|
0
|
1 <tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.0">
|
|
2
|
2 <description>Loading a VCF file into GEMINI</description>
|
|
0
|
3 <expand macro="requirements" />
|
|
|
4 <expand macro="version_command" />
|
|
|
5 <macros>
|
|
|
6 <import>gemini_macros.xml</import>
|
|
|
7 <token name="@BINARY@">load</token>
|
|
|
8 </macros>
|
|
|
9 <command>
|
|
|
10 <![CDATA[
|
|
15
|
11 ln -s "${ infile }" input.vcf &&
|
|
|
12
|
|
4
|
13 gemini
|
|
5
|
14 --annotation-dir ${annotation_databases.fields.path}
|
|
4
|
15 @BINARY@
|
|
15
|
16 -v input.vcf
|
|
11
|
17 #if str( $annotation_type ) != "None":
|
|
|
18 -t $annotation_type
|
|
|
19 #end if
|
|
0
|
20
|
|
|
21 #if $ped:
|
|
|
22 -p $ped
|
|
|
23 #end if
|
|
|
24
|
|
|
25 $skip_gerp_bp
|
|
|
26 $skip_cadd
|
|
|
27 $skip_gene_tables
|
|
|
28 $no_load_genotypes
|
|
|
29 $no_genotypes
|
|
|
30 $passonly
|
|
|
31 --cores \${GALAXY_SLOTS:-4}
|
|
|
32
|
|
|
33 "${ outfile }"
|
|
|
34 ]]>
|
|
|
35 </command>
|
|
|
36 <expand macro="stdio" />
|
|
|
37 <inputs>
|
|
14
|
38 <param name="infile" type="data" format="vcf" label="VCF file to be loaded in the GEMINI database" help="Only build 37 (aka hg19) of the human genome is supported.">
|
|
|
39 <options>
|
|
|
40 <filter type="add_value" value="hg19" />
|
|
|
41 <filter type="add_value" value="Homo_sapiens_nuHg19_mtrCRS" />
|
|
|
42 <filter type="add_value" value="hg_g1k_v37" />
|
|
|
43 </options>
|
|
|
44 </param>
|
|
0
|
45
|
|
|
46 <param name="annotation_type" type="select" label="The annotations to be used with the input vcf" help="(-t)">
|
|
11
|
47 <option value="None">None (not recommended)</option>
|
|
|
48 <option value="snpEff" selected="True">snpEff annotated VCF file</option>
|
|
0
|
49 <option value="VEP">VEP annotated VCF file</option>
|
|
|
50 </param>
|
|
|
51 <param name="ped" type="data" format="tablar" optional="True" label="Sample information file in PED+ format" help="(-p)" />
|
|
4
|
52 <expand macro="annotation_dir" />
|
|
0
|
53
|
|
|
54 <param name="skip_gerp_bp" type="boolean" truevalue="--skip-gerp-bp" falsevalue="" checked="False"
|
|
|
55 label="Do not load GERP scores at base pair resolution" help="(--skip-gerp-bp)"/>
|
|
|
56
|
|
|
57 <param name="skip_cadd" type="boolean" truevalue="--skip-cadd" falsevalue="" checked="False"
|
|
|
58 label="Do not load CADD scores" help="(--skip-cadd)"/>
|
|
|
59
|
|
|
60 <param name="skip_gene_tables" type="boolean" truevalue="--skip-gene-tables" falsevalue="" checked="False"
|
|
|
61 label="Do not load gene tables" help="(--skip-gene-tables)"/>
|
|
|
62
|
|
|
63 <param name="no_load_genotypes" type="boolean" truevalue="--no-load-genotypes" falsevalue="" checked="False"
|
|
|
64 label="Genotypes exist in the file, but should not be stored" help="(--no-load-genotypes)"/>
|
|
|
65
|
|
|
66 <param name="no_genotypes" type="boolean" truevalue="--no-load-genotypes" falsevalue="" checked="False"
|
|
|
67 label="There are no genotypes in the file" help="e.g. some 1000G VCFs (--no-genotypes)"/>
|
|
|
68
|
|
|
69 <param name="passonly" type="boolean" truevalue="--passonly" falsevalue="" checked="False"
|
|
|
70 label="Keep only variants that pass all filters" help="e.g. some 1000G VCFs (--passonly)"/>
|
|
|
71
|
|
|
72 </inputs>
|
|
|
73 <outputs>
|
|
11
|
74 <data name="outfile" format="gemini.sqlite" />
|
|
0
|
75 </outputs>
|
|
|
76 <tests>
|
|
|
77 <test>
|
|
|
78 </test>
|
|
|
79 </tests>
|
|
|
80 <help>
|
|
|
81 **What it does**
|
|
|
82
|
|
|
83 Before we can use GEMINI to explore genetic variation, we must first load our VCF file into the GEMINI database framework.
|
|
|
84 We expect you to have first annotated the functional consequence of each variant in your VCF using either VEP or snpEff.
|
|
|
85
|
|
|
86 http://gemini.readthedocs.org/en/latest/content/loading.html
|
|
|
87
|
|
|
88 @CITATION@
|
|
|
89 </help>
|
|
|
90 <expand macro="citations"/>
|
|
|
91 </tool>
|