Mercurial > repos > iracooke > protk_proteogenomics

comparison protxml_to_gff.xml @ 2:68d8c9e521d7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/iracooke/protk-galaxytools/blob/master/protk-proteogenomics/.shed.yml commit 24e0fef2496984648a8a5cd5bff4d6b9b634a302-dirty
author iracooke
date Tue, 20 Oct 2015 20:34:50 -0400
parents 28067ed4ea0e
children
comparison
equal deleted inserted replaced
1:a85c8de9630a 2:68d8c9e521d7
1 <tool id="protxml_to_gff" name="Proteomics to GFF" version="1.1.0"> 1 <tool id="protxml_to_gff" name="Proteomics to GFF" version="1.1.0">
2 <description>Export Proteomics Data to GFF</description> 2 <description>Export Proteomics Data to GFF</description>
3 <requirements>
4 <container type="docker">iracooke/protk-1.4.3</container>
5 <requirement type="package" version="1.4.3">protk</requirement>
6 <requirement type="package" version="2.2.29">blast+</requirement>
7 </requirements>
8 <stdio>
9 <exit_code range="1:" level="fatal" description="Failure" />
10 </stdio>
11 <command>
12 protxml_to_gff.rb $protxml_file
13 #if $database.source_select=="built_in":
14 -d $database.dbkey
15 #else
16 -d $database.fasta_file
17 #end if
18 -c $gene_file
19 #if str( $gffidpattern ):
20 --gff-idregex='$gffidpattern'
21 #end if
3 22
4 <requirements> 23 #if str( $genomeidpattern ):
5 <container type="docker">iracooke/protk-1.4.1</container> 24 --genome-idregex='$genomeidpattern'
6 <requirement type="package" version="1.4">protk</requirement> 25 #end if
7 <requirement type="package" version="2.2.29">blast+</requirement>
8 </requirements>
9 26
10 <command> 27 #if str( $ignorepattern ):
11 protxml_to_gff.rb $protxml_file 28 --ignore-regex='$ignorepattern'
12 29 #end if
13 #if $database.source_select=="built_in": 30
14 -d $database.dbkey 31 --threshold=$peptide_threshold
15 #else 32 --prot-threshold=$prot_threshold
16 -d $database.fasta_file 33 $stack_charges
17 #end if 34 -o $output
35 </command>
36 <inputs>
37 <conditional name="database">
38 <param name="source_select" type="select" label="Database source used for Proteomics Searches" help="Database should be an amino acid fasta file with entry id's that can be parsed to obtain contig or scaffold ids referenced in your gff file">
39 <option value="input_ref">Your Upload File</option>
40 <option value="built_in">Built-In</option>
41 </param>
42 <when value="built_in">
43 <param name="dbkey" type="select" format="text" >
44 <label>Database</label>
45 <options from_file="pepxml_databases.loc">
46 <column name="name" index="0" />
47 <column name="value" index="2" />
48 </options>
49 </param>
50 </when>
51 <when value="input_ref">
52 <param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" />
53 </when>
54 </conditional>
55 <param name="protxml_file" type="data" format="protxml" multiple="false" label="Proteomics Search Results" help="A ProtXML file produced by Protein Prophet"/>
56 <param name="gene_file" type="data" format="gff3" multiple="false" label="Protein coordinates" help="A gff3 file with coordinates for all protein entries used for proteomics searches. Coordinates should correspond to entries in the genome fasta file"/>
57 <param name="peptide_threshold" label="Peptide Probability Threshold" type="float" value="0.95" min="0" max="1" help="Only peptides within accepted proteins and passing this threshold will appear in the output"/>
58 <param name="prot_threshold" label="Protein Probability Threshold" type="float" value="0.99" min="0" max="1" help="Only peptides within proteins passing this threshold will appear in the output"/>
59 <param name="stack_charges" value="false" type="boolean" label="Peptides with different charges get separate gff entries" help="" truevalue="--stack-charge-states" falsevalue="" />
60 <param name="gffidpattern" size="40" type="text" value="lcl\|([^ ]*)" label="gff id regex" help="Regex with capture group for parsing gff ids from protein ids">
61 <sanitizer>
62 <valid initial="string.printable">
63 <remove value="&apos;"/>
64 </valid>
65 <mapping initial="none">
66 <add source="&apos;" target="__sq__"/>
67 </mapping>
68 </sanitizer>
69 </param>
18 70
19 -c $gene_file 71 <param name="genomeidpattern" size="40" type="text" label="genome id regex" help="Regex with capture group for parsing genomic ids from protein ids">
72 <sanitizer>
73 <valid initial="string.printable">
74 <remove value="&apos;"/>
75 </valid>
76 <mapping initial="none">
77 <add source="&apos;" target="__sq__"/>
78 </mapping>
79 </sanitizer>
80 </param>
20 81
21 --gff-idregex='$gffidpattern' 82 <param name="ignorepattern" size="40" type="text" label="ignore regex" help="Regex to match protein ids that we should ignore completely">
22 83 <sanitizer>
23 -o $output 84 <valid initial="string.printable">
85 <remove value="&apos;"/>
86 </valid>
87 <mapping initial="none">
88 <add source="&apos;" target="__sq__"/>
89 </mapping>
90 </sanitizer>
91 </param>
24 92
25 93
26 </command>
27 94
28 <stdio> 95 </inputs>
29 <exit_code range="1:" level="fatal" description="Failure" /> 96 <outputs>
30 </stdio> 97 <data format="gff3" name="output" />
98 </outputs>
99 <tests>
100 <test>
101 <param name="source_select" value="input_ref"/>
102 <param name="fasta_file" value="small_prot.fasta" format="fasta"/>
31 103
32 <inputs> 104 <param name="protxml_file" value="small.prot.xml" format="protxml"/>
33 <conditional name="database"> 105 <param name="gene_file" value="small_combined.gff" format="gff3"/>
34 <param name="source_select" type="select" label="Database source used for Proteomics Searches" help="Database should be an amino acid fasta file with entry id's that can be parsed to obtain contig or scaffold ids referenced in your gff file"> 106 <output name="output" format="gff3">
35 <option value="input_ref">Your Upload File</option> 107 <assert_contents>
36 <option value="built_in">Built-In</option> 108 <has_text text="polypeptide" />
37 </param> 109 </assert_contents>
38 <when value="built_in"> 110 </output>
39 <param name="dbkey" type="select" format="text" > 111 </test>
40 <label>Database</label> 112 </tests>
41 <options from_file="pepxml_databases.loc"> 113 <help>
42 <column name="name" index="0" />
43 <column name="value" index="2" />
44 </options>
45 </param>
46 </when>
47 <when value="input_ref">
48 <param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" />
49 </when>
50 </conditional>
51
52 <param name="protxml_file" type="data" format="protxml" multiple="false" label="Proteomics Search Results" help="A ProtXML file produced by Protein Prophet"/>
53
54 <param name="gene_file" type="data" format="gff3" multiple="false" label="Protein coordinates" help="A gff3 file with coordinates for all protein entries used for proteomics searches. Coordinates should correspond to entries in the genome fasta file"/>
55
56 <param name="gffidpattern" size="40" type="text" value="lcl\|([^ ]*)" label="gff id regex" help="Regex with capture group for parsing gff ids from protein ids">
57 <sanitizer>
58 <valid initial="string.printable">
59 <remove value="&apos;"/>
60 </valid>
61 <mapping initial="none">
62 <add source="&apos;" target="__sq__"/>
63 </mapping>
64 </sanitizer>
65 </param>
66
67 </inputs>
68
69 <outputs>
70 <data format="gff3" name="output" />
71 </outputs>
72
73
74 <tests>
75 <test>
76 <param name="source_select" value="input_ref"/>
77 <param name="fasta_file" value="small_prot.fasta" format="fasta"/>
78
79 <param name="protxml_file" value="small.prot.xml" format="protxml"/>
80 <param name="gene_file" value="small_combined.gff" format="gff3"/>
81 <output name="output" format="gff3">
82 <assert_contents>
83 <has_text text="polypeptide" />
84 </assert_contents>
85 </output>
86 </test>
87 </tests>
88
89 <help>
90 114
91 **What it does** 115 **What it does**
92 116
93 Exports peptides and proteins to gff 117 Exports peptides and proteins to gff
94 118
95 ---- 119 </help>
96
97 **References**
98
99
100 </help>
101
102 </tool> 120 </tool>