Mercurial > repos > jjohnson > fastq_seq_count

comparison fastq_seq_count.xml @ 0:27c39155d53b draft default tip

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/fastq_seq_count commit 7fcdca778df4012c93cb4aec26c2ff056817afee-dirty"
author jjohnson
date Tue, 26 Oct 2021 14:39:00 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:27c39155d53b
1 <tool id="fastq_seq_count" name="Count sequences in fastq files" version="0.1.1" python_template_version="3.5">
2 <description></description>
3 <requirements>
4 <requirement type="package" version="3.8">python</requirement>
5 </requirements>
6 <command detect_errors="exit_code"><![CDATA[
7 #set $qcol = int(str($query_col))-1
8 python $__tool_directory__/fastq_seq_count.py
9 -p $fastqs_file
10 -i $query_file
11 #if $id_col
12 #set $id_col_list = ','.join([str(int(x)-1) for x in str($id_col).split(',')])
13 -I '$id_col_list'
14 #end if
15 -q $qcol
16 #if $query_label
17 -Q $query_label
18 #end if
19 #if $compare_col
20 #set $ccol = int(str($compare_col))-1
21 -c $ccol
22 #end if
23 #if $compare_label
24 -C $compare_label
25 #end if
26 $reverse_complements
27 -T "\${GALAXY_SLOTS:-4}"
28 $report_fastq_counts
29 -s $report
30 ]]></command>
31 <configfiles>
32 <configfile name="fastqs_file"><![CDATA[#slurp
33 #for $f in $fastqs:
34 #set $line = str($f) + '\t' + $f.element_identifier
35 $line
36 #end for
37 ]]></configfile>
38 </configfiles>
39 <inputs>
40 <param name="fastqs" type="data" format="fastq" multiple="true" label="fastq files to search"/>
41 <param name="query_file" type="data" format="tabular" label="query sequences"/>
42 <param name="id_col" type="data_column" data_ref="query_file" multiple="true" optional="true" numerical="false" label="Identifier column(s)" help="Columns to keep as identifiers for the summary report"/>
43 <param name="query_col" type="data_column" data_ref="query_file" label="query sequence column"/>
44 <param name="query_label" type="text" value="mutant" label="query sequence label"/>
45 <param name="compare_col" type="data_column" data_ref="query_file" optional="true" label="comparison sequence column"/>
46 <param name="compare_label" type="text" value="normal" label="comparison sequence label"/>
47 <param name="reverse_complements" type="boolean" truevalue="-r" falsevalue="" checked="true" label="Also search for reverse complements"/>
48 <param name="report_fastq_counts" type="boolean" truevalue="-n counts" falsevalue="" checked="false" label="report of per fastq counts"/>
49 </inputs>
50 <outputs>
51 <data name="report" format="tabular" label="${tool.name} on ${on_string} summary report"/>
52 <data name="hits" format="tabular" label="${tool.name} on ${on_string} count details" from_work_dir="counts">
53 <filter>report_fastq_counts</filter>
54 </data>
55 </outputs>
56 <tests>
57 <test>
58 <param name="fastqs" ftype="fastq" value="reads1.fastq,reads2.fastq"/>
59 <param name="query_file" ftype="tabular" value="query_seqs.tabular"/>
60 <param name="id_col" value="1,2,3,4,5"/>
61 <param name="query_col" value="4"/>
62 <param name="query_label" value="mutant"/>
63 <param name="compare_col" value="5"/>
64 <param name="compare_label" value="normal"/>
65 <param name="reverse_complements" value="True"/>
66 <param name="report_fastq_counts" value="True"/>
67 <output name="report" ftype="tabular" file="summary_report.out" />
68 <output name="hits" ftype="tabular" file="count_details.out" />
69 </test>
70 </tests>
71 <help><![CDATA[
72 **Report fastq reads that contain sequences**
73
74 This tool searches fastq reads for given nucleic acid query sequences.
75 A typical use would be to compare the relative occurrence of two sequences.
76
77 **NOTE:** This only reports complete matches to the sequences, and reads that may partially match at the ends will not be counted.
78
79 **INPUTS**
80
81 fastq files
82 - the sequence files to search
83
84 query file - a tabular file
85 - that contains a column of "query" sequences to match in fastq reads
86 - it may contain a second "comparison" sequence column to match
87
88 **OUTPUTS**
89
90 summary report - a tabular file
91 - the first column is the line number from the query file
92 - columns from the query file selected as identifiers
93 - the count of fastq entries for the query sequence
94 - the count of fastq entries for the comparison sequence (if selected)
95 - the fraction of query sequence matches compared to the total of query and comparison matches
96
97 count details - an optional tabular file of match count
98 - the fastq name
99 - the first column is the line number from the query file
100 - the sequence that matched
101 - the label of the sequence that matched
102 - the strand that matched
103 - the number reads that matched
104
105 ]]></help>
106 </tool>