annotate filter.xml @ 6:3c50a937d7c1 draft

Uploaded
author bcclaywell
date Wed, 15 Apr 2015 19:14:23 -0400
parents 2d023c621bd0
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
1 <tool id="PHYLO_filter" name="Filter and trim" version="1.2.0">
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
2 <description>sequences</description>
6
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
3 <macros>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
4 <import>macros.xml</import>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
5 </macros>
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
6 <requirements>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
7 <requirement type="package">yapp_env</requirement>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
8 </requirements>
6
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
9 <stdio>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
10 <expand macro="basic_errors"/>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
11 </stdio>
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
12 <version_command>seqmagick --version</version_command>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
13 <command interpreter="bash">
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
14 filter-wrapper.sh ${config}
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
15 </command>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
16 <inputs>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
17 <!-- TODO: can take either fasta+qual or fastq -->
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
18 <param name="plate_id" type="integer" value="1" label="Plate number"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
19 <param name="zone_id" type="integer" value="1" label="Zone number"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
20 <param name="raw_seqs" type="data" format="fasta" label="Unfiltered sequences"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
21 <param name="input_qual" type="data" format="qual" label="Sequence quality data"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
22 <!-- TODO: handle MID format for multi-sample sequencing; see http://qiime.org/scripts/split_libraries.html -->
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
23 <param name="barcodes" type="data" format="csv" label="Barcodes"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
24 <param name="primer" type="text" label="Primer" value="GCGGACTACCVGGGTATCTAAT" area="True" size="1x40"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
25 <param name="min_length" type="integer" min="100" max="1000" value="350" label="Minimum sequence length"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
26 <param name="min_quality" type="integer" min="0" max="63" value="35" label="Minimum mean sequence quality"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
27 <param name="reverse_complement" type="boolean" truevalue="TRUE" falsevalue="FALSE" label="Reads uniformly correspond to negative strands"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
28 </inputs>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
29 <outputs>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
30 <data name="filtered_seqs" format="fasta" label="Filtered sequences"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
31 <data name="filter_report" format="tabular" label="Filtering report"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
32 <data name="filter_details" format="data" label="Filtering details"/>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
33 <data name="split_map" format="csv" label="Read-to-specimen map"/>
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
34 <data name="seq_qual_report" format="html" label="Sequence quality report"/>
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
35 </outputs>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
36 <configfiles>
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
37 <configfile name="plate_json">
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
38 {
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
39 "plate": ${plate_id},
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
40 "name": "Plate ${plate_id}",
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
41 "zones": [
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
42 {
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
43 "zone": ${zone_id},
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
44 "cleaning_stats": "${filter_details}"
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
45 }
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
46 ]
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
47 }
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
48 </configfile>
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
49 <configfile name="config">
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
50 RAW_SEQS="${raw_seqs}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
51 INPUT_QUAL="${input_qual}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
52 BARCODES="${barcodes}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
53 PRIMER="${primer}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
54 MIN_LENGTH="${min_length}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
55 MIN_QUALITY="${min_quality}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
56 REVERSE_COMPLEMENT="${reverse_complement}"
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
57 PLATE_JSON="${plate_json}"
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
58
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
59 FILTERED_SEQS="${filtered_seqs}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
60 FILTER_REPORT="${filter_report}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
61 FILTER_DETAILS="${filter_details}"
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
62 SPLIT_MAP="${split_map}"
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
63 SQR="${seq_qual_report}"
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
64 SQR_DIR="${seq_qual_report.files_path}"
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
65 </configfile>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
66 </configfiles>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
67 <!-- The contents of the help tag is parsed as reStructuredText. Please see
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
68 help-template.rst for examples of commonly-used sections in other Galaxy
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
69 tools. -->
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
70 <help>
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
71
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
72 .. class:: infomark
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
73
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
74 **What it does**
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
75
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
76 This tool truncates and removes sequences that don’t match a set of quality
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
77 criteria, as well as mapping sequence barcodes to specimens. It takes input
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
78 sequences in FASTA format and a quality file, and outputs the filtered
5
2d023c621bd0 Uploaded
bcclaywell
parents: 2
diff changeset
79 sequences as well as a filtering summary and a sequence quality report.
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
80
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
81 The default quality filter settings are:
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
82
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
83 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
84 |parameter |value |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
85 +===========================+======+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
86 |--min-length |350 |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
87 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
88 |--min-mean-quality |35 |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
89 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
90 |--quality-window |30 |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
91 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
92 |--quality-window-prop |0.9 |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
93 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
94 |--quality-window-mean-qual |15 |
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
95 +---------------------------+------+
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
96
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
97 See seqmagick's `quality filter documentation`_ for full explanations of these
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
98 parameters.
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
99
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
100 .. _quality filter documentation: http://fhcrc.github.io/seqmagick/quality_filter.html
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
101
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
102 </help>
6
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
103 <citations>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
104 <expand macro="cite_seqmagick"/>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
105 <expand macro="cite_biopython"/>
3c50a937d7c1 Uploaded
bcclaywell
parents: 5
diff changeset
106 </citations>
2
ce6db18f5fd3 Uploaded
bcclaywell
parents:
diff changeset
107 </tool>