Mercurial > repos > artbio > blastparser_and_hits

comparison BlastParser_and_hits.xml @ 0:9dfb65ebb02e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/blastparser_and_hits commit 48132e5edac97d54804ccbaf620068a5fb800bdc
author artbio
date Sun, 15 Oct 2017 18:43:37 -0400
parents
children 9beb85dba280
comparison
equal deleted inserted replaced
-1:000000000000 0:9dfb65ebb02e
1 <tool id="BlastParser_and_hits" name="Parse blast output and compile hits" version="2.5.0">
2 <description>for virus discovery</description>
3 <requirements></requirements>
4 <command><![CDATA[
5 python '$__tool_directory__'/BlastParser_and_hits.py
6 --sequences '$sequences'
7 --blast '$blast'
8 --tabularOutput '$tabularOutput'
9 --fastaOutput '$fastaOutput'
10 --flanking $flanking
11 --mode $mode
12 ## Additional parameters.
13 #if $additional_filters.use_filters == "yes":
14 --filter_relativeCov $additional_filters.filter_relativeCov
15 --filter_maxScore $additional_filters.filter_maxScore
16 --filter_meanScore $additional_filters.filter_meanScore
17 --filter_term_in "$additional_filters.filter_term_in"
18 --filter_term_out "$additional_filters.filter_term_out"
19 #end if
20 --al_sequences '$al_sequences'
21 --un_sequences '$un_sequences'
22 --dataset_name "$blast.element_identifier"
23
24 ]]></command>
25 <inputs>
26 <param name="sequences" type="data" format="fasta" label="fasta sequences that have been blasted" />
27 <param name="blast" type="data" format="tabular" label="The blast output you wish to parse">
28 <validator type="expression" message="Blast file must have 13 columns">value.metadata.columns == 13</validator>
29 </param>
30 <param name="flanking" type="integer" value= "5" label="Number of flanking nucleotides to add to hits for CAP3 assembly"/>
31 <param name="mode" type="select" label="Extensive or compact reporting mode" help="display (extensive) or not (compact) the oases contigs">
32 <option value="verbose" selected="true">extensive</option>
33 <option value="short">compact</option>
34 </param>
35 <conditional name="additional_filters">
36 <param name="use_filters" type="select" label="Use Additional Filters?">
37 <option value="no">No</option>
38 <option value="yes">Yes</option>
39 </param>
40 <when value="no">
41 </when>
42 <when value="yes">
43 <param name="filter_relativeCov" type="float" value="0" max="1" label="Minimum Relative Subject Coverage" help=""/>
44 <param name="filter_maxScore" type="float" value="0" label="Minimum maximum BitScore" help=""/>
45 <param name="filter_meanScore" type="float" value="0" label="Minimum mean BitScore" help=""/>
46 <param name="filter_term_in" type="text" value="" label="filter the subject list with a keyword" help=""/>
47 <param name="filter_term_out" type="text" value="" label="filter the subject list excluding a keyword" help=""/>
48 </when>
49 </conditional>
50 </inputs>
51 <outputs>
52 <data name="tabularOutput" format="tabular" label="blast analysis, by subjects"/>
53 <data name="fastaOutput" format="fasta" label="hits"/>
54 <data name="al_sequences" format="fasta" label="Blast aligned sequences"/>
55 <data name="un_sequences" format="fasta" label="Blast unaligned sequences"/>
56 </outputs>
57
58 <tests>
59 <test>
60 <param ftype="fasta" name="sequences" value="input.fa" />
61 <param ftype="tabular" name="blast" value="blast.tab" />
62 <param name="flanking" value="5" />
63 <param name="use_filters" value="no" />
64 <param name="mode" value="verbose" />
65 <output name="tabularOutput" ftype="tabular" file="output.tab" />
66 <output name="fastaOutput" ftype="fasta" file="output.fa" />
67 <output name="al_sequences" ftype="fasta" file="al_sequences.fa" />
68 <output name="un_sequences" ftype="fasta" file="un_sequences.fa" />
69 </test>
70 </tests>
71
72 <help>
73
74 **What it does**
75
76 Parse blast output for viruses genome assembly.
77
78 Takes as inputs
79
80 - 1. the fasta sequences that have been submitted to blast
81 - 2. a blast alignment in a tabular format. **Importantly** this tabular output must contains the 12 standard columns (see blast documentation), **plus a column 13** that will report the length of the subject sequence (slen). When you use blast tools prior using this tool, remember to **check the appropriate box** to get the 13th column in the blast tabular output.
82 - 3. the numbers of flanking nucleotides to be recovered at the ends of blast hit sequences
83
84 The tool returns 4 datasets
85
86 - 1. the fasta input sequences that produced significant blast hits
87 - 2. the fasta sequences that did not produced significant blast hits
88 - 3. the sequences of the blast hits, plus the flanking sequences (as specified in the tool form). This dataset may be further used in metavisitor workflows to produce contigs of hits.
89 - 4. and the parsing of the blast alignments which summarizes the blast results by "subject" sequences (blast analysis, by subjects)
90
91 This latter parsing dataset may be customized by tuning the reporting mode and/or using filters
92
93 </help>
94 </tool>