Mercurial > repos > iuc > stacks2_procrad

comparison stacks_procrad.xml @ 0:9993234400f1 draft

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/stacks2 commit b395fa36fa826e26085820ba3a9faacaeddcb460
author iuc
date Mon, 01 Jul 2019 11:00:33 -0400
parents
children ca7aa77c7f57
comparison
equal deleted inserted replaced
-1:000000000000 0:9993234400f1
1 <tool id="stacks2_procrad" name="Stacks2: process radtags" profile="@PROFILE@" version="@STACKS_VERSION@+galaxy@WRAPPER_VERSION@">
2 <description>the Stacks demultiplexing script</description>
3 <macros>
4 <import>macros.xml</import>
5 <import>macros_process.xml</import>
6 </macros>
7 <expand macro="requirements"/>
8 <expand macro="version_cmd"/>
9 <command detect_errors="aggressive"><![CDATA[
10 @FASTQ_INPUT_FUNCTIONS@
11 mkdir stacks_inputs stacks_outputs &&
12
13 #set ($link_command, $inputype) = $fastq_input_nonbatch( $input_type.fqinputs, $input_type.input_type_select, "_R%d_0" )
14 $link_command
15
16 process_radtags
17
18 @PROCESS_IOOPTIONS@
19 @PROCESS_FILTER@
20 @COMMON_ADVANCED@
21 @RESCUE_BARCODE@
22 @PROCESS_ADAPTER@
23
24 ## -E not implemented in Galaxy defaults to phred33
25
26 ## Restriction enzyme options
27 #if str($options_enzyme.enzyme) != '':
28 -e $options_enzyme.enzyme
29 #end if
30 #if str( $options_enzyme.options_enzyme_selector ) == "2" and str($options_enzyme.enzyme2)!='':
31 --renz_2 $options_enzyme.enzyme2
32 #end if
33
34 ## advanced options not shared between shortreads and radtags
35 $options_advanced.bestrad
36 $options_advanced.disable_rad_check
37
38 ## Output options
39 ## --merge not implemented in Galaxy
40 #if $output_log
41 && mv stacks_outputs/process_radtags.stacks_inputs.log $output_log
42 #end if
43 @PROCESS_FASTQ_POSTPROC@
44 ]]></command>
45
46 <inputs>
47 <expand macro="fastq_input_bc_file" multiple="true" listtype="list:paired"/>
48 <conditional name="options_enzyme">
49 <param name="options_enzyme_selector" type="select" label="Number of enzymes">
50 <option value="1">One</option>
51 <option value="2">Two</option>
52 </param>
53 <when value="1">
54 <param name="enzyme" type="select" label="Enzyme" argument="-e" help="provide the restriction enzyme used" >
55 <expand macro="enzymes"/>
56 </param>
57 </when>
58 <when value="2">
59 <param name="enzyme" type="select" label="Enzyme" argument="-e" help="provide the restriction enzyme used" >
60 <expand macro="enzymes"/>
61 </param>
62 <param name="enzyme2" type="select" label="Second enzyme" argument="--renz_2" help="provide the second restriction enzyme used" >
63 <expand macro="enzymes"/>
64 </param>
65 </when>
66 </conditional>
67
68 <section name="options_advanced" title="advanced options" expanded="False">
69 <expand macro="common_advanced"/>
70 <param argument="--bestrad" type="boolean" checked="false" truevalue="--bestrad" falsevalue="" label="Library was generated using BestRAD, check for restriction enzyme on either read and potentially tranpose reads" />
71 <param argument="--disable_rad_check" type="boolean" checked="false" truevalue="--disable_rad_check" falsevalue="" label="Disable checking if the RAD site is intact" />
72 <expand macro="rescue_barcode"/>
73 <expand macro="process_adapter"/>
74 </section>
75
76 <expand macro="process_filter"/>
77 <expand macro="process_output_types"/>
78 <expand macro="in_log"/>
79 </inputs>
80
81 <outputs>
82 <expand macro="out_log"/>
83 <expand macro="process_outputs"/>
84 </outputs>
85 <tests>
86 <!-- single single ended input, no filtering (hence no capturing) + log -->
87 <test>
88 <param name="input_type|input_type_select" value="single"/>
89 <param name="input_type|fqinputs" ftype="fastqsanger" value="procrad/R1.fq"/>
90 <param name="input_type|barcode_encoding" value="--inline_null"/>
91 <param name="barcode" value="procrad/barcodes"/>
92 <param name="options_enzyme|options_enzyme_selector" value="1"/>
93 <param name="options_enzyme|enzyme" value="ecoRI"/>
94 <param name="add_log" value="yes" />
95 <output name="output_log" file="procrad/process_radtags.out" lines_diff="4"/>
96 <output_collection name="demultiplexed" count="40">
97 <element name="PopA_01" file="demultiplexed/PopA_01.fq" ftype="fastqsanger" />
98 </output_collection>
99 </test>
100 <!-- multiple (zipped) single end input (misusing R2 as add single end read file),
101 discarding by quality and capturing them -->
102 <test>
103 <param name="input_type|input_type_select" value="single"/>
104 <param name="input_type|fqinputs" ftype="fastqsanger.gz" value="procrad/R1.fq.gzip,procrad/R2.fq.gzip"/>
105 <param name="input_type|barcode_encoding" value="--inline_null"/>
106 <param name="barcode" value="procrad/barcodes"/>
107 <param name="options_enzyme|options_enzyme_selector" value="1"/>
108 <param name="options_enzyme|enzyme" value="ecoRI"/>
109 <param name="filter_cond|filter_select" value="yes"/>
110 <param name="filter_cond|discard" value="true"/>
111 <param name="filter_cond|sliding" value="0.1" />
112 <param name="filter_cond|score" value="11" />
113 <param name="filter_cond|remove" value="-c" />
114 <param name="filter_cond|filter_illumina" value="--filter_illumina" />
115 <param name="capture" value="true"/>
116 <param name="outype" value="gzfastq"/>
117 <assert_command>
118 <has_text text="-q" />
119 <has_text text="-w 0.1" />
120 <has_text text="-s 11" />
121 <has_text text="-c" />
122 <has_text text="--filter_illumina" />
123 </assert_command>
124 <output_collection name="demultiplexed" count="40">
125 <element name="PopA_01" ftype="fastqsanger.gz" md5="c7250f50138cbca747b85223aaae9565"/>
126 </output_collection>
127 <output_collection name="discarded" count="2">
128 <element name="R1" file="procrad/R1.fq.discards" ftype="fastqsanger"/>
129 <element name="R2" file="procrad/R2.fq.discards" ftype="fastqsanger"/>
130 </output_collection>
131 </test>
132 <!-- paired input, no quality but length filter, gzfasta output -->
133 <test>
134 <param name="input_type|input_type_select" value="paired"/>
135 <param name="input_type|fqinputs">
136 <collection type="list:paired">
137 <element name="reads">
138 <collection type="paired">
139 <element name="forward" value="procrad/R1.fq" ftype="fastqsanger" />
140 <element name="reverse" value="procrad/R2.fq" ftype="fastqsanger"/>
141 </collection>
142 </element>
143 </collection>
144 </param>
145 <param name="barcode" value="procrad/barcodes"/>
146 <param name="options_enzyme|options_enzyme_selector" value="1"/>
147 <param name="options_enzyme|enzyme" value="ecoRI"/>
148 <param name="filter_cond|filter_select" value="no"/>
149 <param name="filter_cond|len_limit" value="50"/>
150 <param name="capture" value="true"/>
151 <param name="outype" value="gzfasta"/>
152 <param name="add_log" value="yes" />
153 <output name="output_log" file="procrad/process_radtags_paired.out" lines_diff="4"/>
154 <assert_command>
155 <has_text text="--len_limit 50" />
156 </assert_command>
157 <output_collection name="demultiplexed_paired" type="list:paired" count="40">
158 <element name="PopA_01">
159 <element name="forward" value="demultiplexed/PopA_01.1.fa.gz" ftype="fasta.gz" />
160 <element name="reverse" value="demultiplexed/PopA_01.2.fa.gz" ftype="fasta.gz" />
161 </element>
162 </output_collection>
163 <output_collection name="remaining" type="list:paired" count="40">
164 <element name="PopA_01">
165 <element name="forward" file="demultiplexed/PopA_01.rem.1.fa.gz" ftype="fasta.gz"/>
166 <element name="reverse" file="demultiplexed/PopA_01.rem.2.fa.gz" ftype="fasta.gz"/>
167 </element>
168 </output_collection>
169 <output_collection name="discarded_paired" type="list:paired" count="1">
170 <element name="reads">
171 <element name="forward" file="procrad/R1.fa.discards" ftype="fasta"/>
172 <element name="reverse" file="procrad/R2.fa.discards" ftype="fasta"/>
173 </element>
174 </output_collection>
175 </test>
176 <!-- paired input (gzipped) + advanced options + two enzymes, fasta output -->
177 <test>
178 <param name="input_type|input_type_select" value="paired"/>
179 <param name="input_type|fqinputs">
180 <collection type="list:paired">
181 <element name="reads">
182 <collection type="paired">
183 <element name="forward" value="procrad/R1.fq.gzip" ftype="fastqsanger.gz" />
184 <element name="reverse" value="procrad/R2.fq.gzip" ftype="fastqsanger.gz"/>
185 </collection>
186 </element>
187 </collection>
188 </param>
189 <param name="barcode" value="procrad/barcodes"/>
190 <param name="options_enzyme|options_enzyme_selector" value="2"/>
191 <param name="options_enzyme|enzyme" value="ecoRI"/>
192 <param name="options_enzyme|enzyme2" value="ecoRI"/>
193 <param name="options_advanced|truncate" value="70" />
194 <param name="options_advanced|rescue_cond|rescue" value="-r"/>
195 <param name="options_advanced|rescue_cond|barcode_dist_1" value="2" />
196 <param name="options_advanced|rescue_cond|barcode_dist_2" value="2" />
197 <param name="options_advanced|bestrad" value="--bestrad" />
198 <param name="options_advanced|retain_header" value="true"/>
199 <param name="options_advanced|disable_rad_check" value="--disable_rad_check" />
200 <param name="options_advanced|adapter_1" value="" />
201 <param name="options_advanced|adapter_2" value="" />
202 <param name="options_advanced|adapter_mm" value="" />
203 <param name="outype" value="fasta"/>
204 <assert_command>
205 <has_text text="-e ecoRI" />
206 <has_text text="--renz_2 ecoRI" />
207 <has_text text="-t 70" />
208 <has_text text="-r" />
209 <has_text text="--bestrad" />
210 <has_text text="--retain_header" />
211 <has_text text="--disable_rad_check" />
212 <has_text text="--barcode_dist_1 2" />
213 <has_text text="--barcode_dist_2 2" />
214 <has_text text="--adapter_mm 2" />
215 </assert_command>
216 <output_collection name="demultiplexed_paired" type="list:paired" count="40">
217 <element name="PopA_01">
218 <element name="forward" file="demultiplexed/PopA_01.1.fa" ftype="fasta"/>
219 <element name="reverse" file="demultiplexed/PopA_01.2.fa" ftype="fasta"/>
220 </element>
221 </output_collection>
222 <output_collection name="remaining" type="list:paired" count="40">
223 <element name="PopA_01">
224 <element name="forward" file="demultiplexed/PopA_01.rem.1.fa" ftype="fasta" />
225 <element name="reverse" file="demultiplexed/PopA_01.rem.2.fa" ftype="fasta" />
226 </element>
227 </output_collection>
228 </test>
229 </tests>
230
231 <help>
232 <![CDATA[
233 .. class:: infomark
234
235 **What it does**
236
237 This program examines raw reads from an Illumina sequencing run and first, checks that the barcode and the RAD cutsite are intact, and demultiplexes the data. If there are errors in the barcode or the RAD site within a certain allowance process_radtags can correct them. Second, it slides a window down the length of the read and checks the average quality score within the window. If the score drops below 90% probability of being correct (a raw phred score of 10), the read is discarded. This allows for some seqeuncing errors while elimating reads where the sequence is degrading as it is being sequenced. By default the sliding window is 15% of the length of the read, but the threshold and window size can be adjusted.
238
239 The process_radtags program can:
240
241 - handle data that is barcoded, either inline or using an index, or unbarcoded.
242 - use combinatorial barcodes.
243 - check and correct for a restriction enzyme cutsite for single or double-digested data.
244 - filter adapter sequence while allowing for sequencing error in the adapter pattern.
245 - process individual files or whole directories of files.
246 - directly read gzipped data
247 - filter reads based on Illumina's Chastity filter
248
249 **Help**
250
251 Input files:
252
253 - A set of one or more FASTQ files (either selected manually, a dataset list, or a paired dataset list)
254
255 - Barcode File
256
257 The barcode file is a very simple format:
258
259 ======= ===========
260 Barcode Sample name
261 ======= ===========
262 ATGGGG PopA_01
263 GGGTAA PopA_02
264 AGGAAA PopA_03
265 TTTAAG PopA_04
266 GGTGTG PopA_05
267 TGATGT PopA_06
268 ======= ===========
269
270 Combinatorial barcodes are specified, one per column, separated by a tab:
271
272 ======== ======== ===========
273 Barcode1 Barcode2 Sample name
274 ======== ======== ===========
275 CGATA ACGTA PopA_01
276 CGGCG CGTA PopA_02
277 GAAGC CGTA PopA_03
278 GAGAT CGTA PopA_04
279 CGATA AGCA PopA_05
280 CGGCG AGCA PopA_06
281 ======== ======== ===========
282
283 The sample name column can be omitted. Then the Barcodes are used for naming the output files.
284
285 @STACKS_INFOS@
286 ]]>
287 </help>
288 <expand macro="citation" />
289 </tool>