Mercurial > repos > guerler > hhsuite

changeset 5:3e4d88784254 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 3002402473e9f6dcdac5bfb4013cd2d81884a938-dirty"
author guerler
date Fri, 31 Jul 2020 23:16:55 -0400
parents 691d8f7c078c
children cec2aa4d6c0d
files hhblits.xml hhsearch.xml
diffstat 2 files changed, 66 insertions(+), 61 deletions(-) [+]
line wrap: on
line diff
--- a/hhblits.xml	Fri Jul 31 14:31:15 2020 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,61 +0,0 @@
-<tool id="hhblits" name="HHblits" version="0.1.0" python_template_version="3.5">
-    <description>itererative protein sequence searching</description>
-    <requirements>
-        <requirement type="package" version="3.2.0">hhsuite</requirement>
-    </requirements>
-    <command detect_errors="exit_code"><![CDATA[
-        link '$hhm_ffdata' hhdb_hhm.ffdata &&
-        link '$hhm_ffindex' hhdb_hhm.ffindex &&
-        link '$cs219_ffdata' hhdb_cs219.ffdata &&
-        link '$cs219_ffindex' hhdb_cs219.ffindex &&
-        $method -n '$n' -e '$e' -i '$input' -d hhdb -o '$output'
-    ]]></command>
-    <inputs>
-        <param format="data" name="input" type="data" label="Query Sequence" help="Single sequence or multiple sequence alignment (MSA)
-                in a3m, a2m, or FASTA format, or HMM in hhm format. (-i)"/>
-        <param format="data" name="hhm_ffindex" type="data" label="HHM Index file" help="Database file ending with 'hhm.ffindex'."/>
-        <param format="data" name="hhm_ffdata" type="data" label="HHM Data file" help="Database file ending with 'hhm.ffdata'."/>
-        <param format="data" name="cs219_ffindex" type="data" label="cs219 Index file" help="Database file ending with 'cs219.ffindex'."/>
-        <param format="data" name="cs219_ffdata" type="data" label="cs219 Data file" help="Database file ending with 'cs219.ffdata'."/>
-        <param name="n" type="integer" label="Number of Iterations. (-n)" value="2" min="1" max="8"/>
-        <param name="e" type="float" label="E-value cutoff for inclusion in result alignment. (-e)" value="0.001" min="0" max="1"/>
-        <param name="method" type="select" label="Search Method" help="Select the search method.">
-            <option value="hhblits" selected="true">HHblits</option>
-            <option value="hhsearch">HHsearch</option>
-        </param>
-    </inputs>
-    <outputs>
-        <data format="data" name="output" />
-    </outputs>
-    <tests>
-        <test>
-            <param name="input" value="6VYB_A.fasta"/>
-            <param name="hhm_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffindex"/>
-            <param name="hhm_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffdata"/>
-            <param name="cs219_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffindex"/>
-            <param name="cs219_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffdata"/>
-            <output name="output" file="6VYB_A.hhr" lines_diff="4"/>
-        </test>
-    </tests>
-    <help><![CDATA[
-HMM-HMM-based lightning-fast iterative sequence search
-HHblits and HHsearch is a sensitive, general-purpose, iterative sequence search tool that represents
-both query and database sequences by HMMs. You can search HHblits databases starting
-with a single query sequence, a multiple sequence alignment (MSA), or an HMM. HHblits
-prints out a ranked list of database HMMs/MSAs and can also generate an MSA by merging
-the significant database HMMs/MSAs onto the query MSA.
-
-Download databases from: http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/
-    ]]></help>
-    <citations>
-        <citation type="bibtex">
-@misc{githubhh-suite,
-  author = {Soeding, Johannes},
-  year = {2005},
-  title = {Protein homology detection by HMM-HMM comparison},
-  publisher = {Oxford University Press},
-  journal = {Bioinformatics},
-  url = {https://doi.org/10.1093/bioinformatics/bti125},
-}</citation>
-    </citations>
-</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/hhsearch.xml	Fri Jul 31 23:16:55 2020 -0400
@@ -0,0 +1,66 @@
+<tool id="hhsearch" name="HHsearch" version="0.1.0" python_template_version="3.5">
+    <description>detecting remote homologues from proteins</description>
+    <requirements>
+        <requirement type="package" version="3.2.0">hhsuite</requirement>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+        link '$hhm_ffdata' hhdb_hhm.ffdata &&
+        link '$hhm_ffindex' hhdb_hhm.ffindex &&
+        link '$cs219_ffdata' hhdb_cs219.ffdata &&
+        link '$cs219_ffindex' hhdb_cs219.ffindex &&
+        $method -e '$e' -i '$input' -d hhdb -o '$output'
+    ]]></command>
+    <inputs>
+        <param format="data" name="input" type="data" label="Query Sequence" help="Single sequence or multiple sequence alignment (MSA)
+                in a3m, a2m, or FASTA format, or HMM in hhm format. (-i)"/>
+        <param format="txt" name="hhm_ffindex" type="data" label="HHM Index file" help="Database file ending with 'hhm.ffindex'."/>
+        <param format="data" name="hhm_ffdata" type="data" label="HHM Data file" help="Database file ending with 'hhm.ffdata'."/>
+        <param format="txt" name="cs219_ffindex" type="data" label="cs219 Index file" help="Database file ending with 'cs219.ffindex'."/>
+        <param format="data" name="cs219_ffdata" type="data" label="cs219 Data file" help="Database file ending with 'cs219.ffdata'."/>
+        <param name="method" type="select" display="radio" label="Search Method" help="Select a search method. See help below for more information.">
+            <option value="hhsearch" selected="true">HHsearch</option>
+            <option value="hhblits">HHblits</option>
+        </param>
+        <param name="e" type="float" label="E-value cutoff for inclusion in result alignment. (-e)" value="0.001" min="0" max="1"/>
+    </inputs>
+    <outputs>
+        <data format="txt" name="output" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="method" value="hhblits"/>
+            <param name="input" value="6VYB_A.fasta"/>
+            <param name="hhm_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffindex"/>
+            <param name="hhm_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_hhm.ffdata"/>
+            <param name="cs219_ffindex" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffindex"/>
+            <param name="cs219_ffdata" value="dbCAN-fam-V8/dbCAN-fam-V8_cs219.ffdata"/>
+            <output name="output" file="6VYB_A.hhr" lines_diff="4"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+HHsearch aligns a profile HMM against a database of target profile HMMs. The search first aligns the
+query HMM with each of the target HMMs using the Viterbi dynamic programming algorithm, which finds the
+alignment with the maximum score. The E-value for the target HMM is calculated from the Viterbi score. 
+Target HMMs that reach sufficient significance to be reported are realigned using the Maximum Accuracy algorithm (MAC).
+This algorithm maximizes the expected number of correctly aligned pairs of residues minus a penalty between 0 and 1.
+Values near 0 produce greedy, long, nearly global alignments, values above 0.3 result in shorter, local alignments.
+
+HHblits is an accelerated version of HHsearch that is fast enough to perform iterative searches through millions of profile HMMs,
+e.g. through the Uniclust profile HMM databases, generated by clustering the UniProt database into clusters of globally alignable sequences. 
+Analogously to PSI-BLAST and HMMER3, such iterative searches can be used to build MSAs by starting from a single query sequence.
+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.
+
+Download databases from: http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/
+    ]]></help>
+    <citations>
+        <citation type="bibtex">
+@misc{githubhh-suite,
+  author = {Soeding, Johannes},
+  year = {2005},
+  title = {Protein homology detection by HMM-HMM comparison},
+  publisher = {Oxford University Press},
+  journal = {Bioinformatics},
+  url = {https://doi.org/10.1093/bioinformatics/bti125},
+}</citation>
+    </citations>
+</tool>
\ No newline at end of file