Mercurial > repos > iuc > mothur_cluster_split

comparison cluster.split.xml @ 0:e56e12d98ac4 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/mothur commit 180a403421967d36f995941b1a4561349d75cfc5
author iuc
date Fri, 24 Jun 2016 16:26:26 -0400
parents
children bfd4e6980f44
comparison
equal deleted inserted replaced
-1:000000000000 0:e56e12d98ac4
1 <tool profile="16.07" id="mothur_cluster_split" name="Cluster.split" version="@WRAPPER_VERSION@.0">
2 <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="version_command"/>
8 <command detect_errors="aggressive"><![CDATA[
9 ## create symlinks to input datasets
10 ln -s "$count" count.dat &&
11 #if $splitby.splitmethod == "distance":
12 ln -s "$splitby.matrix.dist" splitby.matrix.dist.dat &&
13 ln -s "$splitby.matrix.name" splitby.matrix.name.dat &&
14 #elif $splitby.splitmethod == "classify":
15 ln -s "$splitby.dist" splitby.dist.dat &&
16 ln -s "$splitby.name" splitby.name.dat &&
17 ln -s "$splitby.taxonomy" splitby.taxonomy.dat &&
18 #elif $splitby.splitmethod == "fasta":
19 ln -s "$splitby.fasta" splitby.fasta.dat &&
20 ln -s "$splitby.name" splitby.name.dat &&
21 ln -s "$splitby.taxonomy" splitby.taxonomy.dat &&
22 #end if
23
24 echo 'cluster.split(
25 splitmethod=$splitby.splitmethod,
26 #if $splitby.splitmethod == "distance":
27 #if $splitby.matrix.format == "column":
28 column=splitby.matrix.dist.dat,
29 name=splitby.matrix.name.dat,
30 #elif $splitby.matrix.format == "phylip":
31 phylip=splitby.matrix.dist.dat,
32 #if $splitby.matrix.name:
33 name=splitby.matrix.name.dat,
34 #end if
35 #end if
36 #elif $splitby.splitmethod == "classify":
37 column=splitby.dist.dat,
38 name=splitby.name.dat,
39 taxonomy=splitby.taxonomy.dat,
40 #if $splitby.taxlevel > 1:
41 taxlevel=$splitby.taxlevel,
42 #end if
43 #elif $splitby.splitmethod == "fasta":
44 fasta=splitby.fasta.dat,
45 name=splitby.name.dat,
46 taxonomy=splitby.taxonomy.dat,
47 #if $splitby.taxlevel > 1:
48 taxlevel=$splitby.taxlevel,
49 #end if
50 classic=$splitby.classic,
51 #end if
52 #if $count:
53 count=count.dat,
54 #end if
55 #if $method:
56 method=$method,
57 #end if
58 #if float($cutoff) > 0.0:
59 cutoff=$cutoff,
60 #end if
61 hard=$hard,
62 #if $precision
63 precision=$precision,
64 #end if
65 large=$large,
66 cluster=$cluster,
67 processors='\${GALAXY_SLOTS:-8}'
68 )'
69 | sed 's/ //g' ## mothur trips over whitespace
70 | mothur
71 ]]></command>
72 <inputs>
73 <conditional name="splitby">
74 <param name="splitmethod" type="select" label="Split by" help="">
75 <option value="distance">Distance</option>
76 <option value="classify">Classification</option>
77 <option value="fasta">Classification using fasta</option>
78 </param>
79 <when value="distance">
80 <conditional name="matrix">
81 <param name="format" type="select" label="Select a Distance Matrix Format" help="">
82 <option value="column">Pairwise Column Matrix</option>
83 <option value="phylip">Phylip Distance Matrix</option>
84 </param>
85 <when value="column">
86 <param name="dist" type="data" format="mothur.pair.dist" label="column - Distance Matrix"/>
87 <param name="name" type="data" format="mothur.names" label="name - Sequences Name reference"/>
88 </when>
89 <when value="phylip">
90 <param name="dist" type="data" format="mothur.lower.dist,mothur.square.dist" label="phylip - Distance Matrix"/>
91 <param name="name" type="data" format="mothur.names" optional="true" label="name - Sequences Name reference"/>
92 </when>
93 </conditional>
94 </when>
95 <when value="classify">
96 <param name="dist" type="data" format="mothur.pair.dist" label="column - Distance Matrix"/>
97 <param name="name" type="data" format="mothur.names" label="name - Sequences Name reference"/>
98 <param name="taxonomy" type="data" format="mothur.seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/>
99 <param name="taxlevel" type="integer" value="1" label="taxlevel - taxonomy level for split (default=1)" help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/>
100 </when>
101 <when value="fasta">
102 <param name="fasta" type="data" format="mothur.align" label="fasta - Aligned Sequences" help="must be aligned sequences (mothur.align)"/>
103 <param name="name" type="data" format="mothur.names" label="name - Sequences Name reference"/>
104 <param name="taxonomy" type="data" format="mothur.seq.taxonomy" label="taxonomy - Taxonomy (from Classify.seqs)"/>
105 <param name="taxlevel" type="integer" value="3" label="taxlevel - taxonomy level for split (default=3)" help="taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list"/>
106 <param name="classic" type="boolean" checked="false" truevalue="true" falsevalue="false" label="classic - Use cluster.classic"/>
107 </when>
108 </conditional>
109 <param name="count" type="data" format="mothur.count_table" optional="true" label="count - a count_table" help="generated by count.seqs"/>
110 <param name="method" type="select" label="method - Select a Clustering Method" help="">
111 <option value="furthest">Furthest neighbor</option>
112 <option value="nearest">Nearest neighbor</option>
113 <option value="average" selected="true">Average neighbor</option>
114 </param>
115 <param name="cutoff" type="float" value="0.0" min="0.0" label="cutoff - Distance Cutoff threshold - ignored if not > 0" help="Ignore pairwise distances larger than this, a common value would be 0.25"/>
116 <param name="hard" type="boolean" checked="true" truevalue="true" falsevalue="false" label="hard - Use hard cutoff instead of rounding" help=""/>
117 <param name="precision" type="select" optional="true" label="precision - Precision for rounding distance values" help="Set higher precision for longer genome scale sequence lengths">
118 <option value="10">.1</option>
119 <option value="100" selected="true">.01</option>
120 <option value="1000">.001</option>
121 <option value="10000">.0001</option>
122 <option value="100000">.00001</option>
123 <option value="1000000">.000001</option>
124 </param>
125 <param name="large" type="boolean" checked="false" truevalue="true" falsevalue="false" label="large - distance matrix is too large to fit in RAM" help="If your job fails due to not enough memory error, set this to true to rerun"/>
126 <param name="cluster" type="boolean" falsevalue="false" truevalue="true" checked="true" label="The cluster parameter allows you to indicate whether you want to run the clustering or just split the distance matrix, default=T"/>
127 </inputs>
128 <outputs>
129 <expand macro="logfile-output"/>
130 <data name="rabund" format="mothur.rabund" from_work_dir="splitby.*.rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/>
131 <data name="sabund" format="mothur.sabund" from_work_dir="splitby.*.sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/>
132 <data name="otulist" format="mothur.list" from_work_dir="splitby.*.list" label="${tool.name} on ${on_string}: list (OTU List)"/>
133 <collection name="splitdist" type="list" label="${tool.name} on ${on_string}: split dist">
134 <filter>not cluster</filter>
135 <discover_datasets pattern=".*?\.column\.dist\.(?P&lt;designation&gt;.*)\.temp" format="mothur.dist"/>
136 </collection>
137 <collection name="splitnames" type="list" label="${tool.name} on ${on_string}: split names">
138 <filter>not cluster</filter>
139 <discover_datasets pattern=".*?\.names\.(?P&lt;designation&gt;.*)\.temp" format="mothur.names"/>
140 </collection>
141 <data name="splitfile" format="txt" from_work_dir="splitby.*.file" label="${tool.name} on ${on_string}: split.file">
142 <filter>not cluster</filter>
143 </data>
144 </outputs>
145 <tests>
146 <test><!-- test with distance method -->
147 <param name="splitmethod" value="distance"/>
148 <param name="format" value="phylip"/>
149 <param name="dist" value="98_sq_phylip_amazon.dist" ftype="mothur.square.dist"/>
150 <output name="otulist" md5="2613ef0a1805ba9de012a41e938d8947" ftype="mothur.list"/>
151 <output name="rabund" md5="4df813ec2d51c373a846a82380c7a1f8" ftype="mothur.rabund"/>
152 <output name="sabund" md5="8d6813a5e8d2ad426a0ee5fdd99f1a19" ftype="mothur.sabund"/>
153 <expand macro="logfile-test"/>
154 </test>
155 <test><!-- test with cluster false -->
156 <param name="splitmethod" value="distance"/>
157 <param name="format" value="phylip"/>
158 <param name="dist" value="98_sq_phylip_amazon.dist" ftype="mothur.square.dist"/>
159 <param name="cluster" value="false"/>
160 <output name="splitfile" ftype="txt">
161 <assert_contents>
162 <has_text text="column"/>
163 <has_text text="dist"/>
164 <has_text text="names"/>
165 <has_text text="temp"/>
166 </assert_contents>
167 </output>
168 <output_collection name="splitnames" count="4">
169 <element name="0" md5="27037eeb3e696888b24653d0996261cd" ftype="mothur.names"/>
170 </output_collection>
171 <output_collection name="splitdist" count="3">
172 <element name="4" md5="f751aee00b598d3b6691d34f67dbc8d5" ftype="mothur.dist"/>
173 </output_collection>
174 <expand macro="logfile-test"/>
175 </test>
176 <test><!-- test with classify method -->
177 <param name="splitmethod" value="classify"/>
178 <param name="format" value="column"/>
179 <param name="dist" value="amazon.pair.dist" ftype="mothur.pair.dist"/>
180 <param name="name" value="amazon.names" ftype="mothur.names"/>
181 <param name="taxonomy" value="amazon.wang.wang.taxonomy" ftype="mothur.seq.taxonomy"/>
182 <output name="otulist" md5="d6eba624ad79759c530b9bc3285a1361" ftype="mothur.list"/>
183 <output name="rabund" md5="2a165e1e40644fccb8cc9f53d8915bc3" ftype="mothur.rabund"/>
184 <output name="sabund" md5="7aad8a9ca0eade414d6eba1f8bef960f" ftype="mothur.sabund"/>
185 <expand macro="logfile-test"/>
186 </test>
187 <test><!-- test with fasta -->
188 <param name="splitmethod" value="fasta"/>
189 <param name="fasta" value="amazon.align_head" ftype="mothur.align"/>
190 <param name="name" value="amazon.align_head.names" ftype="mothur.names"/>
191 <param name="taxonomy" value="amazon.align_head.wang.taxonomy" ftype="mothur.seq.taxonomy"/>
192 <param name="cutoff" value="9999"/>
193 <output name="otulist" md5="a1279248cf2bc1094e0046b2cff1b785" ftype="mothur.list"/>
194 <output name="rabund" md5="65ec9f326cd92fc607679b9902ec8430" ftype="mothur.rabund"/>
195 <output name="sabund" md5="854d3acd15f64299c5d9d9e18f2d51b4" ftype="mothur.sabund"/>
196 <expand macro="logfile-test"/>
197 </test>
198 </tests>
199 <help>
200 <![CDATA[
201
202 @MOTHUR_OVERVIEW@
203
204
205 **Command Documenation**
206
207 The cluster.split_ command assign sequences to OTUs (Operational Taxonomy Unit).
208
209 .. _cluster.split: http://www.mothur.org/wiki/Cluster.split
210
211 v1.28.0: Upgraded to Mothur 1.33, introduced cluster boolean.
212
213 ]]>
214 </help>
215 <expand macro="citations"/>
216 </tool>