annotate tools/dbbuilder.xml @ 4:b39347891609 draft

Uploaded
author galaxyp
date Fri, 26 Sep 2014 14:31:06 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
4
b39347891609 Uploaded
galaxyp
parents:
diff changeset
1 <tool id="dbbuilder" version="0.2.0" name="Protein Database Downloader">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
2 <description>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
3 </description>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
4 <requirements>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
5 <requirement type="binary">wget</requirement>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
6 </requirements>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
7 <stdio>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
8 <exit_code range="1:" level="fatal" description="Error downloading database." />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
9 <regex match="ERROR" level="fatal" source="stderr" description="Error downloading database." />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
10 </stdio>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
11 <!-- TODO: escape quotes. -->
b39347891609 Uploaded
galaxyp
parents:
diff changeset
12 <!-- Add NCBI and maxquant contaminants. -->
b39347891609 Uploaded
galaxyp
parents:
diff changeset
13 <!-- http://maxquant.org/contaminants.zip -->
b39347891609 Uploaded
galaxyp
parents:
diff changeset
14 <!-- ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.protein.faa.gz-->
b39347891609 Uploaded
galaxyp
parents:
diff changeset
15 <command>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
16 #if $source.from == "uniprot"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
17 #set $url = "http://www.uniprot.org/uniprot/?query=taxonomy%3a%22" + str($source.taxon) + "%22" + str($source.set) + str($source.reviewed) + "&amp;force=yes&amp;format=fasta" + str($source.include_isoform)
b39347891609 Uploaded
galaxyp
parents:
diff changeset
18 #set $type = "direct"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
19 #elif $source.from == "cRAP"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
20 #set $url = "ftp://ftp.thegpm.org/fasta/cRAP/crap.fasta"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
21 #set $type = "direct"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
22 #elif $source.from == "url"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
23 #set $url = $source.url
b39347891609 Uploaded
galaxyp
parents:
diff changeset
24 #set $type = "direct"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
25 #end if
b39347891609 Uploaded
galaxyp
parents:
diff changeset
26 #if $type =="direct"
b39347891609 Uploaded
galaxyp
parents:
diff changeset
27 wget -nv '$url' -O '${output_database}'
b39347891609 Uploaded
galaxyp
parents:
diff changeset
28 #end if
b39347891609 Uploaded
galaxyp
parents:
diff changeset
29 </command>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
30 <inputs>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
31 <conditional name="source">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
32 <param name="from" type="select" label="Download from" help="select database source. cRAP acts as a database for common MS contaminants. UniProtKB is a corss species collection of functional protein databases">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
33 <option value="uniprot">UniProtKB</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
34 <option value="cRAP">cRAP (contaminants)</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
35 <option value="url">Custom URL</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
36 </param>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
37 <when value="uniprot">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
38 <param name="taxon" type="select" format="text" help="select species for protein database">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
39 <label>Taxonomy</label>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
40 <options from_file="uniprot_taxons.loc">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
41 <column name="name" index="0" />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
42 <column name="value" index="1" />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
43 </options>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
44 </param>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
45 <param name="reviewed" type="select" help="UniProtKB/TrEMBL (unreviewed)is a large, automatically annotated database- may contain redundant sequences, but there is a higher chance peptides will be identified. UniProtKB/Swiss-Prot (reviewed) is a smaller, manually annotated database- less of a chance peptides will be identified but less sequence redundancy">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
46 <option value="+">UniProtKB</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
47 <option value="+reviewed%3Ayes">UniProtKB/Swiss-Prot (reviewed only)</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
48 <option value="+reviewed%3Ano">UniProtKB/TrEMBL (unreviewed only)</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
49 <sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
50 <valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
51 <add value="%"/>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
52 </valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
53 </sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
54 </param>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
55 <param name="set" type="select" label="Proteome Set">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
56 <option value="+">Any</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
57 <option value="+keyword%3a1185" selected="true">Reference Proteome Set</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
58 <option value="+keyword%3a181">Complete Proteome Set</option>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
59 <sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
60 <valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
61 <add value="%"/>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
62 </valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
63 </sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
64 </param>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
65 <param name="include_isoform" type="boolean" truevalue="&amp;include=yes" falsevalue="" label="Include isoform data" help="several different forms of a given protein are incorporated into database" />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
66 </when>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
67 <when value="cRAP" />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
68 <when value="url">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
69 <param name="url" value="" type="text" label="URL (http, ftp)">
b39347891609 Uploaded
galaxyp
parents:
diff changeset
70 <sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
71 <valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
72 <add value="%"/>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
73 </valid>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
74 </sanitizer>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
75 </param>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
76 </when>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
77 </conditional>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
78 </inputs>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
79 <outputs>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
80 <data format="fasta" name="output_database" label="Protein Database" />
b39347891609 Uploaded
galaxyp
parents:
diff changeset
81 </outputs>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
82 <help>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
83 **Output**
b39347891609 Uploaded
galaxyp
parents:
diff changeset
84
b39347891609 Uploaded
galaxyp
parents:
diff changeset
85 Creates a FASTA file of specified protein sequences for comparison with experimental MS/MS data in search algorithm.
b39347891609 Uploaded
galaxyp
parents:
diff changeset
86
b39347891609 Uploaded
galaxyp
parents:
diff changeset
87 **External Links**
b39347891609 Uploaded
galaxyp
parents:
diff changeset
88
b39347891609 Uploaded
galaxyp
parents:
diff changeset
89 _Galaxy-P 101 shows usage Protein Database Downloader tool in the creation of a workflow
b39347891609 Uploaded
galaxyp
parents:
diff changeset
90 .. _Galaxy-P 101: http://msi-galaxy-p.readthedocs.org/en/latest/sections/galaxyp_101.html
b39347891609 Uploaded
galaxyp
parents:
diff changeset
91 _UniProtKB provides additional information about the UniProt Knowledgebase
b39347891609 Uploaded
galaxyp
parents:
diff changeset
92 .. _UniProtKB: http://www.uniprot.org/help/uniprotkb
b39347891609 Uploaded
galaxyp
parents:
diff changeset
93 </help>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
94 </tool>
b39347891609 Uploaded
galaxyp
parents:
diff changeset
95