Mercurial > repos > lparsons > cutadapt

comparison cutadapt.xml @ 5:1dada50cca8a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Support for cutadapt 0.9.5, added quality trimming and additional output options
author Lance Parsons <lparsons@princeton.edu>
date Fri, 22 Jul 2011 11:03:00 -0400
parents 0a872e59164c
children 2d6671b10919
comparison
equal deleted inserted replaced
4:0a872e59164c 5:1dada50cca8a
1 <tool id="cutadapt" name="Remove adapter sequences" version="0.9.4"> 1 <tool id="cutadapt" name="Cutadapt" version="0.9.5.a">
2 <description>from high-throughput sequence data</description> 2 <description>Remove adapter sequences from Fastq/Fasta</description>
3 <requirements> 3 <requirements>
4 <requirement type="python-module">cutadapt</requirement> 4 <requirement type="python-module">cutadapt</requirement>
5 </requirements> 5 </requirements>
6 6
7 <command interpreter="sh">discard_stderr_wrapper.sh cutadapt 7 <command>cutadapt
8 #if $input.extension.startswith( "fastq"): 8 #if $input.extension.startswith( "fastq"):
9 --format=fastq 9 --format=fastq
10 #else 10 #else
11 --format=$input.extension 11 --format=$input.extension
12 #end if 12 #end if
13 #for $a in $adapters 13 #for $a in $adapters
14 -a '${a.adapter_source.adapter}' 14 --adapter='${a.adapter_source.adapter}'
15 #end for 15 #end for
16 #for $aa in $anywhere_adapters 16 #for $aa in $anywhere_adapters
17 -b '${aa.anywhere_adapter_source.anywhere_adapter}' 17 --anywhere='${aa.anywhere_adapter_source.anywhere_adapter}'
18 #end for 18 #end for
19 -e $error_rate 19 --error-rate=$error_rate
20 -n $count 20 --times=$count
21 -O $overlap 21 --overlap=$overlap
22 #if str($min) != '0': 22 #if str($min) != '0':
23 -m $min 23 --minimum-length=$min
24 #end if 24 #end if
25 #if str($max) != '0': 25 #if str($max) != '0':
26 -M $max 26 --maximum-length=$max
27 #end if 27 #end if
28 #if $discard: 28 #if str($quality_cutoff) != '0':
29 --discard 29 --quality-cutoff=$quality_cutoff
30 #end if
31 $discard
32 --output='$output'
33 #if str( $output_params.output_type ) == "additional":
34 #if $output_params.rest_file:
35 --rest-file=$rest_output
36 #end if
37 #if $output_params.too_short_file:
38 --too-short-output=$too_short_output
39 #end if
40 #if $output_params.untrimmed_file:
41 --untrimmed-output=$untrimmed_output
42 #end if
30 #end if 43 #end if
31 '$input' 44 '$input'
32 --output='$output'
33 > $report 45 > $report
34 </command> 46 </command>
35 <inputs> 47 <inputs>
36 <param format="fastqsanger, fasta" name="input" type="data" optional="false" label="Fastq file to trim" length="100"/> 48 <param format="fastqsanger, fasta" name="input" type="data" optional="false" label="Fastq file to trim" length="100"/>
37 49
79 </repeat> 91 </repeat>
80 92
81 <param name="error_rate" type="float" min="0" max="1" value="0.1" label="Maximum error rate" help="Maximum allowed error rate (no. of errors divided by the length of the matching region)." /> 93 <param name="error_rate" type="float" min="0" max="1" value="0.1" label="Maximum error rate" help="Maximum allowed error rate (no. of errors divided by the length of the matching region)." />
82 <param name="count" type="integer" min="1" value="1" label="Match times" help="Try to remove adapters at most COUNT times. Useful when an adapter gets appended multiple times." /> 94 <param name="count" type="integer" min="1" value="1" label="Match times" help="Try to remove adapters at most COUNT times. Useful when an adapter gets appended multiple times." />
83 <param name="overlap" type="integer" min="1" value="3" label="Minimum overlap length" help="Minimum overlap length. If the overlap between the adapter and the sequence is shorter than LENGTH, the read is not modified." /> 95 <param name="overlap" type="integer" min="1" value="3" label="Minimum overlap length" help="Minimum overlap length. If the overlap between the adapter and the sequence is shorter than LENGTH, the read is not modified." />
84 <param name="discard" type="boolean" checked="False" default="False" label="Discard Trimmed Reads" help="Discard reads that contain the adapter instead of trimming them. Use the 'Minimum overlap length' option in order to avoid throwing away too many randomly matching reads!" /> 96 <param name="discard" type="boolean" value="false" truevalue="--discard" falsevalue="" label="Discard Trimmed Reads" help="Discard reads that contain the adapter instead of trimming them. Use the 'Minimum overlap length' option in order to avoid throwing away too many randomly matching reads!" />
85 <param name="min" type="integer" min="0" optional="true" value="0" label="Minimum length" help="Discard trimmed reads that are shorter than LENGTH. Reads that are too short even before adapter removal are also discarded. In colorspace, an initial primer is not counted. Value of 0 means no minimum length." /> 97 <param name="min" type="integer" min="0" optional="true" value="0" label="Minimum length" help="Discard trimmed reads that are shorter than LENGTH. Reads that are too short even before adapter removal are also discarded. In colorspace, an initial primer is not counted. Value of 0 means no minimum length." />
86 <param name="max" type="integer" min="0" optional="true" value="0" label="Maximum length" help="Discard trimmed reads that are longer than LENGTH. Reads that are too long even before adapter removal are also discarded. In colorspace, an initial primer is not counted. Value of 0 means no maximum length." /> 98 <param name="max" type="integer" min="0" optional="true" value="0" label="Maximum length" help="Discard trimmed reads that are longer than LENGTH. Reads that are too long even before adapter removal are also discarded. In colorspace, an initial primer is not counted. Value of 0 means no maximum length." />
99 <param name="quality_cutoff" type="integer" min="0" optional="true" value="0" label="Quality cutoff" help="Trim low-quality ends from reads before adapter removal. The algorithm is the same as the one used by BWA (Subtract CUTOFF from all qualities; compute partial sums from all indices to the end of the sequence; cut sequence at the index at which the sum is minimal). Value of 0 means no quality trimming." />
100 <conditional name="output_params">
101 <param name="output_type" type="select" label="Additional output options" help="By default all reads will be put in the same file. However, reads with adapters matching in the middle, unmatched reads, and too-short reads can be saved in separate files.">
102 <option value="default">Default</option>
103 <option value="additional">Additional output files</option>
104 </param>
105 <when value="default" />
106 <when value="additional">
107 <param name="rest_file" type="boolean" value="false" label="Rest of Read" help="When the adapter matches in the middle of a read, write the rest (after the adapter) into a file."/>
108 <param name="too_short_file" type="boolean" value="false" label="Too Short Reads" help="Write reads that are too short (according to minimum length specified) to a file. (default: discard reads)"/>
109 <param name="untrimmed_file" type="boolean" value="false" label="Untrimmed Reads" help="Write reads that do not contain the adapter to a separate file, instead of writing them to the regular output file. (default: output to same file as trimmed)"/>
110 </when>
111 </conditional>
87 </inputs> 112 </inputs>
88 <outputs> 113 <outputs>
89 <data format="txt" name="report" label="${tool.name} on ${on_string} (Report)" /> 114 <data format="txt" name="report" label="${tool.name} on ${on_string} (Report)" />
90 <data format="input" name="output" metadata_source="input"/> 115 <data format="input" name="output" metadata_source="input"/>
116 <data format="input" name="rest_output" metadata_source="input" label="${tool.name} on ${on_string} (Rest of Reads)" >
117 <filter>(output_params['output_type'] == "additional")</filter>
118 <filter>(output_params['rest_file'] is True)</filter>
119 </data>
120 <data format="input" name="too_short_output" metadata_source="input" label="${tool.name} on ${on_string} (Too Short Reads)" >
121 <filter>(output_params['output_type'] == "additional")</filter>
122 <filter>(output_params['too_short_file'] is True)</filter>
123 </data>
124 <data format="input" name="untrimmed_output" metadata_source="input" label="${tool.name} on ${on_string} (Untrimmed Reads)" >
125 <filter>(output_params['output_type'] == "additional")</filter>
126 <filter>(output_params['untrimmed_file'] is True)</filter>
127 </data>
91 </outputs> 128 </outputs>
92 129
93 <tests> 130 <tests>
94 <test> 131 <test>
95 <param name="input" value="fa_gc_content_input.fa"/> 132 <param name="input" value="cutadapt_small.fastq" ftype="fastqsanger"/>
96 <output name="out_file1" file="fa_gc_content_output.txt"/> 133 <param name="adapter_source_list" value="user"/>
134 <param name="adapter" value=""/>
135 <param name="anywhere_adapter_source_list" value="user"/>
136 <param name="anywhere_adapter" value="TTAGACATATCTCCGTCG"/>
137 <param name="output_type" value="default"/>
138 <output name="output" file="cutadapt_small.out"/>
139 </test>
140 <test>
141 <param name="input" value="cutadapt_small.fastq" ftype="fastqsanger"/>
142 <param name="adapter_source_list" value="user"/>
143 <param name="adapter" value="TTAGACATATCTCCGTCG"/>
144 <param name="anywhere_adapter_source_list" value="user"/>
145 <param name="anywhere_adapter" value=""/>
146 <param name="discard" value="true"/>
147 <param name="output_type" value="default"/>
148 <output name="output" file="cutadapt_discard.out"/>
149 </test>
150 <test>
151 <param name="input" value="cutadapt_rest.fa" ftype="fasta"/>
152 <param name="adapter_source_list" value="user"/>
153 <param name="adapter" value="ADAPTER"/>
154 <param name="anywhere_adapter_source_list" value="user"/>
155 <param name="anywhere_adapter" value=""/>
156 <param name="output_type" value="additional"/>
157 <param name="rest_file" value="true"/>
158 <output name="output" file="cutadapt_rest.out"/>
159 <output name="rest_output" file="cutadapt_rest2.out"/>
97 </test> 160 </test>
98 </tests> 161 </tests>
99 162
100 <help> 163 <help>
101 This tool removes adapter sequences from DNA high-throughput 164 This tool removes adapter sequences from DNA high-throughput