Mercurial > repos > iuc > mothur_cluster_split

comparison cluster.split.xml @ 1:bfd4e6980f44 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 ea40e3d84e7850eb4226d6c85f709dcad18d4ba9
author iuc
date Thu, 18 May 2017 18:50:45 -0400
parents e56e12d98ac4
children 063229a11154
comparison
equal deleted inserted replaced
0:e56e12d98ac4 1:bfd4e6980f44
2 <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description> 2 <description>Assign sequences to OTUs (Operational Taxonomic Unit) splits large matrices</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
7 <expand macro="version_command"/> 8 <expand macro="version_command"/>
8 <command detect_errors="aggressive"><![CDATA[ 9 <command><![CDATA[
10 @SHELL_OPTIONS@
11
9 ## create symlinks to input datasets 12 ## create symlinks to input datasets
10 ln -s "$count" count.dat &&
11 #if $splitby.splitmethod == "distance": 13 #if $splitby.splitmethod == "distance":
12 ln -s "$splitby.matrix.dist" splitby.matrix.dist.dat && 14 ln -s "$splitby.matrix.dist" splitby.matrix.dist.dat &&
13 ln -s "$splitby.matrix.name" splitby.matrix.name.dat && 15 ln -s "$splitby.matrix.nameOrCount" splitby.matrix.nameOrCount.dat &&
14 #elif $splitby.splitmethod == "classify": 16 #elif $splitby.splitmethod == "classify":
15 ln -s "$splitby.dist" splitby.dist.dat && 17 ln -s "$splitby.dist" splitby.dist.dat &&
16 ln -s "$splitby.name" splitby.name.dat && 18 ln -s "$splitby.nameOrCount" splitby.nameOrCount.dat &&
17 ln -s "$splitby.taxonomy" splitby.taxonomy.dat && 19 ln -s "$splitby.taxonomy" splitby.taxonomy.dat &&
18 #elif $splitby.splitmethod == "fasta": 20 #elif $splitby.splitmethod == "fasta":
19 ln -s "$splitby.fasta" splitby.fasta.dat && 21 ln -s "$splitby.fasta" splitby.fasta.dat &&
20 ln -s "$splitby.name" splitby.name.dat && 22 ln -s "$splitby.nameOrCount" splitby.nameOrCount.dat &&
21 ln -s "$splitby.taxonomy" splitby.taxonomy.dat && 23 ln -s "$splitby.taxonomy" splitby.taxonomy.dat &&
22 #end if 24 #end if
23 25
24 echo 'cluster.split( 26 echo 'cluster.split(
25 splitmethod=$splitby.splitmethod, 27 splitmethod=$splitby.splitmethod,
26 #if $splitby.splitmethod == "distance": 28 #if $splitby.splitmethod == "distance":
27 #if $splitby.matrix.format == "column": 29 #if $splitby.matrix.format == "column":
28 column=splitby.matrix.dist.dat, 30 column=splitby.matrix.dist.dat,
29 name=splitby.matrix.name.dat, 31 #if $splitby.matrix.nameOrCount.is_of_type("mothur.names"):
32 name=splitby.matrix.nameOrCount.dat,
33 #elif $splitby.matrix.nameOrCount.is_of_type("mothur.count_table"):
34 count=splitby.matrix.nameOrCount.dat,
35 #end if
30 #elif $splitby.matrix.format == "phylip": 36 #elif $splitby.matrix.format == "phylip":
31 phylip=splitby.matrix.dist.dat, 37 phylip=splitby.matrix.dist.dat,
32 #if $splitby.matrix.name: 38 #if $splitby.matrix.nameOrCount:
33 name=splitby.matrix.name.dat, 39 #if $splitby.matrix.nameOrCount.is_of_type("mothur.names"):
40 name=splitby.matrix.nameOrCount.dat,
41 #elif $splitby.matrix.nameOrCount.is_of_type("mothur.count_table"):
42 count=splitby.matrix.nameOrCount.dat,
43 #end if
34 #end if 44 #end if
35 #end if 45 #end if
36 #elif $splitby.splitmethod == "classify": 46 #elif $splitby.splitmethod == "classify":
37 column=splitby.dist.dat, 47 column=splitby.dist.dat,
38 name=splitby.name.dat,
39 taxonomy=splitby.taxonomy.dat, 48 taxonomy=splitby.taxonomy.dat,
40 #if $splitby.taxlevel > 1: 49 #if $splitby.nameOrCount.is_of_type("mothur.names"):
50 name=splitby.nameOrCount.dat,
51 #elif $splitby.nameOrCount.is_of_type("mothur.count_table"):
52 count=splitby.nameOrCount.dat,
53 #end if
54 #if $splitby.taxlevel:
41 taxlevel=$splitby.taxlevel, 55 taxlevel=$splitby.taxlevel,
42 #end if 56 #end if
43 #elif $splitby.splitmethod == "fasta": 57 #elif $splitby.splitmethod == "fasta":
44 fasta=splitby.fasta.dat, 58 fasta=splitby.fasta.dat,
45 name=splitby.name.dat,
46 taxonomy=splitby.taxonomy.dat, 59 taxonomy=splitby.taxonomy.dat,
47 #if $splitby.taxlevel > 1: 60 #if $splitby.nameOrCount.is_of_type("mothur.names"):
61 name=splitby.nameOrCount.dat,
62 #elif $splitby.nameOrCount.is_of_type("mothur.count_table"):
63 count=splitby.nameOrCount.dat,
64 #end if
65 #if $splitby.taxlevel:
48 taxlevel=$splitby.taxlevel, 66 taxlevel=$splitby.taxlevel,
49 #end if 67 #end if
50 classic=$splitby.classic, 68 classic=$splitby.classic,
51 #end if
52 #if $count:
53 count=count.dat,
54 #end if 69 #end if
55 #if $method: 70 #if $method:
56 method=$method, 71 method=$method,
57 #end if 72 #end if
58 #if float($cutoff) > 0.0: 73 #if float($cutoff) > 0.0:
66 cluster=$cluster, 81 cluster=$cluster,
67 processors='\${GALAXY_SLOTS:-8}' 82 processors='\${GALAXY_SLOTS:-8}'
68 )' 83 )'
69 | sed 's/ //g' ## mothur trips over whitespace 84 | sed 's/ //g' ## mothur trips over whitespace
70 | mothur 85 | mothur
86 | tee mothur.out.log
71 ]]></command> 87 ]]></command>
72 <inputs> 88 <inputs>
73 <conditional name="splitby"> 89 <conditional name="splitby">
74 <param name="splitmethod" type="select" label="Split by" help=""> 90 <param name="splitmethod" type="select" label="Split by" help="">
75 <option value="distance">Distance</option> 91 <option value="distance">Distance</option>
82 <option value="column">Pairwise Column Matrix</option> 98 <option value="column">Pairwise Column Matrix</option>
83 <option value="phylip">Phylip Distance Matrix</option> 99 <option value="phylip">Phylip Distance Matrix</option>
84 </param> 100 </param>
85 <when value="column"> 101 <when value="column">
86 <param name="dist" type="data" format="mothur.pair.dist" label="column - Distance Matrix"/> 102 <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"/> 103 <param name="nameOrCount" type="data" format="mothur.names,mothur.count_table" label="name file or count table - Sequences Name reference"/>
88 </when> 104 </when>
89 <when value="phylip"> 105 <when value="phylip">
90 <param name="dist" type="data" format="mothur.lower.dist,mothur.square.dist" label="phylip - Distance Matrix"/> 106 <param name="dist" type="data" format="mothur.dist,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"/> 107 <param name="nameOrCount" type="data" format="mothur.names,mothur.count_table" optional="true" label="name file or count table - Sequences Name reference"/>
92 </when> 108 </when>
93 </conditional> 109 </conditional>
94 </when> 110 </when>
95 <when value="classify"> 111 <when value="classify">
96 <param name="dist" type="data" format="mothur.pair.dist" label="column - Distance Matrix"/> 112 <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)"/> 113 <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"/> 114 <param name="nameOrCount" type="data" format="mothur.names,mothur.count_table" label="name file or count table - Sequences Name reference"/>
115 <param name="taxlevel" type="integer" value="1" min="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> 116 </when>
101 <when value="fasta"> 117 <when value="fasta">
102 <param name="fasta" type="data" format="mothur.align" label="fasta - Aligned Sequences" help="must be aligned sequences (mothur.align)"/> 118 <param name="fasta" type="data" format="mothur.align,fasta" 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)"/> 119 <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"/> 120 <param name="nameOrCount" type="data" format="mothur.names,mothur.count_table" label="name file or count table - Sequences Name reference"/>
121 <param name="taxlevel" type="integer" value="3" min="1" 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"/> 122 <param name="classic" type="boolean" checked="false" truevalue="true" falsevalue="false" label="classic - Use cluster.classic"/>
107 </when> 123 </when>
108 </conditional> 124 </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=""> 125 <param name="method" type="select" label="method - Select a Clustering Method" help="">
111 <option value="furthest">Furthest neighbor</option> 126 <option value="furthest">Furthest neighbor</option>
112 <option value="nearest">Nearest neighbor</option> 127 <option value="nearest">Nearest neighbor</option>
113 <option value="average" selected="true">Average neighbor</option> 128 <option value="average" selected="true">Average neighbor</option>
114 </param> 129 </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"/> 140 <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"/> 141 <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> 142 </inputs>
128 <outputs> 143 <outputs>
129 <expand macro="logfile-output"/> 144 <expand macro="logfile-output"/>
130 <data name="rabund" format="mothur.rabund" from_work_dir="splitby.*.rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)"/> 145 <data name="rabund" format="mothur.rabund" from_work_dir="splitby.*.rabund" label="${tool.name} on ${on_string}: rabund (Rank Abundance)">
131 <data name="sabund" format="mothur.sabund" from_work_dir="splitby.*.sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)"/> 146 <filter>splitby['nameOrCount'].ext != "mothur.count_table"</filter>
147 <filter>splitby['matrix']['nameOrCount'].ext != "mothur.count_table"</filter>
148 </data>
149 <data name="sabund" format="mothur.sabund" from_work_dir="splitby.*.sabund" label="${tool.name} on ${on_string}: sabund (Species Abundance)">
150 <filter>splitby['nameOrCount'].ext != "mothur.count_table"</filter>
151 <filter>splitby['matrix']['nameOrCount'].ext != "mothur.count_table"</filter>
152 </data>
132 <data name="otulist" format="mothur.list" from_work_dir="splitby.*.list" label="${tool.name} on ${on_string}: list (OTU List)"/> 153 <data name="otulist" format="mothur.list" from_work_dir="splitby.*.list" label="${tool.name} on ${on_string}: list (OTU List)"/>
133 <collection name="splitdist" type="list" label="${tool.name} on ${on_string}: split dist"> 154 <collection name="splitdist" type="list" label="${tool.name} on ${on_string}: split dist">
134 <filter>not cluster</filter> 155 <filter>not cluster</filter>
135 <discover_datasets pattern=".*?\.column\.dist\.(?P&lt;designation&gt;.*)\.temp" format="mothur.dist"/> 156 <discover_datasets pattern=".*?\.column\.dist\.(?P&lt;designation&gt;.*)\.temp" format="mothur.dist"/>
136 </collection> 157 </collection>
171 <output_collection name="splitdist" count="3"> 192 <output_collection name="splitdist" count="3">
172 <element name="4" md5="f751aee00b598d3b6691d34f67dbc8d5" ftype="mothur.dist"/> 193 <element name="4" md5="f751aee00b598d3b6691d34f67dbc8d5" ftype="mothur.dist"/>
173 </output_collection> 194 </output_collection>
174 <expand macro="logfile-test"/> 195 <expand macro="logfile-test"/>
175 </test> 196 </test>
176 <test><!-- test with classify method --> 197 <test><!-- test with classify method (mothur.names input file) -->
177 <param name="splitmethod" value="classify"/> 198 <param name="splitmethod" value="classify"/>
178 <param name="format" value="column"/> 199 <param name="format" value="column"/>
179 <param name="dist" value="amazon.pair.dist" ftype="mothur.pair.dist"/> 200 <param name="dist" value="amazon.pair.dist" ftype="mothur.pair.dist"/>
180 <param name="name" value="amazon.names" ftype="mothur.names"/> 201 <param name="nameOrCount" value="amazon.names" ftype="mothur.names"/>
181 <param name="taxonomy" value="amazon.wang.wang.taxonomy" ftype="mothur.seq.taxonomy"/> 202 <param name="taxonomy" value="amazon.wang.wang.taxonomy" ftype="mothur.seq.taxonomy"/>
182 <output name="otulist" md5="d6eba624ad79759c530b9bc3285a1361" ftype="mothur.list"/> 203 <output name="otulist" md5="d6eba624ad79759c530b9bc3285a1361" ftype="mothur.list"/>
183 <output name="rabund" md5="2a165e1e40644fccb8cc9f53d8915bc3" ftype="mothur.rabund"/> 204 <output name="rabund" md5="2a165e1e40644fccb8cc9f53d8915bc3" ftype="mothur.rabund"/>
184 <output name="sabund" md5="7aad8a9ca0eade414d6eba1f8bef960f" ftype="mothur.sabund"/> 205 <output name="sabund" md5="7aad8a9ca0eade414d6eba1f8bef960f" ftype="mothur.sabund"/>
185 <expand macro="logfile-test"/> 206 <expand macro="logfile-test"/>
186 </test> 207 </test>
208 <test><!-- test with classify method (mothur.count_table input file) -->
209 <param name="splitmethod" value="classify"/>
210 <param name="format" value="column"/>
211 <param name="dist" value="amazon.pair.dist" ftype="mothur.pair.dist"/>
212 <param name="nameOrCount" value="amazon.count_table" ftype="mothur.count_table"/>
213 <param name="taxonomy" value="amazon.wang.wang.taxonomy" ftype="mothur.seq.taxonomy"/>
214 <output name="otulist" md5="c5c28330434d3e773221f635d04d6af9" ftype="mothur.list"/>
215 <expand macro="logfile-test"/>
216 </test>
187 <test><!-- test with fasta --> 217 <test><!-- test with fasta -->
188 <param name="splitmethod" value="fasta"/> 218 <param name="splitmethod" value="fasta"/>
189 <param name="fasta" value="amazon.align_head" ftype="mothur.align"/> 219 <param name="fasta" value="amazon.align_head" ftype="mothur.align"/>
190 <param name="name" value="amazon.align_head.names" ftype="mothur.names"/> 220 <param name="nameOrCount" value="amazon.align_head.names" ftype="mothur.names"/>
191 <param name="taxonomy" value="amazon.align_head.wang.taxonomy" ftype="mothur.seq.taxonomy"/> 221 <param name="taxonomy" value="amazon.align_head.wang.taxonomy" ftype="mothur.seq.taxonomy"/>
192 <param name="cutoff" value="9999"/> 222 <param name="cutoff" value="9999"/>
193 <output name="otulist" md5="a1279248cf2bc1094e0046b2cff1b785" ftype="mothur.list"/> 223 <output name="otulist" md5="a1279248cf2bc1094e0046b2cff1b785" ftype="mothur.list"/>
194 <output name="rabund" md5="65ec9f326cd92fc607679b9902ec8430" ftype="mothur.rabund"/> 224 <output name="rabund" md5="65ec9f326cd92fc607679b9902ec8430" ftype="mothur.rabund"/>
195 <output name="sabund" md5="854d3acd15f64299c5d9d9e18f2d51b4" ftype="mothur.sabund"/> 225 <output name="sabund" md5="854d3acd15f64299c5d9d9e18f2d51b4" ftype="mothur.sabund"/>
200 <![CDATA[ 230 <![CDATA[
201 231
202 @MOTHUR_OVERVIEW@ 232 @MOTHUR_OVERVIEW@
203 233
204 234
205 **Command Documenation** 235 **Command Documentation**
206 236
207 The cluster.split_ command assign sequences to OTUs (Operational Taxonomy Unit). 237 The cluster.split_ command assign sequences to OTUs (Operational Taxonomy Unit).
208 238
209 .. _cluster.split: http://www.mothur.org/wiki/Cluster.split 239 .. _cluster.split: https://www.mothur.org/wiki/Cluster.split
210 240
211 v1.28.0: Upgraded to Mothur 1.33, introduced cluster boolean. 241 v1.28.0: Upgraded to Mothur 1.33, introduced cluster boolean.
212 242
213 ]]> 243 ]]>
214 </help> 244 </help>