Mercurial > repos > galaxyp > mzsqlite_psm_align

comparison mzsqlite_psm_align.xml @ 0:f2dc9805107a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mzsqlite_psm_align commit 464e05be1084ed9a65b542c8eabb18147d425666
author galaxyp
date Mon, 16 Apr 2018 18:00:53 -0400
parents
children 4f8cf8fbef57
comparison
equal deleted inserted replaced
-1:000000000000 0:f2dc9805107a
1 <tool id="mzsqlite_psm_align" name="MzSQLite ProBED ProBAM" version="0.1.0">
2 <description>from mz.sqlite aand genomic mapping</description>
3 <requirements>
4 <requirement type="package">biopython</requirement>
5 <requirement type="package">twobitreader</requirement>
6 <requirement type="package">pysam</requirement>
7 <requirement type="package">gffutils</requirement>
8 </requirements>
9 <command detect_errors="exit_code"><![CDATA[
10 #if $readlignments:
11 ln -s -f '${$readlignments}' 'input.bam' &&
12 ln -s -f '${$readlignments.metadata.bam_index}' 'input.bam.bai' &&
13 #end if
14 python '$__tool_directory__/mzsqlite_psm_align.py'
15 #if $ref.ref_source == 'cached':
16 --twobit='$ref.ref_loc.fields.path'
17 #elif $ref.ref_source == 'history':
18 --twobit='$ref.ref_file'
19 #end if
20 #if $gffutilsdb:
21 --gffutils_sqlite '$gffutilsdb'
22 #end if
23 #if $readlignments:
24 --reads_bam 'input.bam'
25 #end if
26 #if 'probed' in str($output_formats).split(','):
27 --probed '$probed'
28 #end if
29 #if 'prosam' in str($output_formats).split(','):
30 --prosam '$prosam'
31 #end if
32 #if 'probam' in str($output_formats).split(','):
33 --probam '$probam'
34 #end if
35 #if $genomicref:
36 --genomeReference $genomicref
37 #else
38 --genomeReference $genomicdb.metadata.dbkey
39 #end if
40 -v
41 '$mzsqlitedb' '$genomicdb'
42 ]]></command>
43 <inputs>
44 <param name="mzsqlitedb" type="data" format="mz.sqlite" label="mz.sqlite databse"/>
45 <param name="genomicdb" type="data" format="sqlite" label="genomic mapping sqlite databse"/>
46 <conditional name="ref">
47 <param name="ref_source" type="select" label="Source for Genomic Sequence Data">
48 <option value="cached">Locally cached twobit</option>
49 <option value="history">History dataset twobit</option>
50 </param>
51 <when value="cached">
52 <param name="ref_loc" type="select" label="Select reference 2bit file">
53 <options from_data_table="twobit" />
54 </param>
55 </when>
56 <when value="history">
57 <param name="ref_file" type="data" format="twobit" label="reference 2bit file" />
58 </when>
59 </conditional>
60 <param name="gffutilsdb" type="data" format="sqlite" label="gffutils sqlite database" optional="true"/>
61 <param name="readlignments" type="data" format="bam" label="read alignments bam" optional="true"/>
62 <param name="genomicref" type="text" value="" label="Genome Reference name" optional="true"/>
63 <param name="output_formats" type="select" display="checkboxes" label="outputs" multiple="true">
64 <option value="probam">pro.bam</option>
65 <option value="prosam">pro.sam</option>
66 <option value="probed">pro.bed</option>
67 </param>
68 </inputs>
69 <outputs>
70 <data name="prosam" format="sam" label="pro.SAM on ${on_string}">
71 <filter>'prosam' in output_formats</filter>
72 </data>
73 <data name="probam" format="bam" label="pro.Bam on ${on_string}">
74 <filter>'probam' in output_formats</filter>
75 </data>
76 <data name="probed" format="bed" label="pro.Bed on ${on_string}">
77 <filter>'probed' in output_formats</filter>
78 </data>
79 </outputs>
80 <help><![CDATA[
81
82 Generates proBAM or proBED feature alignment files for peptides identified from a mass spectrometry protein search analysis.
83
84 The tool mz_to_sqlite generates the a SQLite database for a mzIdentML file,
85 along with the fasta search database and the spectrum files used in the search.
86
87 The genomic mapping sqlite database has this schema:
88
89 CREATE TABLE feature_cds_map ( /* One row for each exon in the search protein */
90 name TEXT, /* Accession name of search protein in mzIdentML */
91 chrom TEXT, /* Reference genome chromosome for this exon */
92 start INTEGER, /* genomic start of the exon (zero-based like BED) */
93 end INTEGER, /* genomic end of the exon (non-incluse like BED) */
94 strand TEXT, /* genomic strand: '+' or '-' */
95 cds_start INTEGER, /* The CDS coding start for this exon (zero-based) */
96 cds_end INTEGER /* The CDS coding start end this exon (non-inclusive) */
97 );
98
99 Example:
100 sqlite> select * from feature_cds_map WHERE name like 'ENSMUSP00000000001%';
101 ENSMUSP00000000001 chr3 108145887 108146005 - 0 118
102 ENSMUSP00000000001 chr3 108123794 108123837 - 118 161
103 ENSMUSP00000000001 chr3 108123541 108123683 - 161 303
104 ENSMUSP00000000001 chr3 108118300 108118458 - 303 461
105 ENSMUSP00000000001 chr3 108115762 108115891 - 461 590
106 ENSMUSP00000000001 chr3 108112472 108112602 - 590 720
107 ENSMUSP00000000001 chr3 108111934 108112088 - 720 874
108 ENSMUSP00000000001 chr3 108109421 108109612 - 874 1065
109
110 This schema can describe structural variants as well as canonical transcripts.
111
112 ]]></help>
113 </tool>