Mercurial > repos > rhpvorderman > fast_fastq_filter

comparison fast_fastq_filter.xml @ 1:6ee24ca51829 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/LUMC/fastq-filter/tree/develop/galaxy commit a4a3ab70c61a5ea14719002eb72a34a02b5d89e3"
author rhpvorderman
date Wed, 08 Jun 2022 07:49:43 +0000
parents 5f0d949db99e
children
comparison
equal deleted inserted replaced
0:5f0d949db99e 1:6ee24ca51829
1 <tool id="fast_fastq_filter" name="fastq-filter" version="0.1.0" python_template_version="3.5" profile="16.04"> 1 <tool id="fast_fastq_filter" name="fastq-filter" version="0.3.0" python_template_version="3.5" profile="16.04">
2 <description>filter FASTQ reads fast</description> 2 <description>filter FASTQ reads fast</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.1.0">fastq-filter</requirement> 4 <requirement type="package" version="0.3.0">fastq-filter</requirement>
5 <!-- TODO: Remove this once biocontainer is published --> 5 <!-- TODO: Remove this once biocontainer is published -->
6 <container type="docker">quay.io/rhpvorderman/fastq-filter:0.1.0</container> 6 <container type="docker">quay.io/rhpvorderman/fastq-filter:0.3.0</container>
7 </requirements> 7 </requirements>
8 <command detect_errors="exit_code"><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 #set all_filters = [str(filter['filter']) + ":" + str(filter['filter_threshold']) for filter in $filters] 9 set -e;
10 fastq-filter -o '$output1' 10 fastq-filter
11 #echo "'" + "|".join($all_filters) + "'" 11 #if str($filters.minimum_length.enabled) == "true"
12 '$input1' 12 --min-length $filters.minimum_length.threshold
13 #end if
14 #if str($filters.maximum_length.enabled) == "true"
15 --max-length $filters.maximum_length.threshold
16 #end if
17 #if str($filters.average_error_rate.enabled) == "true"
18 --average-error-rate $filters.average_error_rate.threshold
19 #end if
20 #if str($filters.mean_quality.enabled) == "true"
21 --mean-quality $filters.mean_quality.threshold
22 #end if
23 #if str($filters.median_quality.enabled) == "true"
24 --median-quality $filters.median_quality.threshold
25 #end if
26 --verbose
27 -o '${output1}.gz'
28 #if str($library.type) == "paired":
29 -o ${output2}.gz
30 #end if
31
32 '$library.input_1'
33 #if str($library.type) == "paired":
34 '$library.input_2'
35 #end if
36 ;
37
38 mv '${output1}.gz' '$output1';
39 #if str($library.type) == "paired":
40 mv '${output2}.gz' '$output2';
41 #end if
13 ]]></command> 42 ]]></command>
14 <inputs> 43 <inputs>
15 <param type="data" name="input1" label="Input FASTQ file" format="fastqsanger,fastqsanger.gz" /> 44 <conditional name="library">
16 <repeat name="filters" title="Filter" min="1"> 45 <param name="type" type="select" label="Single-end or Paired-end reads?">
17 <param name="filter" type="select" label="Filter on"> 46 <option value="single">Single-end</option>
18 <option value="min_length">minimum length</option> 47 <option value="paired">Paired-end</option>
19 <option value="max_length">maximum length</option>
20 <option value="mean_quality" selected="true">mean quality</option>
21 <option value="median_quality">median quality</option>
22 </param> 48 </param>
23 <param name="filter_threshold" type="integer" label="Filter threshold" value="20"/> 49 <when value="single">
24 </repeat> 50 <param type="data" name="input_1" label="Input FASTQ file" format="fastqsanger,fastqsanger.gz" />
51 </when>
52 <when value="paired">
53 <param type="data" name="input_1" label="Input FASTQ file #1" format="fastqsanger,fastqsanger.gz" />
54 <param type="data" name="input_2" label="Input FASTQ file #2" format="fastqsanger,fastqsanger.gz" />
55 </when>
56 </conditional>
57 <section name="filters" title="Filters" expanded="true">
58 <conditional name="minimum_length">
59 <param name="enabled" type="boolean" label="Minimum length"
60 help="The minimum length for a read."/>
61 <when value="true">
62 <param name="threshold" type="integer" label="Threshold"
63 value="20" min="1"/>
64 </when>
65 <when value="false"/>
66 </conditional>
67 <conditional name="maximum_length">
68 <param name="enabled" type="boolean" label="Maximum length"
69 help="The maximum length for a read."/>
70 <when value="true">
71 <param name="threshold" type="integer" label="Threshold"
72 value="1000" min="1"/>
73 </when>
74 <when value="false"/>
75 </conditional>
76 <conditional name="average_error_rate">
77 <param name="enabled" type="boolean" label="Average error rate"
78 help="The minimum average per base error rate."/>
79 <when value="true">
80 <param name="threshold" type="float" label="Threshold"
81 value="0.001" min="0"/>
82 </when>
83 <when value="false"/>
84 </conditional>
85 <conditional name="mean_quality">
86 <param name="enabled" type="boolean" label="Mean quality">
87 <help>
88 Average quality. Same as the 'Average error rate' option but
89 specified with a phred score. I.e a mean quality of 30 is
90 equivalent to an average error rate of 0.001'.
91 </help>
92 </param>
93 <when value="true">
94 <param name="threshold" type="integer" label="Threshold"
95 value="30" min="0"/>
96 </when>
97 <when value="false"/>
98 </conditional>
99 <conditional name="median_quality">
100 <param name="enabled" type="boolean" label="Median quality">
101 <help>
102 DEPRECATED: The minimum median phred score. This is not as
103 informative as the average error rate. It is also slower to
104 calculate. This filter is only included for backwards
105 compatibility reasons.
106 </help>
107 </param>
108 <when value="true">
109 <param name="threshold" type="integer" label="Threshold"
110 value="30" min="0"/>
111 </when>
112 <when value="false"/>
113 </conditional>
114 </section>
25 </inputs> 115 </inputs>
26 <outputs> 116 <outputs>
27 <!--Fastqsanger format for now. For conditionally applying fastqsanger.gz the tool needs 117 <data name="output1" format="fastqsanger.gz" />
28 to be updated. An option is using format auto_detect, so we do not have to conditionally set 118 <data name="output2" format="fastqsanger.gz">
29 fastqsanger or fastqsanger.gz--> 119 <filter>library['type'] == 'paired'</filter>
30 <data name="output1" format="fastqsanger" /> 120 </data>
31 <!--When the tool is updated for paired input, the optional paired output can probably be
32 found in the cutadapt wrapper -->
33 </outputs> 121 </outputs>
34 <tests>
35 <test>
36 <param name="input1" value="input.fastq.gz"/>
37 <output name="output1" file="output.fastq.gz"/>
38 </test>
39 </tests>
40 <help><![CDATA[ 122 <help><![CDATA[
41 The following filters are available: 123 When paired FASTQ data is given, fastq-filter makes sure the output is in
124 sync. The filters behave as follows for paired-end data:
42 125
43 + mean_quality:<quality> The mean quality of the FASTQ record is equal or above the given quality value. 126 + average error rate: The average of the combined phred scores is used.
44 + median_quality:<quality> The median quality of the FASTQ record is equal or above the given quality value. 127 + median quality: The median of the combined phred scores is used.
45 + min_length:<length> The length of the sequence in the FASTQ record is at least min_length 128 + Minimum length: at least one of the records of the pair must meet the minimum length.
46 + max_length:<length> The length of the sequence in the FASTQ record is at most max_length 129 + Maximum length: None of the records in the pair must exceed the maximum length.
130
131 The rationale for the length filters is that R1 and R2 both sequence the same
132 molecule and the canonical length is the longest of both.
47 133
48 ]]></help> 134 ]]></help>
49 <citations> 135 <citations>
50 <citation type="bibtex"> 136 <citation type="bibtex">
51 @misc{githubfastq-filter, 137 @misc{githubfastq-filter,