diff tools/ncbi_blast_plus/ncbi_makeblastdb.xml @ 10:70e7dcbf6573 draft

Uploaded v0.0.20, handles dependencies via package_blast_plus_2_2_26, development moved to GitHub, RST README, MIT licence, citation information, more tests, percentage identity option to BLASTN, cElementTree to ElementTree fallback.
author peterjc
date Mon, 23 Sep 2013 06:14:13 -0400
parents 9dabbfd73c8a
children 4c4a0da938ff
line wrap: on
line diff
--- a/tools/ncbi_blast_plus/ncbi_makeblastdb.xml	Thu Apr 25 09:38:37 2013 -0400
+++ b/tools/ncbi_blast_plus/ncbi_makeblastdb.xml	Mon Sep 23 06:14:13 2013 -0400
@@ -1,5 +1,5 @@
-<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.0.4">
-  <description>Make BLAST database</description>
+<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.0.5">
+    <description>Make BLAST database</description>
     <requirements>
         <requirement type="binary">makeblastdb</requirement>
         <requirement type="package" version="2.2.26+">blast+</requirement>
@@ -14,7 +14,8 @@
 ## some extra spaces, e.g. -in " file1 file2 file3  " but BLAST seems happy:
 -in "
 #for $i in $in
-${i.file} #end for
+${i.file}
+#end for
 "
 #if $title:
 -title "$title"
@@ -38,71 +39,73 @@
 ## #else if $tax.select == 'map':
 ## -taxid_map $tax.map
 ## #end if
-</command>
-<stdio>
-    <!-- Anything other than zero is an error -->
-    <exit_code range="1:" />
-    <exit_code range=":-1" />
-    <!-- In case the return code has not been set propery check stderr too -->
-    <regex match="Error:" />
-    <regex match="Exception:" />
-</stdio>
-<inputs>
-    <param name="dbtype" type="select" display="radio" label="Molecule type of input">
-        <option value="prot">protein</option>
-        <option value="nucl">nucleotide</option>
-    </param>
-    <!-- TODO Allow merging of existing BLAST databases (conditional on the database type)
-    <repeat name="in" title="Blast or Fasta Database" min="1">
-        <param name="file" type="data" format="fasta,blastdbn,blastdbp" label="Blast or Fasta database" />
-    </repeat>
-    -->
-    <repeat name="in" title="FASTA file" min="1">
-        <param name="file" type="data" format="fasta" />
-    </repeat>
-    <param name="title" type="text" value="" label="Title for BLAST database" help="This is the database name shown in BLAST search output" />
-    <param name="parse_seqids" type="boolean" truevalue="-parse_seqids" falsevalue="" checked="False" label="Parse the sequence identifiers" help="This is only advised if your FASTA file follows the NCBI naming conventions using pipe '|' symbols" />
-    <param name="hash_index" type="boolean" truevalue="-hash_index" falsevalue="" checked="true" label="Enable the creation of sequence hash values." help="These hash values can then be used to quickly determine if a given sequence data exists in this BLAST database." />
+    </command>
+    <stdio>
+        <!-- Anything other than zero is an error -->
+        <exit_code range="1:" />
+        <exit_code range=":-1" />
+        <!-- In case the return code has not been set propery check stderr too -->
+        <regex match="Error:" />
+        <regex match="Exception:" />
+    </stdio>
+    <inputs>
+        <param name="dbtype" type="select" display="radio" label="Molecule type of input">
+            <option value="prot">protein</option>
+            <option value="nucl">nucleotide</option>
+        </param>
+        <!-- TODO Allow merging of existing BLAST databases (conditional on the database type)
+        <repeat name="in" title="BLAST or FASTA Database" min="1">
+            <param name="file" type="data" format="fasta,blastdbn,blastdbp" label="BLAST or FASTA database" />
+        </repeat>
+        -->
+        <repeat name="in" title="FASTA file" min="1">
+            <param name="file" type="data" format="fasta" />
+        </repeat>
+        <param name="title" type="text" value="" label="Title for BLAST database" help="This is the database name shown in BLAST search output" />
+        <param name="parse_seqids" type="boolean" truevalue="-parse_seqids" falsevalue="" checked="False" label="Parse the sequence identifiers" help="This is only advised if your FASTA file follows the NCBI naming conventions using pipe '|' symbols" />
+        <param name="hash_index" type="boolean" truevalue="-hash_index" falsevalue="" checked="true" label="Enable the creation of sequence hash values." help="These hash values can then be used to quickly determine if a given sequence data exists in this BLAST database." />
 
-    <!-- SEQUENCE MASKING OPTIONS -->
-    <!-- TODO
-    <repeat name="mask_data" title="Provide one or more files containing masking data">
-        <param name="file" type="data" format="asnb" label="File containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
-    </repeat>
-    <repeat name="gi_mask" title="Create GI indexed masking data">
-        <param name="file" type="data" format="asnb" label="Masking data output file" />
-    </repeat>
-    -->
+        <!-- SEQUENCE MASKING OPTIONS -->
+        <!-- TODO
+        <repeat name="mask_data" title="Provide one or more files containing masking data">
+            <param name="file" type="data" format="asnb" label="File containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
+        </repeat>
+        <repeat name="gi_mask" title="Create GI indexed masking data">
+            <param name="file" type="data" format="asnb" label="Masking data output file" />
+        </repeat>
+        -->
 
-    <!-- TAXONOMY OPTIONS -->
-    <!-- TODO
-    <conditional name="tax">
-        <param name="select" type="select" label="Taxonomy options">
-            <option value="">Do not assign sequences to Taxonomy IDs</option>
-            <option value="id">Assign all sequences to one Taxonomy ID</option>
-            <option value="map">Supply text file mapping sequence IDs to taxnomy IDs</option>
-        </param>
-        <when value="">
-        </when>
-        <when value="id">
-            <param name="id" type="integer" value="" label="NCBI taxonomy ID" help="Integer &gt;=0" />
-        </when>
-        <when value="map">
-            <param name="file" type="data" format="txt" label="Seq ID : Tax ID mapping file" help="Format: SequenceId TaxonomyId" />
-        </when>
-    </conditional>
-    -->
-</inputs>
-<outputs>
-    <!-- If we only accepted one FASTA file, we could use its human name here... -->
-    <data name="outfile" format="data" label="${dbtype.value_label} BLAST database from ${on_string}">
-        <change_format>
-                <when input="dbtype" value="nucl" format="blastdbn"/>
-                <when input="dbtype" value="prot" format="blastdbp"/>
-        </change_format>
-    </data>
-</outputs>
-<help>
+        <!-- TAXONOMY OPTIONS -->
+        <!-- TODO
+        <conditional name="tax">
+            <param name="select" type="select" label="Taxonomy options">
+                <option value="">Do not assign sequences to Taxonomy IDs</option>
+                <option value="id">Assign all sequences to one Taxonomy ID</option>
+                <option value="map">Supply text file mapping sequence IDs to taxnomy IDs</option>
+            </param>
+            <when value="">
+            </when>
+            <when value="id">
+                <param name="id" type="integer" value="" label="NCBI taxonomy ID" help="Integer &gt;=0" />
+            </when>
+            <when value="map">
+                <param name="file" type="data" format="txt" label="Seq ID : Tax ID mapping file" help="Format: SequenceId TaxonomyId" />
+            </when>
+        </conditional>
+        -->
+    </inputs>
+    <outputs>
+        <!-- If we only accepted one FASTA file, we could use its human name here... -->
+        <data name="outfile" format="data" label="${dbtype.value_label} BLAST database from ${on_string}">
+            <change_format>
+                <when input="dbtype" value="nucl" format="blastdbn" />
+                <when input="dbtype" value="prot" format="blastdbp" />
+            </change_format>
+        </data>
+    </outputs>
+    <tests>
+    </tests>
+    <help>
 **What it does**
 
 Make BLAST database from one or more FASTA files and/or BLAST databases.
@@ -118,5 +121,23 @@
 **Documentation**
 
 http://www.ncbi.nlm.nih.gov/books/NBK1763/
-</help>
+
+**References**
+
+If you use this Galaxy tool in work leading to a scientific publication please
+cite the following papers:
+
+Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
+Galaxy tools and workflows for sequence analysis with applications
+in molecular plant pathology. PeerJ 1:e167
+http://dx.doi.org/10.7717/peerj.167
+
+Christiam Camacho et al. (2009).
+BLAST+: architecture and applications.
+BMC Bioinformatics. 15;10:421.
+http://dx.doi.org/10.1186/1471-2105-10-421
+
+This wrapper is available to install into other Galaxy Instances via the Galaxy
+Tool Shed at http://toolshed.g2.bx.psu.edu/view/devteam/ncbi_blast_plus
+    </help>
 </tool>