Mercurial > repos > guerler > hhsuite

annotate hhsearch.xml @ 6:cec2aa4d6c0d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit c335621f41bfb23eb31f71f5e2b2191727eccf9a"
author guerler
date Sun, 27 Sep 2020 17:08:05 +0000
parents 3e4d88784254
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
1 <tool id="hhsearch" name="HHsearch" version="0.1.0" python_template_version="3.5">
6
cec2aa4d6c0d "planemo upload commit c335621f41bfb23eb31f71f5e2b2191727eccf9a"
guerler
parents: 5
diff changeset
2 <description>detecting remote homologues of proteins</description>
5
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
3 <requirements>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
4 <requirement type="package" version="3.2.0">hhsuite</requirement>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
5 </requirements>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
6 <command detect_errors="exit_code"><![CDATA[
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
7 link '$hhm_ffdata' hhdb_hhm.ffdata &&
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
8 link '$hhm_ffindex' hhdb_hhm.ffindex &&
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
9 link '$cs219_ffdata' hhdb_cs219.ffdata &&
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
10 link '$cs219_ffindex' hhdb_cs219.ffindex &&
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
11 $method -e '$e' -i '$input' -d hhdb -o '$output'
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
12 ]]></command>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
13 <inputs>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
14 <param format="data" name="input" type="data" label="Query Sequence" help="Single sequence or multiple sequence alignment (MSA)
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
15 in a3m, a2m, or FASTA format, or HMM in hhm format. (-i)"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
16 <param format="txt" name="hhm_ffindex" type="data" label="HHM Index file" help="Database file ending with 'hhm.ffindex'."/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
17 <param format="data" name="hhm_ffdata" type="data" label="HHM Data file" help="Database file ending with 'hhm.ffdata'."/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
18 <param format="txt" name="cs219_ffindex" type="data" label="cs219 Index file" help="Database file ending with 'cs219.ffindex'."/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
19 <param format="data" name="cs219_ffdata" type="data" label="cs219 Data file" help="Database file ending with 'cs219.ffdata'."/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
20 <param name="method" type="select" display="radio" label="Search Method" help="Select a search method. See help below for more information.">
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
21 <option value="hhsearch" selected="true">HHsearch</option>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
22 <option value="hhblits">HHblits</option>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
23 </param>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
24 <param name="e" type="float" label="E-value cutoff for inclusion in result alignment. (-e)" value="0.001" min="0" max="1"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
25 </inputs>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
26 <outputs>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
27 <data format="txt" name="output" />
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
28 </outputs>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
29 <tests>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
30 <test>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
31 <param name="method" value="hhblits"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
32 <param name="input" value="6VYB_A.fasta"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
33 <param name="hhm_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffindex"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
34 <param name="hhm_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffdata"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
35 <param name="cs219_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffindex"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
36 <param name="cs219_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffdata"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
37 <output name="output" file="6VYB_A.hhr" lines_diff="4"/>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
38 </test>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
39 </tests>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
40 <help><![CDATA[
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
41 HHsearch aligns a profile HMM against a database of target profile HMMs. The search first aligns the
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
42 query HMM with each of the target HMMs using the Viterbi dynamic programming algorithm, which finds the
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
43 alignment with the maximum score. The E-value for the target HMM is calculated from the Viterbi score.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
44 Target HMMs that reach sufficient significance to be reported are realigned using the Maximum Accuracy algorithm (MAC).
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
45 This algorithm maximizes the expected number of correctly aligned pairs of residues minus a penalty between 0 and 1.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
46 Values near 0 produce greedy, long, nearly global alignments, values above 0.3 result in shorter, local alignments.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
47
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
48 HHblits is an accelerated version of HHsearch that is fast enough to perform iterative searches through millions of profile HMMs,
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
49 e.g. through the Uniclust profile HMM databases, generated by clustering the UniProt database into clusters of globally alignable sequences.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
50 Analogously to PSI-BLAST and HMMER3, such iterative searches can be used to build MSAs by starting from a single query sequence.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
51 Sequences from matches to profile HMMs below some E-value threshold (e.g. 10−3) are added to the query MSA for the next search iteration.
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
52
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
53 Download databases from: http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
54 ]]></help>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
55 <citations>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
56 <citation type="bibtex">
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
57 @misc{githubhh-suite,
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
58 author = {Soeding, Johannes},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
59 year = {2005},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
60 title = {Protein homology detection by HMM-HMM comparison},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
61 publisher = {Oxford University Press},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
62 journal = {Bioinformatics},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
63 url = {https://doi.org/10.1093/bioinformatics/bti125},
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
64 }</citation>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
65 </citations>
3e4d88784254 "planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
guerler
parents:
diff changeset
66 </tool>