <!-- <repeat name="datasets"> --> 96
97 <param name="datasets_2|sample" value="fusion-map.txt" ftype="tabular" /> 97 <param name="strand_specific_matching" type="boolean" checked="True" truevalue="--strand-specific-matching" falsevalue="" label="Consider fusion genes distinct when the breakpoints have different strands" help="Only a limited number of file formats support this feature." />
98 <param name="datasets_2|format" value="fusionmap" /> 98 <param name="acceptor_donor_order_specific_matchig" type="boolean" checked="True" truevalue="--acceptor-donor-order-specific-matching" falsevalue="" label="Consider fusion genes distinct when the donor and acceptor sites are swapped (A,B) != (B,A)" help="This settings is not recommended when fusion genes detected in DNA-Seq are used" />
99 <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" /> 99
100 <!-- </repeat> --> 100 <param name="output_format" type="select" label="Output format">
101 <!-- <repeat name="datasets"> --> 101 <option value="list_boolean" selected="true">List (Boolean)</option>
102 <param name="datasets_3|sample" value="edgren_tp.txt" ftype="tabular" /> 102 <option value="list">List</option>
103 <param name="datasets_3|format" value="fusionmap" /> 103 <option value="summary">Count summary</option>
104 <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" /> 104 </param>
105 <!-- </repeat> --> 105 </when>
106 106 </conditional>
107 <param name="output_format" value="summary" /> 107 </inputs>
108 108
109 <output name="fuma_overview" file="output.txt" /> 109 <outputs>
110 </test> 110 <data format="tabular" name="fuma_overview" label="${tool.name} on ${', '.join([ str(d['sample'].hid)+': '+d['sample'].name for d in $datasets ])}" />
111 </tests> 111 </outputs>
112 112
113 <help>============ 113 <tests>
114 <test>
115 <!-- <repeat name="datasets"> -->
116 <param name="datasets_0|sample" value="chimerascan.txt" ftype="tabular" />
117 <param name="datasets_0|format" value="chimerascan" />
118 <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
119 <!-- </repeat> -->
120 <!-- <repeat name="datasets"> -->
121 <param name="datasets_1|sample" value="defuse.txt" ftype="tabular" />
122 <param name="datasets_1|format" value="defuse" />
123 <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
124 <!-- </repeat> -->
125 <!-- <repeat name="datasets"> -->
126 <param name="datasets_2|sample" value="fusion-map.txt" ftype="tabular" />
127 <param name="datasets_2|format" value="fusionmap" />
128 <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
129 <!-- </repeat> -->
130 <!-- <repeat name="datasets"> -->
131 <param name="datasets_3|sample" value="edgren_tp.txt" ftype="tabular" />
132 <param name="datasets_3|format" value="fusionmap" />
133 <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
134 <!-- </repeat> -->
135
136 <param name="settingsType" value="full" />
137
138 <param name="matching_method" value="subset" />
139 <param name="strand_specific_matching" value="--strand-specific-matching" />
140 <param name="acceptor_donor_order_specific_matchig" value="--acceptor-donor-order-specific-matching" />
141 <param name="output_format" value="list_boolean" />
142
143 <output name="fuma_overview" file="output_test_1.txt" />
144 </test>
145 <test>
146 <!-- <repeat name="datasets"> -->
147 <param name="datasets_0|sample" value="chimerascan.txt" ftype="tabular" />
148 <param name="datasets_0|format" value="chimerascan" />
149 <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
150 <!-- </repeat> -->
151 <!-- <repeat name="datasets"> -->
152 <param name="datasets_1|sample" value="defuse.txt" ftype="tabular" />
153 <param name="datasets_1|format" value="defuse" />
154 <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
155 <!-- </repeat> -->
156 <!-- <repeat name="datasets"> -->
157 <param name="datasets_2|sample" value="fusion-map.txt" ftype="tabular" />
158 <param name="datasets_2|format" value="fusionmap" />
159 <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
160 <!-- </repeat> -->
161 <!-- <repeat name="datasets"> -->
162 <param name="datasets_3|sample" value="edgren_tp.txt" ftype="tabular" />
163 <param name="datasets_3|format" value="fusionmap" />
164 <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
165 <!-- </repeat> -->
166
167 <param name="settingsType" value="full" />
168
169 <param name="matching_method" value="subset" />
170 <param name="strand_specific_matching" value="" />
171 <param name="acceptor_donor_order_specific_matchig" value="" />
172 <param name="output_format" value="list_boolean" />
173
174 <output name="fuma_overview" file="output_test_2.txt" />
175 </test>
176 </tests>
177
178 <help><![CDATA[
179 ============
114 Introduction 180 Introduction
115 ============ 181 ============
116 182
117 FuMa (Fusion Matcher) matches predicted fusion events (both genomic and transcriptomic) according to chromosomal location or assocatiated gene annotation(s) where the latter should be genome build inspecific. 183 FuMa (Fusion Matcher) matches predicted fusion events (both genomic and transcriptomic) according to chromosomal location or assocatiated gene annotation(s) where the latter should be genome build inspecific.
118 184
129 ******* 195 *******
130 196
131 +-------------------+-----------------------+-------------------------------------+ 197 +-------------------+-----------------------+-------------------------------------+
132 |Tools | File | Format string | 198 |Tools | File | Format string |
133 +===================+=======================+=====================================+ 199 +===================+=======================+=====================================+
200 |Chimera | prettyPrint() output | chimera |
201 +-------------------+-----------------------+-------------------------------------+
134 |ChimeraScan | chimeras.bedpe | chimerascan | 202 |ChimeraScan | chimeras.bedpe | chimerascan |
135 +-------------------+-----------------------+-------------------------------------+ 203 +-------------------+-----------------------+-------------------------------------+
136 |Complete Genomics | highConfidenceJu*.tsv | complete-genomics | 204 |Complete Genomics | highConfidenceJu*.tsv | complete-genomics |
137 +-------------------+-----------------------+-------------------------------------+ 205 +-------------------+-----------------------+-------------------------------------+
138 |Complete Genomics | allJunctionsBeta*.tsv | complete-genomics | 206 |Complete Genomics | allJunctionsBeta*.tsv | complete-genomics |
151 +-------------------+-----------------------+-------------------------------------+ 219 +-------------------+-----------------------+-------------------------------------+
152 |OncoFuse | | oncofuse | 220 |OncoFuse | | oncofuse |
153 +-------------------+-----------------------+-------------------------------------+ 221 +-------------------+-----------------------+-------------------------------------+
154 |RNA STAR | Chimeric.out.junction | rna-star_chimeric | 222 |RNA STAR | Chimeric.out.junction | rna-star_chimeric |
155 +-------------------+-----------------------+-------------------------------------+ 223 +-------------------+-----------------------+-------------------------------------+
224 |STAR Fusion | _candidates.final | star-fusion_final |
225 +-------------------+-----------------------+-------------------------------------+
156 |TopHat Fusion pre | fusions.out | tophat-fusion_pre | 226 |TopHat Fusion pre | fusions.out | tophat-fusion_pre |
157 +-------------------+-----------------------+-------------------------------------+ 227 +-------------------+-----------------------+-------------------------------------+
158 |TopHat Fusion post | potential_fusion.txt | tophat-fusion_post_potential_fusion | 228 |TopHat Fusion post | potential_fusion.txt | tophat-fusion_post_potential_fusion |
159 +-------------------+-----------------------+-------------------------------------+ 229 +-------------------+-----------------------+-------------------------------------+
160 |TopHat Fusion post | result.txt | tophat-fusion_post_result | 230 |TopHat Fusion post | result.txt | tophat-fusion_post_result |
161 +-------------------+-----------------------+-------------------------------------+ 231 +-------------------+-----------------------+-------------------------------------+
232 |TopHat Fusion post | result.html | tophat-fusion_post_result_html |
233 +-------------------+-----------------------+-------------------------------------+
162 234
163 To annotate genes upon the breakpoints you must provide a BED file that contains gene annotations for the user genome build. Make sure **your BED file contains one gene per line**. You should use BED files that contain one exon per line only if you want restrict your analysis to fusion genes detected within exons. 235 To annotate genes upon the breakpoints you must provide a BED file that contains gene annotations for the user genome build. Make sure **your BED file contains one gene per line**. You should use BED files that contain one exon per line only if you want restrict your analysis to fusion genes detected within exons.
164 236
165 UCSC genome browser provides a very simple way of obtaining BED files with one gene per line by selecting their *RefSeq Genes*-track and *knownGene*-table and putting the export format to BED. Galaxy should have a built-in UCSC table browser. 237 UCSC genome browser provides a very simple way of obtaining BED files with one gene per line by selecting their *RefSeq Genes*-track and *knownGene*-table and putting the export format to BED. Galaxy should have a built-in UCSC table browser.
166 238
167 </help> 239 ]]></help>
168 240
169 <citations> 241 <citations>
170 </citations> 242 <citation type="bibtex">
243 @unpublished{fuma,
244 author = {Youri Hoogstrate},
245 title = {FuMa: reporting overlap in RNA-seq detected fusion genes},
246 url = { https://github.com/yhoogstrate/fuma }
247 }
248 </citation>
249 </citations>
171 </tool> 250 </tool>