Mercurial > repos > iuc > mothur_pre_cluster

comparison pre.cluster.xml @ 3:d6bed1e2df21 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 4648c7574a78601e03ae6a318cbcd5b492a8a9f4
author iuc
date Wed, 14 Feb 2018 09:14:38 -0500
parents e277ab688993
children 4af9561f3c7c
comparison
equal deleted inserted replaced
2:680a07c92867 3:d6bed1e2df21
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements"/>
7 <expand macro="stdio"/> 7 <expand macro="stdio"/>
8 <expand macro="version_command"/> 8 <expand macro="version_command"/>
9 <command><![CDATA[ 9 <command><![CDATA[
10 @SHELL_OPTIONS@ 10 @SHELL_OPTIONS@
11 11
12 ## create symlinks to input datasets 12 ## create symlinks to input datasets
13 ln -s "$fasta" fasta.dat && 13 ln -s '$fasta' fasta.dat &&
14 ln -s "$name" name.dat && 14 ln -s '$name' name.dat &&
15 ln -s "$group" group.dat && 15 ln -s '$group' group.dat &&
16 16
17 echo 'pre.cluster( 17 echo 'pre.cluster(
18 fasta=fasta.dat, 18 fasta=fasta.dat,
19 #if $name.is_of_type("mothur.names"): 19 #if $name.is_of_type("mothur.names"):
20 name=name.dat, 20 name=name.dat,
21 #elif $name.is_of_type("mothur.count_table"): 21 #elif $name.is_of_type("mothur.count_table"):
22 count=name.dat, 22 count=name.dat,
23 #end if 23 #end if
24 #if $group: 24 #if $group:
25 group=group.dat, 25 group=group.dat,
26 #end if 26 #end if
27 diffs=$diffs, 27 diffs=$diffs,
28 match=$match, 28 match=$match,
29 mismatch=$mismatch, 29 mismatch=$mismatch,
30 gapopen=$gapopen, 30 gapopen=$gapopen,
31 gapextend=$gapextend, 31 gapextend=$gapextend,
32 topdown=$topdown, 32 topdown=$topdown,
33 processors='\${GALAXY_SLOTS:-8}' 33 processors='\${GALAXY_SLOTS:-8}'
34 )' 34 )'
35 | sed 's/ //g' ## mothur trips over whitespace 35 | sed 's/ //g' ## mothur trips over whitespace
36 | mothur 36 | mothur
37 | tee mothur.out.log && 37 | tee mothur.out.log &&
38 38
39 if [ -f fasta.precluster.map ]; then mv fasta.precluster.map fasta.precluster.fasta.map; fi 39 cat fasta* &&
40
41 if [ -f fasta.precluster.map ]; then mv fasta.precluster.map fasta.precluster.fasta.map; fi
40 ]]></command> 42 ]]></command>
41 <inputs> 43 <inputs>
42 <param name="fasta" type="data" format="fasta" label="fasta - Sequence Fasta"/> 44 <param argument="fasta" type="data" format="fasta" label="fasta - Sequence Fasta"/>
43 <param name="name" type="data" format="mothur.names,mothur.count_table" optional="true" label="name file or count table - Sequences Name reference"/> 45 <param argument="name" type="data" format="mothur.names,mothur.count_table" optional="true" label="name file or count table - Sequences Name reference"/>
44 <param name="group" type="data" format="mothur.groups" optional="true" label="group - Sequences Name reference"/> 46 <param argument="group" type="data" format="mothur.groups" optional="true" label="group - Sequences Name reference"/>
45 <param name="diffs" type="integer" value="1" min="0" label="diffs - Number of mismatched bases to allow between sequences in a group (default 1)"/> 47 <param argument="diffs" type="integer" value="1" min="0" label="diffs - Number of mismatched bases to allow between sequences in a group (default 1)"/>
46 <param name="match" type="integer" value="1" label="match - reward for a match (default 1)"/> 48 <param argument="match" type="integer" value="1" label="match - reward for a match (default 1)"/>
47 <param name="mismatch" type="integer" value="-1" label="mismatch - penalty for a mismatch (default -1)"/> 49 <param argument="mismatch" type="integer" value="-1" label="mismatch - penalty for a mismatch (default -1)"/>
48 <param name="gapopen" type="integer" value="-2" label="gapopen - penalty for opening a gap (default -2)"/> 50 <param argument="gapopen" type="integer" value="-2" label="gapopen - penalty for opening a gap (default -2)"/>
49 <param name="gapextend" type="integer" value="-1" label="gapextend - penalty for extending a gap (default -1)"/> 51 <param argument="gapextend" type="integer" value="-1" label="gapextend - penalty for extending a gap (default -1)"/>
50 <param name="topdown" type="boolean" truevalue="true" falsevalue="false" checked="true" label="topdown" help="cluster from largest abundance to smallest or vice versa. Default=Yes, meaning largest to smallest"/> 52 <param argument="topdown" type="boolean" truevalue="true" falsevalue="false" checked="true" label="topdown"
53 help="cluster from largest abundance to smallest or vice versa. Default=Yes, meaning largest to smallest"/>
51 </inputs> 54 </inputs>
52 <outputs> 55 <outputs>
53 <expand macro="logfile-output"/> 56 <expand macro="logfile-output"/>
54 <data name="fasta_out" format_source="fasta" from_work_dir="fasta*.precluster.dat" label="${tool.name} on ${on_string}: precluster.fasta"/> 57 <data name="fasta_out" format_source="fasta" from_work_dir="fasta*.precluster.dat" label="${tool.name} on ${on_string}: precluster.fasta"/>
55 <data name="names_out" format="mothur.names" from_work_dir="fasta*.precluster.names" label="${tool.name} on ${on_string}: precluster.names"> 58 <data name="names_out" format="mothur.names" from_work_dir="fasta*.precluster.names" label="${tool.name} on ${on_string}: precluster.names">
64 </outputs> 67 </outputs>
65 <tests> 68 <tests>
66 <test><!-- test with fasta and names file --> 69 <test><!-- test with fasta and names file -->
67 <param name="fasta" value="amazon.fasta_head" ftype="fasta"/> 70 <param name="fasta" value="amazon.fasta_head" ftype="fasta"/>
68 <param name="name" value="amazon.head.names" ftype="mothur.names"/> 71 <param name="name" value="amazon.head.names" ftype="mothur.names"/>
69 <output name="fasta_out" md5="d5d37ace0f2a5c020edd0aa9eb7aca9b" ftype="fasta"/> 72 <output name="fasta_out" ftype="fasta">
70 <output name="names_out" md5="51090fe5e111920ec1003c2073532d96" ftype="mothur.names"/> 73 <assert_contents>
74 <expand macro="test-fasta-format"/>
75 <has_text text="U68589"/>
76 </assert_contents>
77 </output>
78 <output name="names_out" ftype="mothur.names">
79 <assert_contents>
80 <expand macro="test-names-format"/>
81 <has_line_matching expression="^U68589\tU68589$"/>
82 </assert_contents>
83 </output>
71 <output_collection name="map_out" count="1"> 84 <output_collection name="map_out" count="1">
72 <element name="fasta" md5="c2ca7b0d45aa3881c7bd5cb8a44c853b" ftype="tabular"/> 85 <element name="fasta" ftype="tabular">
86 <assert_contents>
87 <has_text text="ideal_seq_1"/>
88 <has_text text="U68589"/>
89 </assert_contents>
90 </element>
73 </output_collection> 91 </output_collection>
74 <expand macro="logfile-test"/> 92 <expand macro="logfile-test"/>
75 </test> 93 </test>
76 <test><!-- test with fasta and count table --> 94 <test><!-- test with fasta and count table -->
77 <param name="fasta" value="amazon.fasta_head" ftype="fasta"/> 95 <param name="fasta" value="amazon.fasta_head" ftype="fasta"/>
78 <param name="name" value="amazon.count_table" ftype="mothur.count_table"/> 96 <param name="name" value="amazon.count_table" ftype="mothur.count_table"/>
79 <output name="fasta_out" md5="d5d37ace0f2a5c020edd0aa9eb7aca9b" ftype="fasta"/> 97 <output name="fasta_out" ftype="fasta">
80 <output name="count_out" md5="9831e271b9a96f91ad700f84aeed03a5" ftype="mothur.count_table"/> 98 <assert_contents>
99 <expand macro="test-fasta-format"/>
100 <has_text text="U68589"/>
101 </assert_contents>
102 </output>
103 <output name="count_out" ftype="mothur.count_table">
104 <assert_contents>
105 <expand macro="test-count-format"/>
106 <has_text text="U68589"/>
107 </assert_contents>
108 </output>
81 <output_collection name="map_out" count="1"> 109 <output_collection name="map_out" count="1">
82 <element name="fasta" md5="c2ca7b0d45aa3881c7bd5cb8a44c853b" ftype="tabular"/> 110 <element name="fasta" ftype="tabular">
111 <assert_contents>
112 <has_text text="ideal_seq_1"/>
113 <has_text text="U68589"/>
114 </assert_contents>
115 </element>
83 </output_collection> 116 </output_collection>
84 <expand macro="logfile-test"/> 117 <expand macro="logfile-test"/>
85 </test> 118 </test>
86 </tests> 119 </tests>
87 <help> 120 <help><![CDATA[
88 <![CDATA[
89 121
90 @MOTHUR_OVERVIEW@ 122 @MOTHUR_OVERVIEW@
91 123
92 **Command Documentation** 124 **Command Documentation**
93 125
94 The pre.cluster_ command implements a pseudo-single linkage algorithm with the goal of removing sequences that are likely due to pyrosequencing errors. The basic idea is that abundant sequences are more likely to generate erroneous sequences than rare sequences. With that in mind, the algorithm proceeds by ranking sequences in order of their abundance. Then we walk through the list of sequences looking for rarer sequences that are within some threshold of the original sequence. Those that are within the threshold are merged with the larger sequence. The original Huse method performs this task on a distance matrix, whereas we do it based on the original sequences. The advantage of our approach is that the algorithm works on aligned sequences instead of a distance matrix. This is advantageous because by pre-clustering you remove a large number of sequences making the distance calculation much faster. 126 The pre.cluster_ command implements a pseudo-single linkage algorithm with the goal of removing sequences that
127 are likely due to pyrosequencing errors. The basic idea is that abundant sequences are more likely to generate
128 erroneous sequences than rare sequences. With that in mind, the algorithm proceeds by ranking sequences in order
129 of their abundance. Then we walk through the list of sequences looking for rarer sequences that are within some
130 threshold of the original sequence. Those that are within the threshold are merged with the larger sequence.
131 The original Huse method performs this task on a distance matrix, whereas we do it based on the original sequences.
132 The advantage of our approach is that the algorithm works on aligned sequences instead of a distance matrix.
133 This is advantageous because by pre-clustering you remove a large number of sequences making the distance
134 calculation much faster.
95 135
96 .. _pre.cluster: https://www.mothur.org/wiki/Pre.cluster 136 .. _pre.cluster: https://www.mothur.org/wiki/Pre.cluster
97 137
98 v1.24.0: Updated to mothur 1.33, added count and topdown parameter 138 v1.24.0: Updated to mothur 1.33, added count and topdown parameter
99 ]]> 139
100 </help> 140 ]]></help>
101 <expand macro="citations"/> 141 <expand macro="citations"/>
102 </tool> 142 </tool>