Mercurial > repos > iuc > stacks_rxstacks

comparison stacks_rxstacks.xml @ 0:a1f5a4be394a 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/stacks commit f3a59c91c231cc1582479109e776d05602b7f24d-dirty
author iuc
date Tue, 14 Jun 2016 14:03:38 -0400
parents
children 55814b6afe69
comparison
equal deleted inserted replaced
-1:000000000000 0:a1f5a4be394a
1 <tool id="stacks_rxstacks" name="Stacks: rxstacks" version="@WRAPPER_VERSION@.0">
2 <description>make corrections to genotype and haplotype calls</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
8 <command><![CDATA[
9
10 mkdir stacks_inputs stacks_outputs
11
12 &&
13
14 #for $input_file in $input_col:
15 #set $ext = ""
16 #if not str($input_file.name).endswith('.tsv'):
17 #set $ext = ".tsv"
18 #end if
19 ln -s "${input_file}" "stacks_inputs/${input_file.name}${ext}" &&
20 #end for
21
22 rxstacks
23
24 -t \${GALAXY_SLOTS:-1}
25
26 -P stacks_inputs
27
28 ## Batch description
29 -b 1
30
31 #if str($options_filtering.lnl):
32 --lnl_filter
33 --lnl_lim $options_filtering.lnl
34 #end if
35
36 $options_filtering.lnl_dist
37
38 #if str($options_filtering.conf):
39 --conf_filter
40 --conf_lim $options_filtering.conf
41 #end if
42
43 #if $options_filtering.prune.prune_haplo:
44 --prune_haplo
45 #if str($options_filtering.prune.max_haplo):
46 --max_haplo $options_filtering.prune.max_haplo
47 #end if
48 #end if
49
50 ## snp_model
51 #if str( $snp_options.select_model.model_type) == "bounded":
52 --model_type bounded
53 --bound_low $snp_options.select_model.bound_low
54 --bound_high $snp_options.select_model.bound_high
55 --alpha $snp_options.select_model.alpha
56 #else if str( $snp_options.select_model.model_type) == "snp":
57 --model_type snp
58 --alpha $snp_options.select_model.alpha
59 #else
60 --model_type fixed
61 #end if
62
63 -o stacks_outputs
64 ]]></command>
65
66 <inputs>
67 <param name="input_col" format="tabular,txt" type="data_collection" collection_type="list" label="Output from previous Stacks pipeline steps (e.g. denovo_map or refmap)" />
68
69 <section name="options_filtering" title="Data filtering options" expanded="true">
70 <param name="lnl" type="float" value="" optional="true" argument="--lnl_lim" label="Filter loci with log likelihood values below this threshold" />
71 <param name="lnl_dist" argument="--lnl_dist" truevalue="--lnl_dist" falsevalue="" type="boolean" checked="false" label="Print distribution of mean log likelihoods for catalog loci." />
72
73 <param name="conf" type="float" value="0.75" optional="true" argument="--conf_lim" min="0.0" max="1.0" label="Proportion of loci in population that must be confounded relative to the catalog locus (between 0.0 and 1.0)."/>
74
75 <conditional name="prune">
76 <param name="prune_haplo" argument="--prune_haplo" type="boolean" checked="false" label="Prune out non-biological haplotypes unlikely to occur in the population." />
77 <when value="false"></when>
78 <when value="true">
79 <param name="max_haplo" argument="--max_haplo" type="integer" value="" optional="true" label="Only consider haplotypes for pruning if they occur in fewer than this value."/>
80 </when>
81 </conditional>
82 </section>
83
84 <!-- SNP Model options -->
85 <section name="snp_options" title="SNP Model Options (ustacks options)" expanded="False">
86 <expand macro="snp_options"/>
87 </section>
88 </inputs>
89
90 <outputs>
91 <data format="txt" name="output_log" label="rxstacks.log with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/batch_1.rxstacks.log" />
92
93 <data format="txt" name="output_lnl_dist" label="Distribution of mean log likelihoods with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/batch_1.rxstacks_lnls.tsv">
94 <filter>options_filtering['lnl_dist']</filter>
95 </data>
96
97 <collection name="tags" type="list" label="Assembled loci filtered from ${on_string}">
98 <discover_datasets pattern="(?P&lt;name&gt;.+\.tags)\.tsv" ext="tabular" directory="stacks_outputs" />
99 </collection>
100
101 <collection name="snps" type="list" label="Model calls from each locus filtered from ${on_string}">
102 <discover_datasets pattern="(?P&lt;name&gt;.+\.snps)\.tsv" ext="tabular" directory="stacks_outputs" />
103 </collection>
104
105 <collection name="alleles" type="list" label="Haplotypes/alleles recorded from each locus filtered from ${on_string}">
106 <discover_datasets pattern="(?P&lt;name&gt;.+\.alleles)\.tsv" ext="tabular" directory="stacks_outputs" />
107 </collection>
108
109 <collection name="all_output" type="list" label="Full output from rxstacks on ${on_string}">
110 <discover_datasets pattern="(?P&lt;name&gt;.+\.(tags|snps|alleles))\.tsv" ext="tabular" directory="stacks_outputs" />
111 </collection>
112 </outputs>
113
114 <tests>
115 <test>
116 <param name="input_col">
117 <collection type="list">
118 <element name="batch_1.catalog.alleles.tsv" ftype="tabular" value="genotypes/batch_1.catalog.alleles.tsv" />
119 <element name="batch_1.catalog.snps.tsv" ftype="tabular" value="genotypes/batch_1.catalog.snps.tsv" />
120 <element name="batch_1.catalog.tags.tsv" ftype="tabular" value="genotypes/batch_1.catalog.tags.tsv" />
121 <element name="PopA_01.alleles.tsv" ftype="tabular" value="genotypes/PopA_01.alleles.tsv" />
122 <element name="PopA_01.matches.tsv" ftype="tabular" value="genotypes/PopA_01.matches.tsv" />
123 <element name="PopA_01.snps.tsv" ftype="tabular" value="genotypes/PopA_01.snps.tsv" />
124 <element name="PopA_01.tags.tsv" ftype="tabular" value="genotypes/PopA_01.tags.tsv" />
125 <element name="PopA_02.alleles.tsv" ftype="tabular" value="genotypes/PopA_02.alleles.tsv" />
126 <element name="PopA_02.matches.tsv" ftype="tabular" value="genotypes/PopA_02.matches.tsv" />
127 <element name="PopA_02.snps.tsv" ftype="tabular" value="genotypes/PopA_02.snps.tsv" />
128 <element name="PopA_02.tags.tsv" ftype="tabular" value="genotypes/PopA_02.tags.tsv" />
129 </collection>
130 </param>
131 <param name="options_filtering|lnl" value="-10.0" />
132 <param name="options_filtering|lnl_dist" value="true" />
133 <param name="options_filtering|prune_haplo" value="true" />
134 <param name="options_filtering|max_haplo" value="1" />
135
136 <output name="output_log">
137 <assert_contents>
138 <has_text text="rxstacks executed" />
139 </assert_contents>
140 </output>
141
142 <output name="output_lnl_dist">
143 <assert_contents>
144 <has_text text="Median" />
145 </assert_contents>
146 </output>
147
148 <!-- samples -->
149 <output_collection name="tags">
150 <element name="PopA_01.tags">
151 <assert_contents>
152 <has_text text="lane1_fakedata7_0" />
153 </assert_contents>
154 </element>
155 </output_collection>
156 <output_collection name="snps">
157 <element name="PopA_01.snps">
158 <assert_contents>
159 <has_text text="24.950" />
160 </assert_contents>
161 </element>
162 </output_collection>
163 <output_collection name="alleles">
164 <element name="PopA_01.alleles">
165 <assert_contents>
166 <has_text text="AC" />
167 </assert_contents>
168 </element>
169 </output_collection>
170 </test>
171 </tests>
172
173 <help>
174 <![CDATA[
175 .. class:: infomark
176
177 **What it does**
178
179 This program will run each of the Stacks components: first, running ustacks on each of the samples specified, building loci and calling SNPs in each. Second, cstacks will be run to create a catalog of all loci that were marked as 'parents' or 'samples' on the command line, and finally, sstacks will be executed to match each sample against the catalog. A bit more detail on this process can be found in the FAQ. The denovo_map.pl program will also load the results of each stage of the analysis: individual loci, the catalog, and matches against the catalog into the database (although this can be disabled). After matching, the program will build a database index to speed up access (index_radtags.pl) and enable web-based filtering.
180
181 --------
182
183 **Input files**
184
185 Output from denovo_map or ref_map
186
187 **Output files**
188
189 - XXX.tags.tsv file:
190
191 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
192
193 Notes: For the tags file, each stack will start in the file with a consensus sequence for the entire stack followed by the flags for that stack. Then, each individual read that was merged into that stack will follow. The next stack will start with another consensus sequence.
194
195
196 - XXX.snps.tsv file:
197
198 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
199
200 Notes: If a stack has two SNPs called within it, then there will be two lines in this file listing each one.
201
202
203 - XXX.alleles.tsv file:
204
205 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
206
207 - XXX.matches.tsv file:
208
209 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
210
211 Notes: Each line in this file records a match between a catalog locus and a locus in an individual, for a particular haplotype. The Batch ID plus the Catalog ID together represent a unique locus in the entire population, while the Sample ID and the Stack ID together represent a unique locus in an individual sample.
212
213 @STACKS_INFOS@
214 ]]>
215 </help>
216 <expand macro="citation" />
217 </tool>
218