Mercurial > repos > rnateam > rcas

comparison rcas.xml @ 1:7c7a2a381dfe draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/rcas/ commit 5c6486dead878a8c9521e1d6d50b3a537a2ec2b0
author rnateam
date Thu, 21 Jun 2018 15:07:13 -0400
parents aa9579837a2e
children
comparison
equal deleted inserted replaced
0:aa9579837a2e 1:7c7a2a381dfe
1 <?xml version="1.0" encoding="UTF-8"?> 1 <tool id="rcas" name="RCAS" version="1.5.4">
2 <tool id="rcas" name="RNA Centric Annotation System" version="1.1.1"> 2 <description>- RNA Centric Annotation System</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.1.1">bioconductor-rcas</requirement> 4 <requirement type="package" version="1.5.4">bioconductor-rcas</requirement>
5 </requirements> 5 </requirements>
6 <stdio> 6 <stdio>
7 <regex match="Execution halted" source="both" level="fatal" description="Execution halted." /> 7 <regex match="Execution halted" source="both" level="fatal" description="Execution halted." />
8 <exit_code range="1:" /> 8 <exit_code range="1:" />
9 </stdio> 9 </stdio>
10 <command><![CDATA[Rscript '$script_file' 10 <command><![CDATA[
11 11 cat '$script_file' &&
12 && 12 #if $analysis_type.analysis_type_selector == 'single_set_analysis':
13 mv *RCAS.report.html RCAS.report.html 13 Rscript '$script_file' &&
14 14 mv *RCAS.report.html RCAS.report.html
15 15 #if $run_annot == "TRUE":
16 #if $run_anot == "TRUE": 16 &&
17 && 17 mv Figure*summarizeQueryRegions.data.tsv summarizeQueryRegions.data.tsv &&
18 mv Figure*summarizeQueryRegions.data.tsv summarizeQueryRegions.data.tsv && 18 mv Figure*query_gene_types.data.tsv query_gene_types.data.tsv &&
19 mv Figure*query_gene_types.data.tsv query_gene_types.data.tsv && 19 mv Figure*transcriptBoundaryCoverage.fiveprime.data.tsv transcriptBoundaryCoverage.fiveprime.data.tsv &&
20 mv Figure*transcriptBoundaryCoverage.fiveprime.data.tsv transcriptBoundaryCoverage.fiveprime.data.tsv && 20 mv Figure*transcriptBoundaryCoverage.threeprime.data.tsv transcriptBoundaryCoverage.threeprime.data.tsv &&
21 mv Figure*transcriptBoundaryCoverage.threeprime.data.tsv transcriptBoundaryCoverage.threeprime.data.tsv && 21 mv Figure*exonIntronBoundaryCoverage.fiveprime.data.tsv exonIntronBoundaryCoverage.fiveprime.data.tsv &&
22 mv Figure*exonIntronBoundaryCoverage.fiveprime.data.tsv exonIntronBoundaryCoverage.fiveprime.data.tsv && 22 mv Figure*exonIntronBoundaryCoverage.threeprime.data.tsv exonIntronBoundaryCoverage.threeprime.data.tsv &&
23 mv Figure*exonIntronBoundaryCoverage.threeprime.data.tsv exonIntronBoundaryCoverage.threeprime.data.tsv && 23 mv Figure*coverageprofilelist.data.tsv coverageprofilelist.data.tsv &&
24 mv Figure*coverageprofilelist.data.tsv coverageprofilelist.data.tsv && 24 mv Table*getTargetedGenesTable.data.tsv getTargetedGenesTable.data.tsv
25 mv Table*getTargetedGenesTable.data.tsv getTargetedGenesTable.data.tsv 25 #end if
26 #if $analysis_type.run_go == "TRUE":
27 &&
28 mv Table*goBP.data.tsv goBP.data.tsv &&
29 mv Table*goMF.data.tsv goMF.data.tsv &&
30 mv Table*goCC.data.tsv goCC.data.tsv
31 #end if
32
33 #if $analysis_type.gsea_set.run_gsea == "TRUE":
34 &&
35 mv Table*GSEA.data.tsv GSEA.data.tsv
36 #end if
37 #else:
38 Rscript '$script_file'
26 #end if 39 #end if
27 40 ]]></command>
28 41 <configfiles>
29 #if $run_GOrich == "TRUE": 42 <configfile name="script_file"><![CDATA[
30 && 43 #import re
31 mv Table*goBP.data.tsv goBP.data.tsv && 44 library("RCAS")
32 mv Table*goMF.data.tsv goMF.data.tsv && 45 #if $analysis_type.analysis_type_selector == 'single_set_analysis':
33 mv Table*goCC.data.tsv goCC.data.tsv 46 runReport(queryFilePath = '${analysis_type.single_bed_file}',
47 gffFilePath = '${input_gtf_file}',
48 genomeVersion = '${genome_version}',
49 #if $analysis_type.run_go
50 goAnalysis = TRUE,
51 #end if
52 #if $analysis_type.gsea_set.run_gsea
53 msigdbAnalysis = TRUE,
54 msigdbFilePath = '${$analysis_type.gsea_set.input_human_msigdb_gmt}',
55 #end if
56 sampleN = '${analysis_type.downsampling}',
57 annotationSummary = ${run_annot},
58 motifAnalysis = ${run_motif},
59 outDir = getwd(),
60 #if $analysis_type.output_raw_tables
61 printProcessedTables = TRUE,
62 #end if
63 selfContained = TRUE)
64 #elif $analysis_type.analysis_type_selector == 'multi_set_analysis':
65 library("mgcv")
66 paths <- c('#echo "','".join(map(str, $analysis_type.multi_bed_file))#')
67 #set $ids = [re.sub('[^\w\-]', '_', str($bed_file.element_identifier)) for $bed_file in $analysis_type.multi_bed_file]
68 ids <- c('#echo "','".join($ids)#')
69 projData <- data.frame('sampleName' = ids, 'bedFilePath' = paths, stringsAsFactors = FALSE)
70 projDataFile <- file.path(getwd(), 'myProjDataFile.tsv')
71 write.table(projData, projDataFile, sep = '\t', quote =FALSE, row.names = FALSE)
72 gtfFilePath = '${input_gtf_file}'
73 databasePath <- file.path(getwd(), 'myProject.sqlite')
74 invisible(createDB(dbPath = databasePath, projDataFile = projDataFile, gtfFilePath = gtfFilePath,
75 motifAnalysis = ${run_motif},
76 annotationSummary = ${run_annot},
77 genomeVersion = '${genome_version}'))
78 sampleData <- data.frame('sampleName' = ids, 'sampleGroup' = ids, stringsAsFactors = FALSE)
79 sampleDataFile <- file.path(getwd(), 'mySampleDataTable.tsv')
80 write.table(sampleData, sampleDataFile, sep = '\t', quote =FALSE, row.names = FALSE)
81 runReportMetaAnalysis(dbPath = databasePath, sampleTablePath = sampleDataFile, outFile = file.path(getwd(), 'RCAS.multi_sample_report.html'))
34 #end if 82 #end if
35 83 ]]></configfile>
36
37 #if $choice.run_PATHrich == "TRUE":
38 &&
39 mv Table*GSEA.data.tsv GSEA.data.tsv
40 #end if
41
42
43 #if $run_motif == "TRUE":
44 &&
45 mv Table*motif_analysis_table.data.tsv motif_analysis_table.data.tsv
46 #end if]]></command>
47 <configfiles>
48 <configfile name="script_file">library("RCAS")
49
50 runReport(queryFilePath = '${input_BED}',
51
52 gffFilePath = '${input_GTF}',
53
54 #if $choice.run_PATHrich == "TRUE":
55 msigdbFilePath = '${choice.input_human_msigdb_gmt}',
56 #end if
57
58 annotationSummary = ${run_anot},
59
60 goAnalysis = ${run_GOrich},
61
62 msigdbAnalysis = ${choice.run_PATHrich},
63
64 motifAnalysis = ${run_motif},
65
66 genomeVersion = '${genomeVersion}',
67
68 outDir = getwd(),
69
70 printProcessedTables = TRUE,
71
72 sampleN = '${downsampling}',
73
74 selfContained = TRUE)</configfile>
75 </configfiles> 84 </configfiles>
76 <inputs> 85 <inputs>
77 <param name="genomeVersion" type="select" label="Genome Version"> 86 <param name="genome_version" type="select" label="Genome Version">
78 <option value="hg19" selected="true">hg19</option> 87 <option value="hg19" selected="true">hg19</option>
88 <option value="hg38">hg38</option>
89 <option value="mm9">mm9</option>
90 <option value="mm10">mm10</option>
79 <option value="dm3">dm3</option> 91 <option value="dm3">dm3</option>
80 <option value="ce10">ce10</option> 92 <option value="ce10">ce10</option>
81 <option value="mm9">mm9</option>
82 </param> 93 </param>
83 <param name="input_BED" type="data" format="BED" label="Target regions in BED format" help="The coordinates should be in accord with Genome Version." /> 94
84 <param name="input_GTF" type="data" format="GTF" label="Reference annotation in ENSEMBL GTF format" /> 95 <param name="input_gtf_file" type="data" format="GTF" label="Reference annotation in ENSEMBL GTF format" />
85 <param name="run_anot" label="Run annotation." type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="True" help="Use this option if you want to run annotation." /> 96
86 <param name="run_GOrich" label="Run GO term enrichment" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False" help="Use this option if you want to run GO term enrichment (supported genome versions: hg19, mm9, dm3)." /> 97 <conditional name="analysis_type">
87 <conditional name="choice"> 98 <param name="analysis_type_selector" type="select" label="Select analysis type">
88 <param name="run_PATHrich" type="select" label="Run gene set enrichment" help="Use this option if you want to run gene set enrichment."> 99 <option value="single_set_analysis" selected="true">Single sample analysis</option>
89 <option value="FALSE" selected="True">No</option> 100 <option value="multi_set_analysis">Multi sample analysis</option>
90 <option value="TRUE">Yes</option>
91 </param> 101 </param>
92 <when value="TRUE"> 102 <!-- Single dataset analysis -->
93 <param name="input_human_msigdb_gmt" type="data" format="tabular" label="Human Molecular Signatures Database (MSigDB)" help="The database is usesd for gene set enrichment (supported genome versions: hg19, mm9, dm3). For non-human species, the human MSigDB will be automatically converted accordingly." /> 103 <when value="single_set_analysis">
104 <param name="single_bed_file" type="data" format="bed"
105 label="Single sample analysis BED file"
106 help="Genomic BED file used for single sample analysis"/>
107 <param name="run_go" label="Run GO term enrichment analysis"
108 type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False"
109 help="Run GO term enrichment analysis (supported genome versions: hg19, hg38, mm9, mm10, dm3)" />
110 <conditional name="gsea_set">
111 <param name="run_gsea" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="false" label="Run gene set enrichment analysis"/>
112 <when value="FALSE" />
113 <when value="TRUE">
114 <param name="input_human_msigdb_gmt" type="data" format="tabular"
115 label="Provide human Molecular Signatures Database (MSigDB) file"
116 help="This database file is needed for gene set enrichment analysis (supported genome versions: hg19, hg38, mm9, mm10, dm3). For non-human species, the human MSigDB will be automatically converted." />
117 </when>
118 </conditional>
119 <param name="downsampling" label="Downsampling (N)" type="text" value="0"
120 help="Randomly sample down query regions to (N). To activate sampling a positive integer value smaller than the total number of query regions should be given. Default value is 0 (i.e. no downsampling applied)" />
121 <param name="output_raw_tables" type="boolean" falsevalue="FALSE" truevalue="TRUE" value="False"
122 label="Output raw data tables"
123 help="Output single sample analysis raw data tables that are used for plots/tables as text files"/>
94 </when> 124 </when>
95 <when value="FALSE" /> 125 <!-- Multiple datasets meta analysis -->
126 <when value="multi_set_analysis">
127 <param name="multi_bed_file" type="data" format="bed"
128 label="Multi sample analysis BED files" multiple="true"
129 help="Genomic BED files used for multi sample analysis. NOTE that the dataset name inside the Galaxy history is used as identifier for each set, resulting in plots with the Galaxy dataset names corresponding to their respective input BED files."/>
130 </when>
96 </conditional> 131 </conditional>
97 <param name="run_motif" label="Run motif search" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False" help="Use this option if you want to run motif search." /> 132
98 <param name="downsampling" label="Downsampling (N)" type="text" value="0" help="Randomly sample query regions down to (N)" /> 133 <!-- Parameters common to multi and single set analysis -->
134 <param name="run_annot" label="Output annotation summaries" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="True" help="Output annotation summaries from overlap operations" />
135 <param name="run_motif" label="Run motif analysis" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False" help="Run motif analysis for each input dataset and each transcript region" />
99 </inputs> 136 </inputs>
100 <outputs> 137 <outputs>
101 <data name="report" format="html" from_work_dir="RCAS.report.html" label="${tool.name} on ${on_string}: dynamic HTML" /> 138 <data name="report" format="html" from_work_dir="RCAS.report.html" label="${tool.name} on ${on_string}: single sample analysis report HTML">
139 <filter>analysis_type["analysis_type_selector"] == "single_set_analysis"</filter>
140 </data>
102 <data name="summarizeQueryRegions" format="tsv" from_work_dir="summarizeQueryRegions.data.tsv" label="${tool.name} on ${on_string}: Query regions summary"> 141 <data name="summarizeQueryRegions" format="tsv" from_work_dir="summarizeQueryRegions.data.tsv" label="${tool.name} on ${on_string}: Query regions summary">
103 <filter>run_anot == True</filter> 142 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
104 </data> 143 </data>
105 <data name="query_gene_types" format="tsv" from_work_dir="query_gene_types.data.tsv" label="${tool.name} on ${on_string}: Query gene types"> 144 <data name="query_gene_types" format="tsv" from_work_dir="query_gene_types.data.tsv" label="${tool.name} on ${on_string}: Query gene types">
106 <filter>run_anot == True</filter> 145 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
107 </data> 146 </data>
108 <data name="transcriptBoundaryCoverage.fiveprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (5')"> 147 <data name="transcriptBoundaryCoverage.fiveprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (5')">
109 <filter>run_anot == True</filter> 148 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
110 </data> 149 </data>
111 <data name="transcriptBoundaryCoverage.threeprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (3')"> 150 <data name="transcriptBoundaryCoverage.threeprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (3')">
112 <filter>run_anot == True</filter> 151 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
113 </data> 152 </data>
114 <data name="exonIntronBoundaryCoverage.fiveprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (5')"> 153 <data name="exonIntronBoundaryCoverage.fiveprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (5')">
115 <filter>run_anot == True</filter> 154 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
116 </data> 155 </data>
117 <data name="exonIntronBoundaryCoverage.threeprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (3')"> 156 <data name="exonIntronBoundaryCoverage.threeprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (3')">
118 <filter>run_anot == True</filter> 157 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
119 </data> 158 </data>
120 <data name="coverageprofilelist" format="tsv" from_work_dir="coverageprofilelist.data.tsv" label="${tool.name} on ${on_string}: Coverage profile list"> 159 <data name="coverageprofilelist" format="tsv" from_work_dir="coverageprofilelist.data.tsv" label="${tool.name} on ${on_string}: Coverage profile list">
121 <filter>run_anot == True</filter> 160 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
122 </data> 161 </data>
123 <data name="getTargetedGenesTable" format="tsv" from_work_dir="getTargetedGenesTable.data.tsv" label="${tool.name} on ${on_string}: Targeted genes"> 162 <data name="getTargetedGenesTable" format="tsv" from_work_dir="getTargetedGenesTable.data.tsv" label="${tool.name} on ${on_string}: Targeted genes">
124 <filter>run_anot == True</filter> 163 <filter>run_annot is True and analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['output_raw_tables'] is True</filter>
125 </data> 164 </data>
126 <data name="goCC" format="tsv" from_work_dir="goCC.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (cellular compartments)"> 165 <data name="goCC" format="tsv" from_work_dir="goCC.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (cellular compartments)">
127 <filter>run_GOrich == True</filter> 166 <filter>analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['run_go'] is True and analysis_type['output_raw_tables'] is True</filter>
128 </data> 167 </data>
129 <data name="goBP" format="tsv" from_work_dir="goBP.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (biological processes)"> 168 <data name="goBP" format="tsv" from_work_dir="goBP.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (biological processes)">
130 <filter>run_GOrich == True</filter> 169 <filter>analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['run_go'] is True and analysis_type['output_raw_tables'] is True</filter>
131 </data> 170 </data>
132 <data name="goMF" format="tsv" from_work_dir="goMF.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (molecular functions)"> 171 <data name="goMF" format="tsv" from_work_dir="goMF.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (molecular functions)">
133 <filter>run_GOrich == True</filter> 172 <filter>analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['run_go'] is True and analysis_type['output_raw_tables'] is True</filter>
134 </data> 173 </data>
135 <data name="GSEA" format="tsv" from_work_dir="GSEA.data.tsv" label="${tool.name} on ${on_string}: Gene set enrichment analysis"> 174 <data name="GSEA" format="tsv" from_work_dir="GSEA.data.tsv" label="${tool.name} on ${on_string}: Gene set enrichment analysis">
136 <filter>choice['run_PATHrich'] == "TRUE"</filter> 175 <filter>analysis_type["analysis_type_selector"] == "single_set_analysis" and analysis_type['gsea_set']['run_gsea'] is True and analysis_type['output_raw_tables'] is True</filter>
137 </data> 176 </data>
138 <data name="motif" format="tsv" from_work_dir="motif_analysis_table.data.tsv" label="${tool.name} on ${on_string}: Motif"> 177 <data name="multi_report" format="html" from_work_dir="RCAS.multi_sample_report.html" label="${tool.name} on ${on_string}: multi sample analysis report HTML">
139 <filter>run_motif == True</filter> 178 <filter>analysis_type["analysis_type_selector"] == "multi_set_analysis"</filter>
140 </data> 179 </data>
141 </outputs> 180 </outputs>
142 <tests> 181 <tests>
143 <test> 182 <test>
144 <param name="input_BED" value="input.TIA1.bed" /> 183 <param name="analysis_type_selector" value="single_set_analysis"/>
145 <param name="input_GTF" value="input.Homo_sapiens.GRCh37-chr1-f10k.75.gtf" /> 184 <param name="single_bed_file" value="input.TIA1.bed"/>
146 <param name="input_human_msigdb_gmt" value="input.msigdb_test.gmt" /> 185 <param name="input_gtf_file" value="input.Homo_sapiens.GRCh37-chr1-f10k.75.gtf"/>
147 <param name="run_anot" value="TRUE" /> 186 <param name="input_human_msigdb_gmt" value="input.msigdb_test.gmt"/>
148 <param name="run_GOrich" value="TRUE" /> 187 <param name="run_annot" value="TRUE"/>
149 <param name="run_PATHrich" value="TRUE" /> 188 <param name="run_go" value="TRUE"/>
150 <param name="run_motif" value="TRUE" /> 189 <param name="run_gsea" value="TRUE"/>
151 <param name="genomeVersion" value="hg19" /> 190 <param name="run_motif" value="TRUE"/>
152 <output name="report" file="output.TIA1.bed.RCAS.report.html" ftype="html" compare="sim_size" /> 191 <param name="output_raw_tables" value="TRUE"/>
153 <output name="summarizeQueryRegions" file="summarizeQueryRegions.data.tsv" ftype="tsv" /> 192 <param name="genome_version" value="hg19" />
154 <output name="query_gene_types" file="query_gene_types.data.tsv" ftype="tsv" /> 193 <output name="report" file="input.TIA1.bed.RCAS.report.html" ftype="html" compare="sim_size"/>
155 <output name="transcriptBoundaryCoverage.fiveprime" file="transcriptBoundaryCoverage.fiveprime.data.tsv" ftype="tsv" /> 194 <output name="summarizeQueryRegions" file="summarizeQueryRegions.data.tsv" ftype="tsv"/>
156 <output name="transcriptBoundaryCoverage.threeprime" file="transcriptBoundaryCoverage.threeprime.data.tsv" ftype="tsv" /> 195 <output name="query_gene_types" file="query_gene_types.data.tsv" ftype="tsv"/>
157 <output name="exonIntronBoundaryCoverage.fiveprime" file="exonIntronBoundaryCoverage.fiveprime.data.tsv" ftype="tsv" /> 196 <output name="transcriptBoundaryCoverage.fiveprime" file="transcriptBoundaryCoverage.fiveprime.data.tsv" ftype="tsv"/>
158 <output name="exonIntronBoundaryCoverage.threeprime" file="exonIntronBoundaryCoverage.threeprime.data.tsv" ftype="tsv" /> 197 <output name="transcriptBoundaryCoverage.threeprime" file="transcriptBoundaryCoverage.threeprime.data.tsv" ftype="tsv"/>
159 <output name="coverageprofilelist" file="coverageprofilelist.data.tsv" ftype="tsv" /> 198 <output name="exonIntronBoundaryCoverage.fiveprime" file="exonIntronBoundaryCoverage.fiveprime.data.tsv" ftype="tsv"/>
160 <output name="getTargetedGenesTable" file="getTargetedGenesTable.data.tsv" ftype="tsv" /> 199 <output name="exonIntronBoundaryCoverage.threeprime" file="exonIntronBoundaryCoverage.threeprime.data.tsv" ftype="tsv"/>
200 <output name="coverageprofilelist" file="coverageprofilelist.data.tsv" ftype="tsv"/>
201 <output name="getTargetedGenesTable" file="getTargetedGenesTable.data.tsv" ftype="tsv"/>
161 <output name="goCC" file="goCC.data.tsv" ftype="tsv" compare="sim_size"/> 202 <output name="goCC" file="goCC.data.tsv" ftype="tsv" compare="sim_size"/>
162 <output name="goBP" file="goBP.data.tsv" ftype="tsv" compare="sim_size"/> 203 <output name="goBP" file="goBP.data.tsv" ftype="tsv" compare="sim_size"/>
163 <output name="goMF" file="goMF.data.tsv" ftype="tsv" compare="sim_size"/> 204 <output name="goMF" file="goMF.data.tsv" ftype="tsv" compare="sim_size"/>
164 <output name="GSEA" file="GSEA.data.tsv" ftype="tsv" /> 205 <output name="GSEA" file="GSEA.data.tsv" ftype="tsv"/>
165 <output name="motif" file="motif_analysis_table.data.tsv" ftype="tsv" compare="sim_size" /> 206 </test>
207 <test>
208 <param name="analysis_type_selector" value="multi_set_analysis"/>
209 <param name="multi_bed_file" value="EIF4A3Sauliere20121a.bed,EIF4A3Sauliere20121b.bed,FMR1_Ascano2012a_hg19.bed,FMR1_Ascano2012b_hg19.bed,FUS_Nakaya2013c_hg19.bed,FUS_Nakaya2013d_hg19.bed"/>
210 <param name="input_gtf_file" value="hg19.sample.gtf"/>
211 <param name="run_annot" value="TRUE"/>
212 <param name="run_motif" value="TRUE"/>
213 <param name="genome_version" value="hg19" />
214 <output name="multi_report" file="test2_multi_set_analysis_report.html" ftype="html" compare="sim_size" delta="20000"/>
166 </test> 215 </test>
167 </tests> 216 </tests>
168 <help><![CDATA[.. class:: infomark 217 <help><![CDATA[
169 218
170 **Purpose** 219 **Introduction**
171 220
172 RNA Centric Annotation System (RCAS) automatically generates 221 RCAS is an R/Bioconductor package designed as a generic reporting tool for the functional analysis of transcriptome-wide regions of interest detected by high-throughput experiments. Such transcriptomic regions could be, for instance, signal peaks detected by CLIP-Seq analysis for protein-RNA interaction sites, RNA modification sites (alias the epitranscriptome), CAGE-tag locations, or any other collection of query regions at the level of the transcriptome. RCAS produces in-depth annotation summaries and coverage profiles based on the distribution of the query regions with respect to transcript features (exons, introns, 5’/3’ UTR regions, exon-intron boundaries, promoter regions). Moreover, RCAS can carry out functional enrichment analyses of annotated gene sets, GO terms, and de novo motif discovery. RCAS is available in the Bioconductor repository, packaged in multiple environments including Conda, Galaxy, and Guix, and as a webservice at http://rcas.mdc-berlin.de/.
173 dynamic annotations for custom input files 222
174 that contain transcriptomic target regions. 223 Currently supported genome builds are hg19 and hg38 (human), mm9 and mm10 (mouse), dm3 (fly), and ce10 (worm). Modules for annotation summaries and motif analysis are supported for each of these genome builds. GO term and gene-set enrichment analyses are supported for hg19, hg38, mm9, mm10, and dm3. ce10 is currently not supportedfor GO/GSEA modules.
175 RCAS automatically summarizes annotated features 224
176 that overlap with targets in the BED file,
177 and perform enrichment analysis of
178 Gene Ontology (GO) terms, gene set and motifs.
179 225
180 ----- 226 -----
181 227
182 .. class:: infomark
183
184 **Inputs** 228 **Inputs**
185 229
186 1. A target region file in BED format 230 1. One (single sample analysis) or several (multi sample analysis) genomic target region files in BED format
187 2. A reference annotation file in GTF format 231 2. A genome reference annotation file in GTF format
188 3. A Human Molecular Signatures Database (MSigDB) (only needed for gene set enrichment) 232 3. A human Molecular Signatures Database (MSigDB) (only in single sample analysis for gene set enrichment analysis)
189 233
190 ----- 234 -----
191 235
192 .. class:: infomark
193
194 **Outputs** 236 **Outputs**
195 237
196 The outputs consist of a dynamic HTML file and 238 The outputs consist of a dynamic HTML file (both for single and multi sample analysis) and optionally a number (depending on selected options) of tabular files (single sample analysis only).
197 a dozen of tabular files. 239 The dynamic HTML file is composed of interactive tables and figures,
198 The dynamic HTML file is composed of the interactive tables and figures,
199 which can be downloaded and viewed with a web browser. 240 which can be downloaded and viewed with a web browser.
200 241
201 The tabular files correspond to the respective figures in the HTML file, 242 The tabular files contain the RCAS analysis results, corresponding to the
202 which are the results 243 respective figures in the HTML file:
203 of different RCAS analysis, as following:
204 244
205 1. Annotation summary for query regions 245 1. Annotation summary for query regions
206 246
207 * Query regions summary 247 * Query regions summary
208 * Query gene types 248 * Query gene types
219 * GO term enrichment (biological processes) 259 * GO term enrichment (biological processes)
220 * GO term enrichment (molecular functions) 260 * GO term enrichment (molecular functions)
221 261
222 3. Gene set enrichment analysis results 262 3. Gene set enrichment analysis results
223 263
224 4. Motif analysis results]]></help> 264 4. Motif analysis results (no table output in 1.5.4.)
265
266 ]]></help>
225 <citations> 267 <citations>
226 <citation type="doi">10.1093/nar/gkx120</citation> 268 <citation type="doi">10.1093/nar/gkx120</citation>
227 </citations> 269 </citations>
228 </tool> 270 </tool>