changeset 9:6aafa0ced802 draft

Uploaded v0.0.8, moved development to GitHub; no functional changes

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/blastxml_to_top_descr/README.rst	Tue Jul 30 08:07:28 2013 -0400
@@ -0,0 +1,120 @@
+Galaxy tool to extract top BLAST hit descriptions from BLAST XML
+================================================================
+
+This tool is copyright 2012-2013 by Peter Cock, The James Hutton Institute
+(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
+See the licence text below.
+
+This tool is a short Python script to parse a BLAST XML file, and extract the
+identifiers with description for the top matches (by default the top 3), and
+output these as a simple tabular file along with the query identifiers.
+
+It is available from the Galaxy Tool Shed at:
+http://toolshed.g2.bx.psu.edu/view/peterjc/blastxml_to_top_descr
+
+This requires the 'blast_datatypes' repository from the Galaxy Tool Shed
+to provide the 'blastxml' file format definition.
+
+
+Automated Installation
+======================
+
+This should be straightforward, Galaxy should automatically install the
+'blast_datatypes' dependency.
+
+
+Manual Installation
+===================
+
+If you haven't done so before, first install the 'blast_datatypes' repository.
+
+There are just two files to install (if doing this manually):
+
+* blastxml_to_top_descr.py (the Python script)
+* blastxml_to_top_descr.xml (the Galaxy tool definition)
+
+The suggested location is in the Galaxy folder tools/ncbi_blast_plus next to
+the NCBI BLAST+ tool wrappers.
+
+You will also need to modify the tools_conf.xml file to tell Galaxy to offer
+the tool. e.g. next to the NCBI BLAST+ tools. Simply add the line::
+
+    <tool file="filters/seq_select_by_id.xml" />
+
+To run the tool's tests, also add this line to tools_conf.xml.sample then::
+
+    $ sh run_functional_tests.sh -id blastxml_to_top_descr
+
+
+History
+=======
+
+======= ======================================================================
+Version Changes
+------- ----------------------------------------------------------------------
+v0.0.1  - Initial version.
+v0.0.2  - Since BLAST+ was moved out of the Galaxy core, now have a dependency
+          on the 'blast_datatypes' repository in the Tool Shed.
+v0.0.3  - Include the test files required to run the unit tests
+v0.0.4  - Quote filenames in case they contain spaces (internal change)
+v0.0.5  - Include number of queries with BLAST matches in stdout (peek text)
+v0.0.6  - Check for errors via the script's return code (internal change)
+v0.0.7  - Link to Tool Shed added to help text and this documentation.
+        - Tweak dependency on blast_datatypes to also work on Test Tool Shed
+        - Adopt standard MIT License.
+v0.0.8  - Development moved to GitHub, https://github.com/peterjc/galaxy_blast
+======= ======================================================================
+
+
+Bug Reports
+===========
+
+You can file an issue here https://github.com/peterjc/galaxy_blast/issues or ask
+us on the Galaxy development list http://lists.bx.psu.edu/listinfo/galaxy-dev
+
+
+Developers
+==========
+
+This script and related tools were originally developed on the 'tools' branch of
+the following Mercurial repository: https://bitbucket.org/peterjc/galaxy-central/
+
+As of July 2013, development is continuing on a dedicated GitHub repository:
+https://github.com/peterjc/galaxy_blast
+
+For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball use
+the following command from the GitHub repository root folder::
+
+    $ tar -czf blastxml_to_top_descr.tar.gz blastxml_to_top_descr/README.rst blastxml_to_top_descr/blastxml_to_top_descr.* blastxml_to_top_descr/repository_dependencies.xml test-data/blastp_four_human_vs_rhodopsin.xml test-data/blastp_four_human_vs_rhodopsin_top3.tabular
+
+Check this worked::
+
+    $ tar -tzf blastxml_to_top_descr.tar.gz
+    blastxml_to_top_descr/README.rst
+    blastxml_to_top_descr/blastxml_to_top_descr.py
+    blastxml_to_top_descr/blastxml_to_top_descr.xml
+    blastxml_to_top_descr/repository_dependencies.xml
+    test-data/blastp_four_human_vs_rhodopsin.xml
+    test-data/blastp_four_human_vs_rhodopsin_top3.tabular
+
+
+Licence (MIT)
+=============
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/blastxml_to_top_descr/blastxml_to_top_descr.py	Tue Jul 30 08:07:28 2013 -0400
@@ -0,0 +1,122 @@
+#!/usr/bin/env python
+"""Convert a BLAST XML file to a top hits description table.
+
+Takes three command line options, input BLAST XML filename, output tabular
+BLAST filename, number of hits to collect the descriptions of.
+"""
+import sys
+import re
+
+if "-v" in sys.argv or "--version" in sys.argv:
+    print "v0.0.5"
+    sys.exit(0)
+
+if sys.version_info[:2] >= ( 2, 5 ):
+    import xml.etree.cElementTree as ElementTree
+else:
+    from galaxy import eggs
+    import pkg_resources; pkg_resources.require( "elementtree" )
+    from elementtree import ElementTree
+
+def stop_err( msg ):
+    sys.stderr.write("%s\n" % msg)
+    sys.exit(1)
+
+#Parse Command Line
+try:
+    in_file, out_file, topN = sys.argv[1:]
+except:
+    stop_err("Expect 3 arguments: input BLAST XML file, output tabular file, number of hits")
+
+
+try:
+    topN = int(topN)
+except ValueError:
+    stop_err("Number of hits  argument should be an integer (at least 1)")
+if topN < 1:
+    stop_err("Number of hits  argument should be an integer (at least 1)")
+
+# get an iterable
+try: 
+    context = ElementTree.iterparse(in_file, events=("start", "end"))
+except:
+    stop_err("Invalid data format.")
+# turn it into an iterator
+context = iter(context)
+# get the root element
+try:
+    event, root = context.next()
+except:
+    stop_err( "Invalid data format." )
+
+
+re_default_query_id = re.compile("^Query_\d+$")
+assert re_default_query_id.match("Query_101")
+assert not re_default_query_id.match("Query_101a")
+assert not re_default_query_id.match("MyQuery_101")
+re_default_subject_id = re.compile("^Subject_\d+$")
+assert re_default_subject_id.match("Subject_1")
+assert not re_default_subject_id.match("Subject_")
+assert not re_default_subject_id.match("Subject_12a")
+assert not re_default_subject_id.match("TheSubject_1")
+
+
+count = 0
+pos_count = 0
+outfile = open(out_file, 'w')
+outfile.write("#Query\t%s\n" % "\t".join("BLAST hit %i" % (i+1) for i in range(topN)))
+for event, elem in context:
+    # for every <Iteration> tag
+    if event == "end" and elem.tag == "Iteration":
+        #Expecting either this, from BLAST 2.2.25+ using FASTA vs FASTA
+        # <Iteration_query-ID>sp|Q9BS26|ERP44_HUMAN</Iteration_query-ID>
+        # <Iteration_query-def>Endoplasmic reticulum resident protein 44 OS=Homo sapiens GN=ERP44 PE=1 SV=1</Iteration_query-def>
+        # <Iteration_query-len>406</Iteration_query-len>
+        # <Iteration_hits></Iteration_hits>
+        #
+        #Or, from BLAST 2.2.24+ run online
+        # <Iteration_query-ID>Query_1</Iteration_query-ID>
+        # <Iteration_query-def>Sample</Iteration_query-def>
+        # <Iteration_query-len>516</Iteration_query-len>
+        # <Iteration_hits>...
+        qseqid = elem.findtext("Iteration_query-ID")
+        if qseqid is None:
+            stop_err("Missing <Iteration_query-ID> (could be really old BLAST XML data?)")
+        if re_default_query_id.match(qseqid):
+            #Place holder ID, take the first word of the query definition
+            qseqid = elem.findtext("Iteration_query-def").split(None,1)[0]
+        # for every <Hit> within <Iteration>
+        hit_descrs = []
+        for hit in elem.findall("Iteration_hits/Hit"):
+            #Expecting either this,
+            # <Hit_id>gi|3024260|sp|P56514.1|OPSD_BUFBU</Hit_id>
+            # <Hit_def>RecName: Full=Rhodopsin</Hit_def>
+            # <Hit_accession>P56514</Hit_accession>
+            #or,
+            # <Hit_id>Subject_1</Hit_id>
+            # <Hit_def>gi|57163783|ref|NP_001009242.1| rhodopsin [Felis catus]</Hit_def>
+            # <Hit_accession>Subject_1</Hit_accession>
+            #
+            #apparently depending on the parse_deflines switch
+            sseqid = hit.findtext("Hit_id").split(None,1)[0]
+            hit_def = sseqid + " " + hit.findtext("Hit_def")
+            if re_default_subject_id.match(sseqid) \
+            and sseqid == hit.findtext("Hit_accession"):
+                #Place holder ID, take the first word of the subject definition
+                hit_def = hit.findtext("Hit_def")
+                sseqid = hit_def.split(None,1)[0]
+            assert hit_def not in hit_descrs
+            hit_descrs.append(hit_def)
+        #print "%r has %i hits" % (qseqid, len(hit_descrs))
+        if hit_descrs:
+            pos_count += 1
+        hit_descrs = hit_descrs[:topN]
+        while len(hit_descrs) < topN:
+            hit_descrs.append("")
+        outfile.write("%s\t%s\n" % (qseqid, "\t".join(hit_descrs)))
+        count += 1
+        # prevents ElementTree from growing large datastructure
+        root.clear()
+        elem.clear()
+outfile.close()
+print "Of %i queries, %i had BLAST results" % (count, pos_count)

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/blastxml_to_top_descr/blastxml_to_top_descr.xml	Tue Jul 30 08:07:28 2013 -0400
@@ -0,0 +1,58 @@
+<tool id="blastxml_to_top_descr" name="BLAST top hit descriptions" version="0.0.8">
+    <description>Make a table from BLAST XML</description>
+    <version_command interpreter="python">blastxml_to_top_descr.py --version</version_command>
+    <command interpreter="python">
+      blastxml_to_top_descr.py "${blastxml_file}" "${tabular_file}" ${topN}
+    </command>
+    <stdio>
+        <!-- Assume anything other than zero is an error -->
+        <exit_code range="1:" />
+        <exit_code range=":-1" />
+    </stdio>
+    <inputs>
+        <param name="blastxml_file" type="data" format="blastxml" label="BLAST results as XML"/> 
+	<param name="topN" type="integer" min="1" max="100" optional="false" label="Number of descriptions" value="3"/>
+    </inputs>
+    <outputs>
+        <data name="tabular_file" format="tabular" label="Top $topN descriptions from $blastxml_file.name" />
+    </outputs>
+    <requirements>
+    </requirements>
+    <tests>
+        <test>
+            <param name="blastxml_file" value="blastp_four_human_vs_rhodopsin.xml" ftype="blastxml" />
+            <param name="topN" value="3" />
+            <output name="tabular_file" file="blastp_four_human_vs_rhodopsin_top3.tabular" ftype="tabular" />
+        </test>
+    </tests>
+    <help>
+    
+**What it does**
+
+NCBI BLAST+ (and the older NCBI 'legacy' BLAST) can output in a range of
+formats including text, tabular and a more detailed XML format. You can
+do a lot of things with tabular files in Galaxy (sorting, filtering, joins,
+etc) however currently the BLAST tabular output omits the hit descriptions
+found in the other output formats.
+
+This tool turns a BLAST XML file into a simple tabular file containing
+one row per query sequence, containing the query identifier and then
+the three (by default) top hit descriptions. If a query doesn't have
+that many hits, then these entries are left blank.
+
+**Example Usage**
+
+One simple usage would be to take a transcriptome assembly or set of
+gene predictions, run a BLAST search against the NCBI NR database, and
+then use this tool to make a table of the top three BLAST hits. This
+can give you a 'quick and dirty' crude annotation, potentially enough
+to spot some problems (e.g. bacterial contaimination could be very
+obvious).
+
+**Citation**
+
+This wrapper is available to install into other Galaxy Instances via the Galaxy
+Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/blastxml_to_top_descr
+
+    </help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/blastxml_to_top_descr/repository_dependencies.xml	Tue Jul 30 08:07:28 2013 -0400
@@ -0,0 +1,5 @@
+<?xml version="1.0"?>
+<repositories description="This requires the BLAST datatype definitions (e.g. the BLAST XML format).">
+<!-- Revision 4:f9a7783ed7b6 on the main (and test) tool shed is v0.0.14 which added BLAST databases -->
+<repository changeset_revision="f9a7783ed7b6" name="blast_datatypes" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" />
+</repositories>

--- a/tools/ncbi_blast_plus/blastxml_to_top_descr.py	Wed Jul 24 11:56:22 2013 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,122 +0,0 @@
-#!/usr/bin/env python
-"""Convert a BLAST XML file to a top hits description table.
-
-Takes three command line options, input BLAST XML filename, output tabular
-BLAST filename, number of hits to collect the descriptions of.
-"""
-import sys
-import re
-
-if "-v" in sys.argv or "--version" in sys.argv:
-    print "v0.0.5"
-    sys.exit(0)
-
-if sys.version_info[:2] >= ( 2, 5 ):
-    import xml.etree.cElementTree as ElementTree
-else:
-    from galaxy import eggs
-    import pkg_resources; pkg_resources.require( "elementtree" )
-    from elementtree import ElementTree
-
-def stop_err( msg ):
-    sys.stderr.write("%s\n" % msg)
-    sys.exit(1)
-
-#Parse Command Line
-try:
-    in_file, out_file, topN = sys.argv[1:]
-except:
-    stop_err("Expect 3 arguments: input BLAST XML file, output tabular file, number of hits")
-
-
-try:
-    topN = int(topN)
-except ValueError:
-    stop_err("Number of hits  argument should be an integer (at least 1)")
-if topN < 1:
-    stop_err("Number of hits  argument should be an integer (at least 1)")
-
-# get an iterable
-try: 
-    context = ElementTree.iterparse(in_file, events=("start", "end"))
-except:
-    stop_err("Invalid data format.")
-# turn it into an iterator
-context = iter(context)
-# get the root element
-try:
-    event, root = context.next()
-except:
-    stop_err( "Invalid data format." )
-
-
-re_default_query_id = re.compile("^Query_\d+$")
-assert re_default_query_id.match("Query_101")
-assert not re_default_query_id.match("Query_101a")
-assert not re_default_query_id.match("MyQuery_101")
-re_default_subject_id = re.compile("^Subject_\d+$")
-assert re_default_subject_id.match("Subject_1")
-assert not re_default_subject_id.match("Subject_")
-assert not re_default_subject_id.match("Subject_12a")
-assert not re_default_subject_id.match("TheSubject_1")
-
-
-count = 0
-pos_count = 0
-outfile = open(out_file, 'w')
-outfile.write("#Query\t%s\n" % "\t".join("BLAST hit %i" % (i+1) for i in range(topN)))
-for event, elem in context:
-    # for every <Iteration> tag
-    if event == "end" and elem.tag == "Iteration":
-        #Expecting either this, from BLAST 2.2.25+ using FASTA vs FASTA
-        # <Iteration_query-ID>sp|Q9BS26|ERP44_HUMAN</Iteration_query-ID>
-        # <Iteration_query-def>Endoplasmic reticulum resident protein 44 OS=Homo sapiens GN=ERP44 PE=1 SV=1</Iteration_query-def>
-        # <Iteration_query-len>406</Iteration_query-len>
-        # <Iteration_hits></Iteration_hits>
-        #
-        #Or, from BLAST 2.2.24+ run online
-        # <Iteration_query-ID>Query_1</Iteration_query-ID>
-        # <Iteration_query-def>Sample</Iteration_query-def>
-        # <Iteration_query-len>516</Iteration_query-len>
-        # <Iteration_hits>...
-        qseqid = elem.findtext("Iteration_query-ID")
-        if qseqid is None:
-            stop_err("Missing <Iteration_query-ID> (could be really old BLAST XML data?)")
-        if re_default_query_id.match(qseqid):
-            #Place holder ID, take the first word of the query definition
-            qseqid = elem.findtext("Iteration_query-def").split(None,1)[0]
-        # for every <Hit> within <Iteration>
-        hit_descrs = []
-        for hit in elem.findall("Iteration_hits/Hit"):
-            #Expecting either this,
-            # <Hit_id>gi|3024260|sp|P56514.1|OPSD_BUFBU</Hit_id>
-            # <Hit_def>RecName: Full=Rhodopsin</Hit_def>
-            # <Hit_accession>P56514</Hit_accession>
-            #or,
-            # <Hit_id>Subject_1</Hit_id>
-            # <Hit_def>gi|57163783|ref|NP_001009242.1| rhodopsin [Felis catus]</Hit_def>
-            # <Hit_accession>Subject_1</Hit_accession>
-            #
-            #apparently depending on the parse_deflines switch
-            sseqid = hit.findtext("Hit_id").split(None,1)[0]
-            hit_def = sseqid + " " + hit.findtext("Hit_def")
-            if re_default_subject_id.match(sseqid) \
-            and sseqid == hit.findtext("Hit_accession"):
-                #Place holder ID, take the first word of the subject definition
-                hit_def = hit.findtext("Hit_def")
-                sseqid = hit_def.split(None,1)[0]
-            assert hit_def not in hit_descrs
-            hit_descrs.append(hit_def)
-        #print "%r has %i hits" % (qseqid, len(hit_descrs))
-        if hit_descrs:
-            pos_count += 1
-        hit_descrs = hit_descrs[:topN]
-        while len(hit_descrs) < topN:
-            hit_descrs.append("")
-        outfile.write("%s\t%s\n" % (qseqid, "\t".join(hit_descrs)))
-        count += 1
-        # prevents ElementTree from growing large datastructure
-        root.clear()
-        elem.clear()
-outfile.close()
-print "Of %i queries, %i had BLAST results" % (count, pos_count)

--- a/tools/ncbi_blast_plus/blastxml_to_top_descr.rst	Wed Jul 24 11:56:22 2013 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,109 +0,0 @@
-Galaxy tool to extract top BLAST hit descriptions from BLAST XML
-================================================================
-
-This tool is copyright 2012-2013 by Peter Cock, The James Hutton Institute
-(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
-See the licence text below.
-
-This tool is a short Python script to parse a BLAST XML file, and extract the
-identifiers with description for the top matches (by default the top 3), and
-output these as a simple tabular file along with the query identifiers.
-
-It is available from the Galaxy Tool Shed at:
-http://toolshed.g2.bx.psu.edu/view/peterjc/blastxml_to_top_descr
-
-This requires the 'blast_datatypes' repository from the Galaxy Tool Shed
-to provide the 'blastxml' file format definition.
-
-
-Automated Installation
-======================
-
-This should be straightforward, Galaxy should automatically install the
-'blast_datatypes' dependency.
-
-
-Manual Installation
-===================
-
-If you haven't done so before, first install the 'blast_datatypes' repository.
-
-There are just two files to install (if doing this manually):
-
-* blastxml_to_top_descr.py (the Python script)
-* blastxml_to_top_descr.xml (the Galaxy tool definition)
-
-The suggested location is in the Galaxy folder tools/ncbi_blast_plus next to
-the NCBI BLAST+ tool wrappers.
-
-You will also need to modify the tools_conf.xml file to tell Galaxy to offer
-the tool. e.g. next to the NCBI BLAST+ tools. Simply add the line::
-
-    <tool file="filters/seq_select_by_id.xml" />
-
-To run the tool's tests, also add this line to tools_conf.xml.sample then::
-
-    $ sh run_functional_tests.sh -id blastxml_to_top_descr
-
-
-History
-=======
-
-======= ======================================================================
-Version Changes
-------- ----------------------------------------------------------------------
-v0.0.1  - Initial version.
-v0.0.2  - Since BLAST+ was moved out of the Galaxy core, now have a dependency
-          on the 'blast_datatypes' repository in the Tool Shed.
-v0.0.3  - Include the test files required to run the unit tests
-v0.0.4  - Quote filenames in case they contain spaces (internal change)
-v0.0.5  - Include number of queries with BLAST matches in stdout (peek text)
-v0.0.6  - Check for errors via the script's return code (internal change)
-v0.0.7  - Link to Tool Shed added to help text and this documentation.
-        - Tweak dependency on blast_datatypes to also work on Test Tool Shed
-        - Adopt standard MIT License.
-======= ======================================================================
-
-
-Developers
-==========
-
-This script and related tools are being developed on the following hg branch:
-http://bitbucket.org/peterjc/galaxy-central/src/tools
-
-For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball use
-the following command from the Galaxy root folder::
-
-    $ tar -czf blastxml_to_top_descr.tar.gz tools/ncbi_blast_plus/blastxml_to_top_descr.* tools/ncbi_blast_plus/repository_dependencies.xml test-data/blastp_four_human_vs_rhodopsin.xml test-data/blastp_four_human_vs_rhodopsin_top3.tabular
-
-Check this worked::
-
-    $ tar -tzf blastxml_to_top_descr.tar.gz
-    tools/ncbi_blast_plus/blastxml_to_top_descr.py
-    tools/ncbi_blast_plus/blastxml_to_top_descr.rst
-    tools/ncbi_blast_plus/blastxml_to_top_descr.xml
-    tools/ncbi_blast_plus/repository_dependencies.xml
-    test-data/blastp_four_human_vs_rhodopsin.xml
-    test-data/blastp_four_human_vs_rhodopsin_top3.tabular
-
-
-Licence (MIT)
-=============
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.

--- a/tools/ncbi_blast_plus/blastxml_to_top_descr.xml	Wed Jul 24 11:56:22 2013 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,58 +0,0 @@
-<tool id="blastxml_to_top_descr" name="BLAST top hit descriptions" version="0.0.7">
-    <description>Make a table from BLAST XML</description>
-    <version_command interpreter="python">blastxml_to_top_descr.py --version</version_command>
-    <command interpreter="python">
-      blastxml_to_top_descr.py "${blastxml_file}" "${tabular_file}" ${topN}
-    </command>
-    <stdio>
-        <!-- Assume anything other than zero is an error -->
-        <exit_code range="1:" />
-        <exit_code range=":-1" />
-    </stdio>
-    <inputs>
-        <param name="blastxml_file" type="data" format="blastxml" label="BLAST results as XML"/> 
-	<param name="topN" type="integer" min="1" max="100" optional="false" label="Number of descriptions" value="3"/>
-    </inputs>
-    <outputs>
-        <data name="tabular_file" format="tabular" label="Top $topN descriptions from $blastxml_file.name" />
-    </outputs>
-    <requirements>
-    </requirements>
-    <tests>
-        <test>
-            <param name="blastxml_file" value="blastp_four_human_vs_rhodopsin.xml" ftype="blastxml" />
-            <param name="topN" value="3" />
-            <output name="tabular_file" file="blastp_four_human_vs_rhodopsin_top3.tabular" ftype="tabular" />
-        </test>
-    </tests>
-    <help>
-    
-**What it does**
-
-NCBI BLAST+ (and the older NCBI 'legacy' BLAST) can output in a range of
-formats including text, tabular and a more detailed XML format. You can
-do a lot of things with tabular files in Galaxy (sorting, filtering, joins,
-etc) however currently the BLAST tabular output omits the hit descriptions
-found in the other output formats.
-
-This tool turns a BLAST XML file into a simple tabular file containing
-one row per query sequence, containing the query identifier and then
-the three (by default) top hit descriptions. If a query doesn't have
-that many hits, then these entries are left blank.
-
-**Example Usage**
-
-One simple usage would be to take a transcriptome assembly or set of
-gene predictions, run a BLAST search against the NCBI NR database, and
-then use this tool to make a table of the top three BLAST hits. This
-can give you a 'quick and dirty' crude annotation, potentially enough
-to spot some problems (e.g. bacterial contaimination could be very
-obvious).
-
-**Citation**
-
-This wrapper is available to install into other Galaxy Instances via the Galaxy
-Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/blastxml_to_top_descr
-
-    </help>
-</tool>

--- a/tools/ncbi_blast_plus/repository_dependencies.xml	Wed Jul 24 11:56:22 2013 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,5 +0,0 @@
-<?xml version="1.0"?>
-<repositories description="This requires the BLAST datatype definitions (e.g. the BLAST XML format).">
-<!-- Revision 4:f9a7783ed7b6 on the main (and test) tool shed is v0.0.14 which added BLAST databases -->
-<repository changeset_revision="f9a7783ed7b6" name="blast_datatypes" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" />
-</repositories>