opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

EMBOSS Version 5 for primersearch revseq seqmatchall sirna splitter tranalign transeq

Browse Source
This commit is contained in:
Chinmay Rao
2007-12-12 22:56:38 +00:00
parent 4421fce049
commit c2c4cf84b4
7 changed files with 573 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/emboss_5/emboss_primersearch.xml
+32
View File
@@ -0,0 +1,32 @@
<tool id="EMBOSS_primersearch81" name="primersearch">
<description>Searches DNA sequences for matches with primer pairs</description>
<command>primersearch -seqall $input1 -infile $input2 -outfile $out_file1 -mismatchpercent $mismatchpercent -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Main sequences</label>
</param>
<param format="data" name="input2" type="data">
<label>Primer file</label>
</param>
<param name="mismatchpercent" size="4" type="text" value="0">
<label>Allowed percent mismatch</label>
</param>
</inputs>
<outputs>
<data format="primersearch" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="input2" value="emboss_primersearch.fasta"/>
<param name="mismatchpercent" value="0"/>
<output name="out_file1" file="emboss_primersearch_out.primersearch"/>
</test>
</tests>
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/primersearch.html
</help>
</tool>
tools/emboss_5/emboss_revseq.xml
+89
View File
@@ -0,0 +1,89 @@
<tool id="EMBOSS_revseq82" name="revseq">
<description>Reverse and complement a sequence</description>
<command>revseq -sequence $input1 -outseq $out_file1 -reverse $reverse -complement $complement -osformat2 $out_format1 -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Sequences</label>
</param>
<param name="reverse" type="select">
<label>Reverse the sequence</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
<param name="complement" type="select">
<label>Complement the sequence</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
<param name="out_format1" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
<option value="gff">GFF</option>
<option value="pir">PIR</option>
<option value="swiss">SwissProt</option>
<option value="dbmotif">DbMotif</option>
<option value="diffseq">Diffseq</option>
<option value="excel">Excel (tab delimited)</option>
<option value="feattable">FeatTable</option>
<option value="motif">Motif</option>
<option value="regions">Regions</option>
<option value="seqtable">SeqTable</option>
<option value="simple">SRS Simple</option>
<option value="srs">SRS</option>
<option value="tagseq">TagSeq</option>
</param>
</inputs>
<outputs>
<data format="fasta" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="reverse" value="yes"/>
<param name="complement" value="yes"/>
<param name="out_format1" value="fasta"/>
<output name="out_file1" file="emboss_revseq_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
.. class:: warningmark
The input dataset needs to be sequences.
-----
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/revseq.html
</help>
</tool>
tools/emboss_5/emboss_seqmatchall.xml
+53
View File
@@ -0,0 +1,53 @@
<tool id="EMBOSS_seqmatchall83" name="seqmatchall">
<description>All-against-all comparison of a set of sequences</description>
<command>seqmatchall -sequence $input1 -outfile $out_file1 -wordsize $wordsize -aformat2 $out_format1 -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Sequences</label>
</param>
<param name="wordsize" size="4" type="text" value="4">
<label>Word size</label>
</param>
<param name="out_format1" type="select">
<label>Output Alignment File Format</label>
<option value="match">Match (m)</option>
<option value="simple">Simple (m)</option>
<option value="fasta">FASTA (m)</option>
<option value="msf">MSF (m)</option>
<option value="srs">SRS (m)</option>
<option value="pair">Pair (p)</option>
<option value="markx0">Markx0 (p)</option>
<option value="markx1">Markx1 (p)</option>
<option value="markx2">Markx2 (p)</option>
<option value="markx3">Markx3 (p)</option>
<option value="markx10">Markx10 (p)</option>
<option value="srspair">SRS pair (p)</option>
<option value="score">Score (p)</option>
<option value="seqmatchall">Seqmatchall Output File</option>
</param>
</inputs>
<outputs>
<data format="seqmatchall" name="out_file1" />.
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="wordsize" value="2"/>
<param name="out_format1" value="fasta"/>
<output name="out_file1" file="emboss_seqmatchall_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
.. class:: warningmark
The input dataset needs to be sequences.
-----
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/seqmatchall.html
</help>
</tool>
tools/emboss_5/emboss_sirna.xml
+117
View File
@@ -0,0 +1,117 @@
<tool id="EMBOSS_sirna89" name="sirna">
<description>Finds siRNA duplexes in mRNA</description>
<command>sirna -sequence $input1 -outfile $ofile1 -outseq $ofile2 -poliii $poliii -aa $aa -tt $tt -polybase $polybase -context $context -rformat2 $out_format1 -osformat3 $out_format2
-auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Sequences</label>
</param>
<param name="poliii" type="select">
<label>Select only the 21 base probes that start with a purine (Pol III expression vectors)</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="aa" type="select">
<label>Select only those 23 base regions that start with AA</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="tt" type="select">
<label>Select only those 23 base regions that end with TT</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="polybase" type="select">
<label>Report more than those 23 base regions that have no repeat of 4 or more of any bases in a row</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
<param name="context" type="select">
<label>Displays the whole 23 bases of the region with the first two bases in brackets</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="out_format1" type="select">
<label>Output Report File Format</label>
<option value="table">Table</option>
<option value="embl">EMBL</option>
<option value="genbank">GENBANK</option>
<option value="gff">GFF</option>
<option value="pir">PIR</option>
<option value="swiss">SwissProt</option>
<option value="dbmotif">DbMotif</option>
<option value="diffseq">Diffseq</option>
<option value="excel">Excel (tab delimited)</option>
<option value="feattable">FeatTable</option>
<option value="motif">Motif</option>
<option value="regions">Regions</option>
<option value="seqtable">SeqTable</option>
<option value="simple">SRS Simple</option>
<option value="srs">SRS</option>
<option value="tagseq">TagSeq</option>
</param>
<param name="out_format2" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
</param>
</inputs>
<outputs>
<data format="table" name="ofile1" />
<data format="fasta" name="ofile2" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="poliii" value="no"/>
<param name="aa" value="no"/>
<param name="tt" value="no"/>
<param name="polybase" value="yes"/>
<param name="context" value="no"/>
<param name="mismatchpercent" value="0"/>
<param name="out_format1" value="gff"/>
<param name="out_format2" value="fasta"/>
<output name="ofile2" file="emboss_sirna_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
.. class:: warningmark
The input dataset needs to be sequences.
-----
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/sirna.html
</help>
</tool>
tools/emboss_5/emboss_splitter.xml
+78
View File
@@ -0,0 +1,78 @@
<tool id="EMBOSS_splitter92" name="splitter">
<description>Split a sequence into (overlapping) smaller sequences</description>
<command>splitter -sequence $input1 -outseq $out_file1 -size "$size" -overlap "$overlap" -addoverlap $addoverlap -osformat2 $out_format1 -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Sequences</label>
</param>
<param name="size" size="10" type="text" value="10000">
<label>Size to split at</label>
</param>
<param name="overlap" size="4" type="text" value="0">
<label>Overlap between split sequences</label>
</param>
<param name="addoverlap" type="select">
<label>Add overlap to size</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="out_format1" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
</param>
</inputs>
<outputs>
<data format="fasta" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="size" value="10000"/>
<param name="overlap" value="0"/>
<param name="addoverlap" value="no"/>
<param name="out_format1" value="fasta"/>
<output name="out_file1" file="emboss_splitter_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
.. class:: warningmark
The input dataset needs to be sequences.
-----
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/splitter.html
</help>
</tool>
tools/emboss_5/emboss_tranalign.xml
+83
View File
@@ -0,0 +1,83 @@
<tool id="EMBOSS_tranalign100" name="tranalign">
<description>Align nucleic coding regions given the aligned proteins</description>
<command>tranalign -asequence $input1 -bsequence $input2 -outseq $out_file1 -table $table -osformat3 $out_format1 -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Nucleic Sequences</label>
</param>
<param format="data" name="input2" type="data">
<label>Protein Sequences</label>
</param>
<param name="table" type="select">
<label>Code to use</label>
<option value="0">Standard</option>
<option value="1">Standard (with alternative initiation codons)</option>
<option value="2">Vertebrate Mitochondrial</option>
<option value="3">Yeast Mitochondrial</option>
<option value="4">Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option>
<option value="5">Invertebrate Mitochondrial</option>
<option value="6">Ciliate Macronuclear and Dasycladacean</option>
<option value="9">Echinoderm Mitochondrial</option>
<option value="10">Euplotid Nuclear</option>
<option value="11">Bacterial</option>
<option value="12">Alternative Yeast Nuclear</option>
<option value="13">Ascidian Mitochondrial</option>
<option value="14">Flatworm Mitochondrial</option>
<option value="15">Blepharisma Macronuclear</option>
<option value="16">Chlorophycean Mitochondrial</option>
<option value="21">Trematode Mitochondrial</option>
<option value="22">Scenedesmus obliquus</option>
<option value="23">Thraustochytrium Mitochondrial</option>
</param>
<param name="out_format1" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
</param>
</inputs>
<outputs>
<data format="fasta" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="3.fasta"/>
<param name="input2" value="2.pep"/>
<param name="table" value="0"/>
<param name="out_format1" value="fasta"/>
<output name="out_file1" file="emboss_tranalign_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/tranalign.html
</help>
</tool>
tools/emboss_5/emboss_transeq.xml
+121
View File
@@ -0,0 +1,121 @@
<tool id="EMBOSS_transeq101" name="transeq">
<description>Translate nucleic acid sequences</description>
<command>transeq -sequence $input1 -outseq $out_file1 -frame $frame -table $table -regions "$regions" -trim $trim -clean $clean -alternative $alternative -osformat2 $out_format1 -auto</command>
<inputs>
<param format="fasta" name="input1" type="data">
<label>Sequences</label>
</param>
<param name="frame" type="select">
<label>Frame(s) to translate</label>
<option value="1">Frame 1</option>
<option value="2">Frame 2</option>
<option value="3">Frame 3</option>
<option value="F">Forward three frames</option>
<option value="-1">Frame -1</option>
<option value="-2">Frame -2</option>
<option value="-3">Frame -3</option>
<option value="R">Reverse three frames</option>
<option value="6">All six frames</option>
</param>
<param name="table" type="select">
<label>Code to use</label>
<option value="0">Standard</option>
<option value="1">Standard (with alternative initiation codons)</option>
<option value="2">Vertebrate Mitochondrial</option>
<option value="3">Yeast Mitochondrial</option>
<option value="4">Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option>
<option value="5">Invertebrate Mitochondrial</option>
<option value="6">Ciliate Macronuclear and Dasycladacean</option>
<option value="9">Echinoderm Mitochondrial</option>
<option value="10">Euplotid Nuclear</option>
<option value="11">Bacterial</option>
<option value="12">Alternative Yeast Nuclear</option>
<option value="13">Ascidian Mitochondrial</option>
<option value="14">Flatworm Mitochondrial</option>
<option value="15">Blepharisma Macronuclear</option>
<option value="16">Chlorophycean Mitochondrial</option>
<option value="21">Trematode Mitochondrial</option>
<option value="22">Scenedesmus obliquus</option>
<option value="23">Thraustochytrium Mitochondrial</option>
</param>
<param name="regions" size="10" type="text" value="">
<label>Regions to translate</label>
</param>
<param name="trim" type="select">
<label>Remove all 'X' and '*' characters from the right end of the translation</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="clean" type="select">
<label>Change all STOP codon positions from the '*' character to 'X'</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="alternative" type="select">
<label>Define frame '-1' as using the set of codons starting with the last codon of the sequence</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="out_format1" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
</param>
</inputs>
<outputs>
<data format="fasta" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<param name="frame" value="1"/>
<param name="table" value="0"/>
<param name="regions" value=""/>
<param name="trim" value="no"/>
<param name="clean" value="no"/>
<param name="alternative" value="no"/>
<param name="out_format1" value="fasta"/>
<output name="out_file1" file="emboss_transeq_out.fasta"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
.. class:: warningmark
The input dataset needs to be sequences.
-----
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/transeq.html
</help>
</tool>