Mercurial > repos > bebatut > cdhit

comparison cd_hit_est.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_est" name="CD-HIT-EST" version="1.2"> 1 <tool id="cd_hit_est" name="CD-HIT-EST" version="1.2">
2 <description>Cluster a nucleotide dataset into representative sequences</description> 2 <description>Cluster a nucleotide 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-est -i "$fasta_in" -o rep_seq -c $similarity -n $wordsize $strand 8 <requirements>
11 #include source=$common_cdhit_options# 9 <requirement type="package" version="4.6.1">cd-hit</requirement>
12 #include source=$runtime_tuning# 10 </requirements>
13 </command> 11
14 <inputs> 12 <command><![CDATA[
15 <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/> 13 cd-hit-est
16 <param name="similarity" type="float" value="0.9" label="similarity threshold: .75 - 1.0, default is .9"> 14 -i "$fasta_in"
17 <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/> 15 -o rep_seq
18 </param> 16 -c $similarity
19 <param name="wordsize" type="integer" value="8" label="word size"> 17 -n $wordsize $strand
20 <help> Suggested word size: 18
21 8,9,10 for thresholds 0.90 ~ 1.0 19 #include source=$common_cdhit_options#
22 7 for thresholds 0.88 ~ 0.9 20 #include source=$runtime_tuning#
23 6 for thresholds 0.85 ~ 0.88 21 ]]></command>
24 5 for thresholds 0.80 ~ 0.85 22
25 4 for thresholds 0.75 ~ 0.8 23 <inputs>
26 </help> 24 <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/>
27 <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/> 25 <param name="similarity" type="float" value="0.9" label="similarity threshold: .75 - 1.0, default is .9">
28 </param> 26 <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/>
29 <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/> 27 </param>
30 <expand macro="common_cdhit_options" /> 28 <param name="wordsize" type="integer" value="8" label="word size">
31 <expand macro="runtime_tuning" /> 29 <help> Suggested word size:
32 </inputs> 30 8,9,10 for thresholds 0.90 ~ 1.0
33 <outputs> 31 7 for thresholds 0.88 ~ 0.9
34 <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/> 32 6 for thresholds 0.85 ~ 0.88
35 <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/> 33 5 for thresholds 0.80 ~ 0.85
36 </outputs> 34 4 for thresholds 0.75 ~ 0.8
37 <tests> 35 </help>
38 <test> 36 <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/>
39 <!-- Expect 3 clusters: 0,1,2 --> 37 </param>
40 <param name="fasta_in" value="cd_hit_est_in.fa" /> 38 <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/>
41 <param name="similarity" value="0.9"/> 39 <expand macro="common_cdhit_options" />
42 <param name="wordsize" value="8"/> 40 <expand macro="runtime_tuning" />
43 <param name="strand" value="true"/> 41 </inputs>
44 <!-- conditionals in macros --> 42
45 <param name="settings" value="no"/> 43 <outputs>
46 <param name="tuning" value="default"/> 44 <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
47 <output name="clusters_out"> 45 <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
48 <assert_contents> 46 </outputs>
49 <has_text text=">Cluster 0" /> 47
50 <!-- There should not be a Cluster 3 --> 48 <tests>
51 <not_has_text text="Cluster 3" /> 49 <test>
52 <has_text_matching expression="F12Fcsw_481739" /> 50 <!-- Expect 3 clusters: 0,1,2 -->
53 </assert_contents> 51 <param name="fasta_in" value="cd_hit_est_in.fa" />
54 </output> 52 <param name="similarity" value="0.9"/>
55 <output name="fasta_out"> 53 <param name="wordsize" value="8"/>
56 <assert_contents> 54 <param name="strand" value="true"/>
57 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" /> 55 <!-- conditionals in macros -->
58 </assert_contents> 56 <param name="settings" value="no"/>
59 </output> 57 <param name="tuning" value="default"/>
60 </test> 58 <output name="clusters_out">
61 <test> 59 <assert_contents>
62 <!-- tighter constraints should yield more clusters --> 60 <has_text text=">Cluster 0" />
63 <param name="fasta_in" value="cd_hit_est_in.fa" /> 61 <!-- There should not be a Cluster 3 -->
64 <param name="similarity" value="0.95"/> 62 <not_has_text text="Cluster 3" />
65 <param name="wordsize" value="9"/> 63 <has_text_matching expression="F12Fcsw_481739" />
66 <param name="strand" value="true"/> 64 </assert_contents>
67 <!-- conditionals in macros --> 65 </output>
68 <param name="settings" value="no"/> 66 <output name="fasta_out">
69 <param name="tuning" value="default"/> 67 <assert_contents>
70 <output name="clusters_out"> 68 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
71 <assert_contents> 69 </assert_contents>
72 <has_text text=">Cluster 4" /> 70 </output>
73 <has_text_matching expression=">F12Fcsw_481739" /> 71 </test>
74 </assert_contents> 72 <test>
75 </output> 73 <!-- tighter constraints should yield more clusters -->
76 <output name="fasta_out"> 74 <param name="fasta_in" value="cd_hit_est_in.fa" />
77 <assert_contents> 75 <param name="similarity" value="0.95"/>
78 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" /> 76 <param name="wordsize" value="9"/>
79 </assert_contents> 77 <param name="strand" value="true"/>
80 </output> 78 <!-- conditionals in macros -->
81 </test> 79 <param name="settings" value="no"/>
82 </tests> 80 <param name="tuning" value="default"/>
83 <help> 81 <output name="clusters_out">
84 **CD-HIT-EST** 82 <assert_contents>
83 <has_text text=">Cluster 4" />
84 <has_text_matching expression=">F12Fcsw_481739" />
85 </assert_contents>
86 </output>
87 <output name="fasta_out">
88 <assert_contents>
89 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
90 </assert_contents>
91 </output>
92 </test>
93 </tests>
94
95 <help><![CDATA[
96 **What it does**
85 97
86 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. 98 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.
87 99
88 .. _CD-HIT: http://www.bioinformatics.org/cd-hit/ 100 .. _CD-HIT: http://www.bioinformatics.org/cd-hit/
89 101
114 1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... * 126 1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... *
115 2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73% 127 2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73%
116 3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69% 128 3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
117 129
118 130
119 </help> 131 ]]></help>
132
133 <citations>
134 <citation type="doi">10.1093/bioinformatics/btl158</citation>
135 <citation type="doi">10.1093/bioinformatics/bts565</citation>
136 </citations>
120 </tool> 137 </tool>