Mercurial > repos > bebatut > cdhit

comparison cd_hit_protein.xml @ 1:2f0a6f227f87 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 5c45ed58045ce1686aa069403f8a9426ea20bac5-dirty
author bebatut
date Tue, 12 Apr 2016 02:54:39 -0400
parents 617a5f3baf7f
children aa923171e225
comparison
equal deleted inserted replaced
0:617a5f3baf7f 1:2f0a6f227f87
1 <tool id="cd_hit_protein" name="CD-HIT PROTEIN" version="1.2"> 1 <tool id="cd_hit_protein" name="CD-HIT PROTEIN" version="1.2">
2 <description>Cluster a protein dataset into representative sequences</description> 2 <description>Cluster a protein dataset into representative sequences</description>
3 <requirements> 3
4 <requirement type="package" version="4.6.1">cd-hit</requirement>
5 </requirements>
6 <macros> 4 <macros>
7 <import>cdhit_macros.xml</import> 5 <import>cdhit_macros.xml</import>
8 </macros> 6 </macros>
9 <command> 7
10 cd-hit -i "$fasta_in" -o rep_seq -c $similarity -n $wordsize 8 <requirements>
11 #include source=$common_cdhit_options# 9 <requirement type="package" version="4.6.1">cd-hit</requirement>
12 #include source=$runtime_tuning# 10 </requirements>
13 </command> 11
14 <inputs> 12 <command><![CDATA[
15 <param name="fasta_in" type="data" format="fasta" label="Protein Sequences to cluster"/> 13 cd-hit
16 <param name="similarity" type="float" value="0.9" label="similarity threshold: .4 - 1.0 (default .9)"> 14 -i "$fasta_in"
17 <validator type="in_range" message="sequence similarity threshold should be .4 - 1.0" min=".4" max="1.0"/> 15 -o rep_seq
18 </param> 16 -c $similarity
19 <param name="wordsize" type="integer" value="5" label="word size (default 5)"> 17 -n $wordsize
20 <help> Suggested word size: 18 #include source=$common_cdhit_options#
21 5 for thresholds 0.7 ~ 1.0; 19 #include source=$runtime_tuning#
22 4 for thresholds 0.6 ~ 0.7; 20 ]]></command>
23 3 for thresholds 0.5 ~ 0.6; 21
24 2 for thresholds 0.4 ~ 0.5; 22 <inputs>
25 </help> 23 <param name="fasta_in" type="data" format="fasta" label="Protein Sequences to cluster"/>
26 <validator type="in_range" message="word size should be between 2 and 5" min="2" max="5"/> 24 <param name="similarity" type="float" value="0.9" label="similarity threshold: .4 - 1.0 (default .9)">
27 </param> 25 <validator type="in_range" message="sequence similarity threshold should be .4 - 1.0" min=".4" max="1.0"/>
28 <expand macro="common_cdhit_options" /> 26 </param>
29 <expand macro="runtime_tuning" /> 27 <param name="wordsize" type="integer" value="5" label="word size (default 5)">
30 </inputs> 28 <help> Suggested word size:
31 <outputs> 29 5 for thresholds 0.7 ~ 1.0;
32 <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/> 30 4 for thresholds 0.6 ~ 0.7;
33 <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/> 31 3 for thresholds 0.5 ~ 0.6;
34 </outputs> 32 2 for thresholds 0.4 ~ 0.5;
35 <tests> 33 </help>
36 <test> 34 <validator type="in_range" message="word size should be between 2 and 5" min="2" max="5"/>
37 <param name="fasta_in" value="cd_hit_protein_in.fasta" /> 35 </param>
38 <param name="similarity" value="0.9"/> 36 <expand macro="common_cdhit_options" />
39 <param name="wordsize" value="5"/> 37 <expand macro="runtime_tuning" />
40 <!-- conditionals in macros --> 38 </inputs>
41 <param name="settings" value="no"/> 39
42 <param name="tuning" value="default"/> 40 <outputs>
43 <output name="clusters_out"> 41 <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
42 <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
43 </outputs>
44
45 <tests>
46 <test>
47 <param name="fasta_in" value="cd_hit_protein_in.fasta" />
48 <param name="similarity" value="0.9"/>
49 <param name="wordsize" value="5"/>
50 <!-- conditionals in macros -->
51 <param name="settings" value="no"/>
52 <param name="tuning" value="default"/>
53 <output name="clusters_out">
54 <assert_contents>
55 <has_text text="Cluster 0" />
56 <!--
57 <has_text_matching expression=">sp.P00338-2.LDHA_HU" />
58 -->
59 </assert_contents>
60 </output>
61 <output name="fasta_out">
62 <assert_contents>
63 <has_text_matching expression=">sp.P19858.LDHA_BOVIN" />
64 </assert_contents>
65 </output>
66 </test>
67 <test>
68 <param name="fasta_in" value="cd_hit_protein_in.fasta" />
69 <param name="similarity" value="0.8" />
70 <param name="wordsize" value="5" />
71 <!-- conditionals in macros -->
72 <param name="settings" value="no"/>
73 <param name="tuning" value="default"/>
74 <output name="clusters_out">
44 <assert_contents> 75 <assert_contents>
45 <has_text text="Cluster 0" /> 76 <has_text text="Cluster 0" />
46 <!-- 77 <not_has_text text="Cluster 4" />
47 <has_text_matching expression=">sp.P00338-2.LDHA_HU" />
48 -->
49 </assert_contents> 78 </assert_contents>
50 </output> 79 </output>
51 <output name="fasta_out"> 80 <output name="fasta_out">
52 <assert_contents> 81 <assert_contents>
53 <has_text_matching expression=">sp.P19858.LDHA_BOVIN" /> 82 <has_text_matching expression=">sp.P00340.LDHA_CHICK" />
54 </assert_contents> 83 </assert_contents>
55 </output> 84 </output>
56 </test> 85 </test>
57 <test> 86 </tests>
58 <param name="fasta_in" value="cd_hit_protein_in.fasta" />
59 <param name="similarity" value="0.8" />
60 <param name="wordsize" value="5" />
61 <!-- conditionals in macros -->
62 <param name="settings" value="no"/>
63 <param name="tuning" value="default"/>
64 <output name="clusters_out">
65 <assert_contents>
66 <has_text text="Cluster 0" />
67 <not_has_text text="Cluster 4" />
68 </assert_contents>
69 </output>
70 <output name="fasta_out">
71 <assert_contents>
72 <has_text_matching expression=">sp.P00340.LDHA_CHICK" />
73 </assert_contents>
74 </output>
75 </test>
76 </tests>
77 87
78 <help> 88 <help><![CDATA[
79 **CD-HIT** 89 **What it does**
80 90
81 CD-HIT_ stands for Cluster Database at High Identity with Tolerance. The program (cd-hit) takes a fasta format sequence database as input and produces a set of 'non-redundant' (nr) representative sequences as output. In addition cd-hit outputs a cluster file, documenting the sequence 'groupies' for each nr sequence representative. The idea is to reduce the overall size of the database without removing any sequence information by only removing 'redundant' (or highly similar) sequences. This is why the resulting database is called non-redundant (nr). Essentially, cd-hit produces a set of closely related protein families from a given fasta sequence database. 91 CD-HIT_ stands for Cluster Database at High Identity with Tolerance. The program (cd-hit) takes a fasta format sequence database as input and produces a set of 'non-redundant' (nr) representative sequences as output. In addition cd-hit outputs a cluster file, documenting the sequence 'groupies' for each nr sequence representative. The idea is to reduce the overall size of the database without removing any sequence information by only removing 'redundant' (or highly similar) sequences. This is why the resulting database is called non-redundant (nr). Essentially, cd-hit produces a set of closely related protein families from a given fasta sequence database.
82 92
83 .. _CD-HIT: http://www.bioinformatics.org/cd-hit/ 93 .. _CD-HIT: http://www.bioinformatics.org/cd-hit/
84 94
109 1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... * 119 1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... *
110 2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73% 120 2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73%
111 3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69% 121 3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
112 122
113 123
114 </help> 124 ]]></help>
125
126 <citations>
127 <citation type="doi">10.1093/bioinformatics/btl158</citation>
128 <citation type="doi">10.1093/bioinformatics/bts565</citation>
129 </citations>
115 </tool> 130 </tool>