Mercurial > repos > jjohnson > mzsqlite_psm_align

comparison mzsqlite_psm_align.xml @ 0:492f98d89e26 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/jj-umn/galaxytools/tree/master/mzsqlite_psm_align commit 88e2fb9c31fbd687a0956924a870137d1fb9bee3-dirty
author jjohnson
date Tue, 10 Apr 2018 09:57:49 -0400
parents
children 46113c737b68
comparison
equal deleted inserted replaced
-1:000000000000 0:492f98d89e26
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 python '$__tool_directory__/mzsqlite_psm_align.py'
11 #if $ref.ref_source == 'cached':
12 --twobit='$ref.ref_loc.fields.path'
13 #elif $ref.ref_source == 'history':
14 --twobit='$ref.ref_file'
15 #end if
16 #if $gffutilsdb:
17 --gffutils_file '$gffutilsdb'
18 #end if
19 #if $readlignments:
20 --reads_bam '$readlignments'
21 #end if
22 #if 'probed' in $output_formats:
23 --probed '$probed'
24 #end if
25 #if 'prosam' in $output_formats:
26 --prosam '$prosam'
27 #end if
28 #if 'probam' in $output_formats:
29 --probam '$probam'
30 #end if
31 #if $genomicref:
32 --genomeReference $genomicref
33 #else
34 --genomeReference $genomicdb.metadata.dbkey
35 #end if
36 '$mzsqlitedb' '$genomicdb'
37 ]]></command>
38 <inputs>
39 <param name="mzsqlitedb" type="data" format="mz.sqlite" label="mz.sqlite databse"/>
40 <param name="genomicdb" type="data" format="mz.sqlite" label="mz.sqlite databse"/>
41 <conditional name="ref">
42 <param name="ref_source" type="select" label="Source for Genomic Sequence Data">
43 <option value="cached">Locally cached twobit</option>
44 <option value="history">History dataset twobit</option>
45 </param>
46 <when value="cached">
47 <param name="ref_loc" type="select" label="Select reference 2bit file">
48 <options from_data_table="twobit" />
49 </param>
50 </when>
51 <when value="history">
52 <param name="ref_file" type="data" format="twobit" label="reference 2bit file" />
53 </when>
54 </conditional>
55 <param name="gffutilsdb" type="data" format="sqlite" label="gffutils sqlite database" optional="true"/>
56 <param name="readlignments" type="data" format="bam" label="read alignments bam" optional="true"/>
57 <param name="genomicref" type="text" value="" label="Genome Reference name" optional="true"/>
58 <param name="output_formats" type="select" display="checkboxes" label="outputs" multiple="true">
59 <option value="probam">pro.bam</option>
60 <option value="prosam">pro.sam</option>
61 <option value="probed">pro.bed</option>
62 </param>
63 </inputs>
64 <outputs>
65 <data name="prosam" format="pro.sam">
66 <filter>'prosam' in output_formats</filter>
67 </data>
68 <data name="probam" format="pro.bam">
69 <filter>'probam' in output_formats</filter>
70 </data>
71 <data name="probed" format="pro.bed">
72 <filter>'probed' in output_formats</filter>
73 </data>
74 </outputs>
75 <help><![CDATA[
76
77 Generates proBAM or proBED feature alignment files for peptides identified from a mass spectrometry protein search analysis.
78
79 The tool mz_to_sqlite generates the a SQLite database for a mzIdentML file,
80 along with the fasta search database and the spectrum files used in the search.
81
82 The genomic mapping sqlite database has this schema:
83
84 CREATE TABLE feature_cds_map ( /* One row for each exon in the search protein */
85 name TEXT, /* Accession name of search protein in mzIdentML */
86 chrom TEXT, /* Reference genome chromosome for this exon */
87 start INTEGER, /* genomic start of the exon (zero-based like BED) */
88 end INTEGER, /* genomic end of the exon (non-incluse like BED) */
89 strand TEXT, /* genomic strand: '+' or '-' */
90 cds_start INTEGER, /* The CDS coding start for this exon (zero-based) */
91 cds_end INTEGER /* The CDS coding start end this exon (non-inclusive) */
92 );
93
94 Example:
95 sqlite> select * from feature_cds_map WHERE name like 'ENSMUSP00000000001%';
96 ENSMUSP00000000001 chr3 108145887 108146005 - 0 118
97 ENSMUSP00000000001 chr3 108123794 108123837 - 118 161
98 ENSMUSP00000000001 chr3 108123541 108123683 - 161 303
99 ENSMUSP00000000001 chr3 108118300 108118458 - 303 461
100 ENSMUSP00000000001 chr3 108115762 108115891 - 461 590
101 ENSMUSP00000000001 chr3 108112472 108112602 - 590 720
102 ENSMUSP00000000001 chr3 108111934 108112088 - 720 874
103 ENSMUSP00000000001 chr3 108109421 108109612 - 874 1065
104
105 This schema can describe structural variants as well as canonical transcripts.
106
107 ]]></help>
108 </tool>