Mercurial > repos > bebatut > qiime

comparison split_libraries_fastq.xml @ 0:c1bd0c560018 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/galaxyproject/tools-iuc/tree/master/tools/qiime commit bcbe76277f3e60303faf826f8ce7f018bc663a9a-dirty
author bebatut
date Tue, 02 Feb 2016 05:50:37 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c1bd0c560018
1 <tool id="split_libraries_fastq" name="Split fastq libraries" version="1.9.1">
2 <description>to performs demultiplexing of Fastq sequence data</description>
3
4 <macros>
5 <import>macros.xml</import>
6 </macros>
7
8 <expand macro="requirements" />
9
10 <version_command><![CDATA[
11 split_libraries_fastq.py --version
12 ]]>
13 </version_command>
14
15 <command><![CDATA[
16 split_libraries_fastq.py
17
18 #set $seq_files = ''
19 #set $sep = ''
20 #for $file in $input_fastq_files
21 #set $seq_files += $sep + str($file)
22 #set $sep = ','
23 #end for
24 -i $seq_files
25
26 -o split_libraries
27
28 #set $mapping_files = ''
29 #set $sep = ''
30 #for $file in $input_mapping_files
31 #set $mapping_files += $sep + str($file)
32 #set $sep = ','
33 #end for
34 -m $mapping_files
35
36 #set $barcode_files = ''
37 #set $sep = ''
38 #for $file in $input_files_barcode_read_fps
39 #set $barcode_files += $sep + str($file)
40 #set $sep = ','
41 #end for
42 -b $barcode_files
43
44 $store_qual_scores
45
46 #if str($sample_ids):
47 --sample_ids $sample_ids
48 #end if
49
50 $store_demultiplexed_fastq
51 $retain_unassigned_reads
52 -r $max_bad_run_length
53 -p $min_per_read_length_fraction
54 -n $sequence_max_n
55 -s $start_seq_id
56
57 $rev_comp_barcode
58 $rev_comp_mapping_barcodes
59 $rev_comp
60
61 -q $phred_quality_threshold
62
63 #if str( $barcode_type.barcode_selector ) != "custom_length"
64 --barcode_type $barcode_type.barcode_selector
65 #else
66 --barcode_type $barcode_type.barcode_length
67 #end if
68
69 --max_barcode_errors $max_barcode_errors
70
71 $phred_offset
72 ]]>
73 </command>
74
75 <inputs>
76 <param name="input_fastq_files" type="data"
77 format="fastq,fastqsanger,fastqsolexa"
78 label="Input fastq files" multiple="True" help="(-i/--sequence_read_fps)"/>
79
80 <param name="input_mapping_files" type="data"
81 format="txt,tabular,tsv,csv" label="Metadata mapping files (optional)"
82 multiple="True" optional="True" help="(-m/--mapping_fps)"/>
83
84 <param name="input_files_barcode_read_fps" type="data"
85 format="fastq,fastqsanger,fastqsolexa" label="Barcode read files (optional)"
86 multiple="True" optional="True" help="(-b/--barcode_read_fps)"/>
87
88 <param name="store_qual_scores" type="boolean" label="Store quality strings
89 in files?" truevalue="--store_qual_scores" falsevalue="" checked="False"
90 help="(--store_qual_scores)" />
91
92 <param name="sample_ids" type="text" label="Comma-separated list of samples
93 ids to be applied to all sequences (optional)" optional="True"
94 help="It must be one per input file path (used when data is not
95 multiplexed, --sample_ids)"/>
96
97 <param name="store_demultiplexed_fastq" type="boolean" label="Write
98 demultiplexed fastq files?" truevalue="--store_demultiplexed_fastq"
99 falsevalue="" checked="False" help="(--store_demultiplexed_fastq)" />
100
101 <param name="retain_unassigned_reads" type="boolean" label="Retain
102 sequences which don’t map to a barcode in the mapping file?"
103 truevalue="--retain_unassigned_reads" falsevalue="" checked="False"
104 help="Sample ID will be 'Unassigned' (--retain_unassigned_reads)" />
105
106 <param name="max_bad_run_length" type="integer" value="3"
107 label="Maximum number of consecutive low quality base calls allowed
108 before truncating a read" help="(-r/--max_bad_run_length)" />
109
110 <param name="min_per_read_length_fraction" type="float" value="0.75"
111 label="Minimum number of consecutive high quality base calls to
112 include a read (per single end read) as a fraction of the input read
113 length" help="(-p/--min_per_read_length_fraction)" />
114
115 <param name="sequence_max_n" type="integer" value="0"
116 label="Maximum number of N characters allowed in a sequence to retain
117 it" help="This is applied after quality trimming, and is total over
118 combined paired end reads if applicable (-n/--sequence_max_n)" />
119
120 <param name="start_seq_id" type="integer" value="0"
121 label="Start seq_ids as ascending integers beginning with start_seq_id"
122 help="(-s/--start_seq_id)" />
123
124 <param name="rev_comp_barcode" type="boolean" label="Reverse complement
125 barcode reads before lookup?" truevalue="--rev_comp_barcode"
126 falsevalue="" checked="False" help="(--rev_comp_barcode)" />
127
128 <param name="rev_comp_mapping_barcodes" type="boolean" label="Reverse
129 complement barcode in mapping before lookup?"
130 truevalue="--rev_comp_mapping_barcodes" falsevalue="" checked="False"
131 help="It is useful if barcodes in mapping file are reverse
132 complements of golay codes (--rev_comp_mapping_barcodes)" />
133
134 <param name="rev_comp" type="boolean" label="Reverse omplement sequence
135 before writing to output file?" truevalue="--rev_comp" falsevalue=""
136 checked="False" help="(--rev_comp)" />
137
138 <param name="phred_quality_threshold" type="integer" value="3"
139 label="Maximum unacceptable Phred quality score" help="E.g., for
140 Q20 and better, 19 must be specified (-q/--phred_quality_threshold)" />
141
142 <conditional name="barcode_type">
143 <param name="barcode_selector" type="select" label="Type of barcode"
144 help="(--barcode_type)">
145 <option value="hamming_8">hamming_8</option>
146 <option value="golay_12" selected="true">golay_12</option>
147 <option value="variable_length">variable_length (disable any barcode correction)</option>
148 <option value="custom_length">Custom length</option>
149 <option value="not-barcoded">Data not barcoded</option>
150 </param>
151 <when value="hamming_8" />
152 <when value="golay_12" />
153 <when value="variable_length" />
154 <when value="custom_length">
155 <param name="barcode_length" type="integer" value="4"
156 label="Barcode length"/>
157 </when>
158 <when value="not-barcoded" />
159 </conditional>
160
161 <param name="max_barcode_errors" type="float" value="1.5"
162 label="Maximum number of errors in barcode"
163 help="(--max_barcode_errors)" />
164
165 <param name="phred_offset" type="select" label="Ascii offset to use when
166 decoding phred scores" help="(--phred_offset)">
167 <option value="--phred_offset 33">33</option>
168 <option value="--phred_offset 64">64</option>
169 <option value="" selected="true">Automatically determined</option>
170 </param>
171 </inputs>
172
173 <outputs>
174 <data name="log" format="txt"
175 from_work_dir="split_libraries/split_library_log.txt"
176 label="${tool.name} on ${on_string}: log"/>
177 <data name="histograms" format="tabular"
178 from_work_dir="split_libraries/histograms.txt"
179 label="${tool.name} on ${on_string}: histograms"/>
180 <data name="seqs" format="fasta"
181 from_work_dir="split_libraries/seqs.fna"
182 label="${tool.name} on ${on_string}: sequences"/>
183 <data name="seqs_qual" format="qual"
184 from_work_dir="split_libraries/seqs.qual"
185 label="${tool.name} on ${on_string}: sequence qualities">
186 <filter>store_qual_scores is True</filter>
187 </data>
188 <data name="seqs_fastq" format="fastq"
189 from_work_dir="split_libraries/seqs.fastq"
190 label="${tool.name} on ${on_string}: demultiplexed sequences (fastq)">
191 <filter>store_demultiplexed_fastq is True</filter>
192 </data>
193 </outputs>
194
195 <tests>
196 <test>
197 <param name="input_fastq_files" value="forward_reads.fastq"/>
198 <param name="input_mapping_files" value="map.tsv"/>
199 <param name="input_files_barcode_read_fps" value="barcodes.fastq"/>
200 <param name="store_qual_scores" value="--store_qual_scores" />
201 <param name="store_demultiplexed_fastq" value="--store_demultiplexed_fastq" />
202 <param name="retain_unassigned_reads" value=""/>
203 <param name="max_bad_run_length" value="3"/>
204 <param name="min_per_read_length_fraction" value="0.75"/>
205 <param name="sequence_max_n" value="0"/>
206 <param name="start_seq_id" value="0" />
207 <param name="rev_comp_barcode" value="" />
208 <param name="rev_comp_mapping_barcodes" value="" />
209 <param name="rev_comp" value="" />
210 <param name="start_seq_id" value="3"/>
211 <param name="barcode_selector" value="golay_12"/>
212 <param name="max_barcode_errors" value="1.5"/>
213 <param name="phred_offset" value="" />
214
215 <output name="log" file="split_fastq_libraries_log.txt"/>
216 <output name="seqs" file="split_fastq_libraries_sequences.fasta"/>
217 <output name="histograms" file="split_fastq_libraries_histograms.tabular"/>
218 <output name="histograms" file="split_fastq_libraries_histograms.tabular"/>
219 <output name="seqs_qual" file="split_fastq_libraries_sequence_qualities.qual"/>
220 <output name="seqs_fastq" file="split_fastq_libraries_demultiplexed_sequences.fastq"/>
221 </test>
222 </tests>
223
224 <help><![CDATA[
225
226 **What it does**
227
228 This tool performs demultiplexing of Fastq sequence data where barcodes and sequences are contained in two separate fastq files (common on Illumina runs).
229
230 More information about this tool is available on
231 `QIIME documentation <http://qiime.org/scripts/split_libraries_fastq.html>`_.
232 ]]>
233 </help>
234
235 <citations>
236 <expand macro="citations" />
237 </citations>
238
239 </tool>