Mercurial > repos > mvdbeek > dedup_hash

comparison dedup_hash.xml @ 0:f33e9e6a6c88 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/mvdbeek/dedup_hash commit 367da560c5924d56c39f91ef9c731e523825424b-dirty
author mvdbeek
date Wed, 23 Nov 2016 07:49:05 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f33e9e6a6c88
1 <tool id="dedup_hash" name="Deduplicate FASTQ files" version="0.1.1">
2 <description>with fast and memory-efficient sequence hashes</description>
3 <requirements>
4 <requirement type="package" version="0.150.1">smhasher</requirement>
5 </requirements>
6 <command><![CDATA[
7 python '$__tool_directory__/dedup_hash/dedup_hash.py'
8 #if str($readtype.single_or_paired) == "se":
9 --r1_in '${readtype.input_single}'
10 --r1_out '$output_single'
11 #elif str($readtype.single_or_paired) == "pe_sep":
12 --r1_in '${readtype.input_paired1}'
13 --r2_in '${readtype.input_paired2}'
14 --r1_out '$output_paired1'
15 --r2_out '$output_paired2'
16 #else
17 --r1_in '${readtype.input_paired.forward}'
18 --r2_in '${readtype.input_paired.reverse}'
19 --r1_out '${output_paired_coll.forward}'
20 --r2_out '${output_paired_coll.reverse}'
21 #end if
22 $compress_fastq
23 ]]></command>
24 <inputs>
25 <conditional name="readtype">
26 <param name="single_or_paired" type="select" label="Single-end or paired-end reads?">
27 <option value="se" selected="true">Single-end</option>
28 <option value="pe_sep">Paired-end (two separate input files)</option>
29 <option value="pe_collection">Paired-end (as collection)</option>
30 </param>
31 <when value="se">
32 <param format="fastq,fastq.gz" name="input_single" type="data" label="Single-end FASTQ reads" help="(-f)" />
33 </when>
34 <when value="pe_sep">
35 <param format="fastq,fastq.gz" name="input_paired1" type="data" label="Paired-end forward strand FASTQ reads" help="(-f)" />
36 <param format="fastq,fastq.gz" name="input_paired2" type="data" label="Paired-end reverse strand FASTQ reads" help="(-r)" />
37 </when>
38 <when value="pe_collection">
39 <param name="input_paired" format="fastq,fastq.gz" type="data_collection" collection_type="paired" label="Paired-end FASTQ reads as paired collection" />
40 </when>
41 </conditional>
42 <param name="compress_fastq" type="boolean" checked="true" truevalue="--write_gzip" falsevalue="" label="Produce compressed fastq?"/>
43 </inputs>
44 <outputs>
45 <data name="output_single" format="fastq" label="Single-end output of ${tool.name} on ${on_string}">
46 <filter>readtype['single_or_paired'] == 'se'</filter>
47 <change_format>
48 <when input="compress_fastq" value="--write_gzip" format="fastq.gz" />
49 </change_format>
50 </data>
51 <data name="output_paired1" format="fastq" label="Paired-end forward strand output of ${tool.name} on ${on_string}">
52 <filter>readtype['single_or_paired'] == 'pe_sep'</filter>
53 <change_format>
54 <when input="compress_fastq" value="--write_gzip" format="fastq.gz" />
55 </change_format>
56 </data>
57 <data name="output_paired2" format="fastq" label="Paired-end reverse strand output of ${tool.name} on ${on_string}">
58 <filter>readtype['single_or_paired'] == 'pe_sep'</filter>
59 <change_format>
60 <when input="compress_fastq" value="--write_gzip" format="fastq.gz" />
61 </change_format>
62 </data>
63 <collection name="output_paired_coll" type="paired" structured_like="readtype.pe_collection" label="Paired-end output of ${tool.name} on ${on_string}">
64 <filter>readtype['single_or_paired'] == 'pe_collection'</filter>
65 <data name="forward" format="fastq">
66 <change_format>
67 <when input="compress_fastq" value="--write_gzip" format="fastq.gz" />
68 </change_format>
69 </data>
70 <data name="reverse" format="fastq">
71 <change_format>
72 <when input="compress_fastq" value="--write_gzip" format="fastq.gz" />
73 </change_format>
74 </data>
75 </collection>
76 </outputs>
77 <tests>
78 <test>
79 <param name="single_or_paired" value="pe_sep"/>
80 <param name="input_paired1" value="r1.fastq.gz" ftype="fastq.gz"/>
81 <param name="input_paired2" value="r2.fastq.gz" ftype="fastq.gz"/>
82 <param name="compress_fastq" value="--write_gzip"/>
83 <output name="output_paired1" file="r1_dedup.fastq.gz" ftype="fastq.gz" compare="sim_size"/>
84 <output name="output_paired2" file="r2_dedup.fastq.gz" ftype="fastq.gz" compare="sim_size"/>
85 </test>
86 <test>
87 <param name="single_or_paired" value="pe_sep"/>
88 <param name="input_paired1" value="r1.fastq" ftype="fastq"/>
89 <param name="input_paired2" value="r2.fastq" ftype="fastq"/>
90 <param name="compress_fastq" value=""/>
91 <output name="output_paired1" file="r1_dedup.fastq" ftype="fastq"/>
92 <output name="output_paired2" file="r2_dedup.fastq" ftype="fastq"/>
93 </test>
94 </tests>
95 <help> <![CDATA[
96 **Deduplicate paired fastq** is a fast and memory-efficient tool for removal of duplicates in paired short DNA sequence reads in fastq format.
97 It identifies duplicates by concatenating the sequence of a readpair and calculating a short hash that uniquely identifies the concatenated sequence.
98 Sequences that are not unique (i.e a hash of the concatenated sequence has been seen previously) are being discarded.
99
100 Compared to fastuniq this tool requires only a fraction of the memory, but does not identify pairs that are identical,
101 except for a switch of R1 and R2. Such reads may nevertheless align to different places based on the seed-searching of the aligner,
102 so this may or may not be a problem for your application.
103
104 Fastuniq consumed 76 GB of memory and took 4:01.52 on a typical dataset of 100nt 25 x 10^6 paired end reads,
105 while this tool took 4.7GB of memory and 3:23.27 for the same dataset.
106
107 Both tools produced the exact same result, arguing that, at least before quality and/or adapter trimming,
108 the previously mentioned limitations are of theoretical concern.
109
110 ]]> </help>
111 <citations>
112 <citation type="doi">doi:10.1371/journal.pone.0052249</citation>
113 </citations>
114 </tool>