|
1
|
1 <tool id="genomeindex" name="genomePrepare" workflow_compatible="false" version="20.05">
|
|
|
2 <!-- <description>get genome sequences, annotation and file path (built-in or uploaded)</description> -->
|
|
|
3
|
|
|
4 <command><![CDATA[
|
|
|
5 bash ${__tool_directory__}/scripts/obtainSpecies.sh
|
|
|
6 --curpath ${__tool_directory__}
|
|
|
7 #if $genometype.datainput == "UploadData":
|
|
|
8 --name "$genometype.speciename"
|
|
|
9 --genome $genometype.genomeData
|
|
|
10 --gff $genometype.annotationData
|
|
|
11 --otherrna $genometype.otherrna
|
|
|
12 --transcript $genometype.transcriptsData
|
|
|
13 --protein $genometype.proteinsData
|
|
|
14 --speciesout $filePath
|
|
|
15 --infout $infout1
|
|
|
16 #else
|
|
|
17 --ensembl "$genometype.buildplant"
|
|
|
18 --verorder "$genometype.version"
|
|
|
19
|
|
|
20 --outgenome $outgenome
|
|
|
21 --outgff3 $outgff3
|
|
|
22 --outtranscript $outtranscript
|
|
|
23 --outtrsnsnoRNA $outtrsnsnoRNA
|
|
|
24 --outprotein $outprotein
|
|
|
25
|
|
|
26 --speciesout $builtinPath
|
|
|
27 --infout $infout2
|
|
|
28 #end if
|
|
|
29
|
|
|
30 ]]></command>
|
|
|
31
|
|
|
32 <inputs>
|
|
|
33 <conditional name="genometype">
|
|
|
34 <!-- <param name="datainput" type="boolean" truevalue="yes" falsevalue="no" checked="true"
|
|
|
35 label="Upload your own genome data?" help ="User can also select built-in species by clicking the button-No " /> -->
|
|
|
36 <param type="select" name="datainput" display="radio" multiple="false" help="Note: for 'upload from local disk', please upload files by uploadFile function first."
|
|
|
37 label="Two ways for preparing genome data:" >
|
|
|
38 <option value="BuiltinSpecies" selected="true" > Download from EnsemblPlants database</option>
|
|
|
39 <option value="UploadData"> Upload from local disk</option>
|
|
|
40 </param>
|
|
|
41
|
|
|
42 <when value="BuiltinSpecies">
|
|
|
43 <param name="buildplant" type="select"
|
|
|
44 label="Species (support for 61 species)"
|
|
|
45 help="">
|
|
|
46 <options from_data_table="ensembl_plant" >
|
|
|
47 <!-- <filter type="sort_by" column="1"/>
|
|
|
48 <validator type="no_options" message="No indexes are available for the selected input dataset"/> -->
|
|
|
49 </options>
|
|
|
50 </param>
|
|
|
51
|
|
|
52 <param name="version" type="select"
|
|
|
53 label="Database version"
|
|
|
54 help="">
|
|
|
55 <options from_data_table="ensembl_plant_version">
|
|
|
56 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
|
57 </options>
|
|
|
58 </param>
|
|
|
59
|
|
|
60 </when>
|
|
|
61
|
|
|
62 <when value="UploadData">
|
|
|
63 <param type="text" name="speciename" value=""
|
|
|
64 label="Species"
|
|
|
65 help="e.g. Arabidopsis thaliana" />
|
|
|
66
|
|
|
67 <param name="genomeData" type="data" format="fasta" optional="true" label="Genome sequences (.fasta)" />
|
|
|
68 <param name="annotationData" type="data" format="gff3" optional="true" label="Annotation file (.gff3)" />
|
|
|
69 <param name="otherrna" type="data" format="fasta" optional="true" label="t/r/sn/snoRNA sequences (.fasta)" />
|
|
|
70 <param name="transcriptsData" type="data" format="fasta" optional="true" label="cDNA sequences (.fasta)" />
|
|
|
71 <param name="proteinsData" type="data" format="fasta" optional="true" label="Optional: Protein sequences (.fasta)" />
|
|
|
72 </when>
|
|
|
73 </conditional>
|
|
|
74 </inputs>
|
|
|
75
|
|
|
76 <stdio><exit_code range="1:" level="fatal" description="Error when running ${tool.name}"/></stdio>
|
|
|
77
|
|
|
78 <outputs>
|
|
|
79 <data format="simple" name="filePath" label="${genometype.speciename.value}">
|
|
|
80 <filter> genometype['datainput'] == "UploadData" </filter>
|
|
|
81 </data>
|
|
|
82 <data format="pdf" name="infout1" label="${genometype.speciename.value} | ${tool.name} | Summary of genomic features">
|
|
|
83 <filter> genometype['datainput'] == "UploadData" </filter>
|
|
|
84 </data>
|
|
|
85 <data format="simple" name="builtinPath" label="${genometype.buildplant.value}_${genometype.version.value}">
|
|
|
86 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
87 </data>
|
|
|
88 <data format="pdf" name="infout2" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Summary of genomic features">
|
|
|
89 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
90 </data>
|
|
|
91 <data format="gz" name="outgenome" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Genome sequences ">
|
|
|
92 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
93 </data>
|
|
|
94 <data format="fasta" name="outtrsnsnoRNA" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | t/r/sn/snoRNA sequences">
|
|
|
95 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
96 </data>
|
|
|
97 <data format="gff3" name="outgff3" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | GFF3 annotations">
|
|
|
98 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
99 </data>
|
|
|
100 <data format="fasta" name="outtranscript" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | cDNA sequences">
|
|
|
101 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
102 </data>
|
|
|
103 <data format="fasta" name="outprotein" label="${genometype.buildplant.value}_${genometype.version.value} | ${tool.name} | Protein sequences">
|
|
|
104 <filter> genometype['datainput'] == "BuiltinSpecies" </filter>
|
|
|
105 </data>
|
|
|
106
|
|
|
107 </outputs>
|
|
|
108
|
|
|
109 <tests>
|
|
|
110 <test>
|
|
|
111 <param name="genomeData" value="Arabidopsis_genome.fa" ftype="fasta" />
|
|
|
112 <param name="annotationData" value="Arabidopsis_annotation.gff3" ftype="fasta" />
|
|
|
113 <output name="filePath" file="genomePrepare: References_of_Arabidopsis_thaliana.simple" ftype="simple" />
|
|
|
114 </test>
|
|
|
115
|
|
|
116 </tests>
|
|
|
117
|
|
|
118
|
|
|
119 <help><![CDATA[
|
|
|
120
|
|
|
121 .. class:: donemark
|
|
|
122
|
|
|
123 **What it does**
|
|
|
124
|
|
|
125 This tool provides two ways for preparing genome data:
|
|
|
126
|
|
|
127 1. Automatically download genomes, annotations, t/r/sn/snoRNAs (i.e. tRNAs, rRNAs, snRNAs, and snoRNAs), cDNAs, and proteins from `EnsemblPlants database`_.
|
|
|
128 2. Upload genomic data for species not included in EnsemblPlants.
|
|
|
129
|
|
|
130 .. class:: infomark
|
|
|
131
|
|
|
132 **Outputs**
|
|
|
133
|
|
|
134 - A file containing the path of formatted genome sequences and annotations. Index files of the reference genome and t/r/sn/snoRNA sequences in this path are used for 'miRNAPredict' analysis.
|
|
|
135 - Summary of the number and length of genomic features.
|
|
|
136 - Genome sequences, annotation file in GFF3 format, t/r/sn/snoRNA sequences, cDNAs, and protein sequences.
|
|
|
137
|
|
|
138 .. _`EnsemblPlants database`: ftp://ftp.ensemblgenomes.org/pub/plants
|
|
|
139
|
|
|
140 |
|
|
|
141
|
|
|
142 ]]></help>
|
|
|
143
|
|
|
144 <citations>
|
|
|
145 <citation type="doi">10.1007/978-1-4939-6658-5_1</citation>
|
|
|
146 </citations>
|
|
|
147
|
|
|
148 </tool>
|
