annotate cd_hit_est.xml @ 0:617a5f3baf7f draft

planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
author bebatut
date Mon, 14 Dec 2015 04:19:46 -0500
parents
children 2f0a6f227f87
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
1 <tool id="cd_hit_est" name="CD-HIT-EST" version="1.2">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
2 <description>Cluster a nucleotide dataset into representative sequences</description>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
3 <requirements>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
4 <requirement type="package" version="4.6.1">cd-hit</requirement>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
5 </requirements>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
6 <macros>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
7 <import>cdhit_macros.xml</import>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
8 </macros>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
9 <command>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
10 cd-hit-est -i "$fasta_in" -o rep_seq -c $similarity -n $wordsize $strand
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
11 #include source=$common_cdhit_options#
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
12 #include source=$runtime_tuning#
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
13 </command>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
14 <inputs>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
15 <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
16 <param name="similarity" type="float" value="0.9" label="similarity threshold: .75 - 1.0, default is .9">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
17 <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
18 </param>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
19 <param name="wordsize" type="integer" value="8" label="word size">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
20 <help> Suggested word size:
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
21 8,9,10 for thresholds 0.90 ~ 1.0
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
22 7 for thresholds 0.88 ~ 0.9
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
23 6 for thresholds 0.85 ~ 0.88
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
24 5 for thresholds 0.80 ~ 0.85
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
25 4 for thresholds 0.75 ~ 0.8
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
26 </help>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
27 <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
28 </param>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
29 <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
30 <expand macro="common_cdhit_options" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
31 <expand macro="runtime_tuning" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
32 </inputs>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
33 <outputs>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
34 <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
35 <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
36 </outputs>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
37 <tests>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
38 <test>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
39 <!-- Expect 3 clusters: 0,1,2 -->
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
40 <param name="fasta_in" value="cd_hit_est_in.fa" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
41 <param name="similarity" value="0.9"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
42 <param name="wordsize" value="8"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
43 <param name="strand" value="true"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
44 <!-- conditionals in macros -->
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
45 <param name="settings" value="no"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
46 <param name="tuning" value="default"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
47 <output name="clusters_out">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
48 <assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
49 <has_text text=">Cluster 0" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
50 <!-- There should not be a Cluster 3 -->
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
51 <not_has_text text="Cluster 3" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
52 <has_text_matching expression="F12Fcsw_481739" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
53 </assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
54 </output>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
55 <output name="fasta_out">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
56 <assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
57 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
58 </assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
59 </output>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
60 </test>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
61 <test>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
62 <!-- tighter constraints should yield more clusters -->
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
63 <param name="fasta_in" value="cd_hit_est_in.fa" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
64 <param name="similarity" value="0.95"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
65 <param name="wordsize" value="9"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
66 <param name="strand" value="true"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
67 <!-- conditionals in macros -->
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
68 <param name="settings" value="no"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
69 <param name="tuning" value="default"/>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
70 <output name="clusters_out">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
71 <assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
72 <has_text text=">Cluster 4" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
73 <has_text_matching expression=">F12Fcsw_481739" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
74 </assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
75 </output>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
76 <output name="fasta_out">
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
77 <assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
78 <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
79 </assert_contents>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
80 </output>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
81 </test>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
82 </tests>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
83 <help>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
84 **CD-HIT-EST**
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
85
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
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.
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
87
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
88 .. _CD-HIT: http://www.bioinformatics.org/cd-hit/
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
89
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
90 ------
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
91
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
92 **Inputs**
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
93
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
94 cd-hit-est requires a fasta dataset as input.
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
95
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
96 ------
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
97
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
98 **Outputs**
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
99
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
100 A fasta datasets containing representative sequences.
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
101
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
102 A text file listing the mapping of sequences to the representative sequences::
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
103
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
104 >Cluster 0
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
105 0 2799aa, >PF04998.6|RPOC2_CHLRE/275-3073... *
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
106 >Cluster 1
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
107 0 2214aa, >PF06317.1|Q6Y625_9VIRU/1-2214... at 80%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
108 1 2215aa, >PF06317.1|O09705_9VIRU/1-2215... at 84%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
109 2 2217aa, >PF06317.1|Q6Y630_9VIRU/1-2217... *
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
110 3 2216aa, >PF06317.1|Q6GWS6_9VIRU/1-2216... at 84%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
111 4 527aa, >PF06317.1|Q67E14_9VIRU/6-532... at 63%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
112 >Cluster 2
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
113 0 2202aa, >PF06317.1|Q6UY61_9VIRU/8-2209... at 60%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
114 1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... *
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
115 2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
116 3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
117
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
118
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
119 </help>
617a5f3baf7f planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 822c081d971c1fa6eef307936fb07dcf9d5db1c5-dirty
bebatut
parents:
diff changeset
120 </tool>