Mercurial > repos > peterjc > sff_filter_by_id

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/filters/sff_filter_by_id.py	Tue Jun 07 17:24:49 2011 -0400
@@ -0,0 +1,97 @@
+#!/usr/bin/env python
+"""Filter an SSF file with IDs from a tabular file, e.g. from BLAST.
+
+Takes five command line options, tabular filename, ID column numbers
+(comma separated list using one based counting), input SFF filename, and
+two output SFF filenames (for records with and without the given IDs).
+
+Any Roche XML manifest in the input file is preserved in both output files.
+
+Note in the default NCBI BLAST+ tabular output, the query sequence ID is
+in column one, and the ID of the match from the database is in column two.
+Here sensible values for the column numbers would therefore be "1" or "2".
+"""
+import sys
+
+def stop_err(msg, err=1):
+    sys.stderr.write(msg.rstrip() + "\n")
+    sys.exit(err)
+
+try:
+    from Bio.SeqIO.SffIO import SffIterator, SffWriter
+except ImportError:
+    stop_err("Requires Biopython 1.54 or later")
+
+try:
+    from Bio.SeqIO.SffIO import ReadRocheXmlManifest
+except ImportError:
+    #Prior to Biopython 1.56 this was a private function
+    from Bio.SeqIO.SffIO import _sff_read_roche_index_xml as ReadRocheXmlManifest
+
+#Parse Command Line
+try:
+    tabular_file, cols_arg, in_file, out_positive_file, out_negative_file = sys.argv[1:]
+except ValueError:
+    stop_err("Expected five arguments, got %i:\n%s" % (len(sys.argv)-1, " ".join(sys.argv)))
+try:
+    columns = [int(arg)-1 for arg in cols_arg.split(",")]
+except ValueError:
+    stop_err("Expected list of columns (comma separated integers), got %s" % cols_arg)
+
+#Read tabular file and record all specified identifiers
+ids = set()
+handle = open(tabular_file, "rU")
+if len(columns)>1:
+    #General case of many columns
+    for line in handle:
+        if line.startswith("#"):
+            #Ignore comments
+            continue
+        parts = line.rstrip("\n").split("\t")
+        for col in columns:
+            ids.add(parts[col])
+    print "Using %i IDs from %i columns of tabular file" % (len(ids), len(columns))
+else:
+    #Single column, special case speed up
+    col = columns[0]
+    for line in handle:
+        if not line.startswith("#"):
+            ids.add(line.rstrip("\n").split("\t")[col])
+    print "Using %i IDs from tabular file" % (len(ids))
+handle.close()
+
+#Now write filtered SFF file based on IDs from BLAST file
+in_handle = open(in_file, "rb") #must be binary mode!
+try:
+    manifest = ReadRocheXmlManifest(in_handle)
+except ValueError:
+    manifest = None
+
+#This makes two passes though the SFF file with isn't so efficient,
+#but this makes the code simple.
+
+if out_positive_file != "-":
+    out_handle = open(out_positive_file, "wb")
+    writer = SffWriter(out_handle, xml=manifest)
+    in_handle.seek(0) #start again after getting manifest
+    pos_count = writer.write_file(rec for rec in SffIterator(in_handle) if rec.id in ids)
+    out_handle.close()
+
+if out_negative_file != "-":
+    out_handle = open(out_negative_file, "wb")
+    writer = SffWriter(out_handle, xml=manifest)
+    in_handle.seek(0) #start again
+    neg_count = writer.write_file(rec for rec in SffIterator(in_handle) if rec.id not in ids)
+    out_handle.close()
+
+#And we're done
+in_handle.close()
+
+if out_positive_file != "-" and out_negative_file != "-":
+    print "%i with and %i without specified IDs" % (pos_count, neg_count)
+elif out_positive_file != "-":
+    print "%i with specified IDs" % pos_count
+elif out_negative_file != "-":
+    print "%i without specified IDs" % neg_count
+else:
+    stop_err("Neither output file requested")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/filters/sff_filter_by_id.txt	Tue Jun 07 17:24:49 2011 -0400
@@ -0,0 +1,74 @@
+Galaxy tool to filter SFF sequences by ID
+=========================================
+
+This tool is copyright 2010 by Peter Cock, SCRI, UK. All rights reserved.
+See the licence text below.
+
+This tool is a short Python script (using the Biopython library functions) which
+divides an SFF file in two, those sequences with or without an ID present in
+the specified column(s) of a tabular file. Example uses include filtering based
+on search results from a tool like NCBI BLAST before assembly.
+
+There are just two files to install:
+
+* sff_filter_by_id.py (the Python script)
+* sff_filter_by_id.xml (the Galaxy tool definition)
+
+The suggested location is in the Galaxy folder tools/filters next to the tool
+for calling sff_extract.py for converting SFF to FASTQ or FASTA + QUAL.
+
+You will also need to modify the tools_conf.xml file to tell Galaxy to offer
+the tool. One suggested location is next to the sff_extractor.xml entry. Simply
+add the line:
+
+<tool file="filters/sff_filter_by_id.xml" />
+
+You will also need to install Biopython 1.54 or later. That's it.
+
+
+History
+=======
+
+v0.0.1 - Initial version
+
+
+Developers
+==========
+
+This script and similar versions for FASTA and FASTQ files are currently being
+developed on the following hg branch:
+http://bitbucket.org/peterjc/galaxy-central/src/fasta_filter
+
+For making the "Galaxy Tool Shed" http://community.g2.bx.psu.edu/ tarball use
+the following command from the Galaxy root folder:
+
+tar -czf sff_filter_by_id.tar.gz tools/filters/sff_filter_by_id.*
+
+Check this worked:
+
+$ tar -tzf sff_filter_by_id.tar.gz
+filter/sff_filter_by_id.py
+filter/sff_filter_by_id.txt
+filter/sff_filter_by_id.xml
+
+
+Licence (MIT/BSD style)
+=======================
+
+Permission to use, copy, modify, and distribute this software and its
+documentation with or without modifications and for any purpose and
+without fee is hereby granted, provided that any copyright notices
+appear in all copies and that both those copyright notices and this
+permission notice appear in supporting documentation, and that the
+names of the contributors or copyright holders not be used in
+advertising or publicity pertaining to distribution of the software
+without specific prior permission.
+
+THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL
+WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE
+CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT
+OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
+OR PERFORMANCE OF THIS SOFTWARE.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/filters/sff_filter_by_id.xml	Tue Jun 07 17:24:49 2011 -0400
@@ -0,0 +1,76 @@
+<tool id="sff_filter_by_id" name="Filter SFF by ID" version="0.0.1">
+	<description>from a tabular file</description>
+	<command interpreter="python">
+sff_filter_by_id.py $input_tabular $columns $input_sff
+#if $output_choice_cond.output_choice=="both"
+ $output_pos $output_neg
+#elif $output_choice_cond.output_choice=="pos"
+ $output_pos -
+#elif $output_choice_cond.output_choice=="neg"
+ - $output_neg
+#end if
+	</command>
+	<inputs>
+		<param name="input_sff" type="data" format="sff" label="SFF file to filter on the identifiers"/>
+		<param name="input_tabular" type="data" format="tabular" label="Tabular file containing SFF identifiers"/>
+		<param name="columns" type="data_column" data_ref="input_tabular" multiple="True" numerical="False" label="Column(s) containing SFF identifiers" help="Multi-select list - hold the appropriate key while clicking to select multiple columns">
+			<validator type="no_options" message="Pick at least one column"/>
+		</param>
+		<conditional name="output_choice_cond">
+			<param name="output_choice" type="select" label="Output positive matches, negative matches, or both?">
+				<option value="both">Both positive matches (ID on list) and negative matches (ID not on list), as two SFF files</option>
+				<option value="pos">Just positive matches (ID on list), as a single SFF file</option>
+				<option value="neg">Just negative matches (ID not on list), as a single SFF file</option>
+			</param>
+			<!-- Seems need these dummy entries here, compare this to indels/indel_sam2interval.xml -->
+			<when value="both" />
+			<when value="pos" />
+			<when value="neg" />
+		</conditional>
+	</inputs>
+	<outputs>
+		<data name="output_pos" format="sff" label="With matched ID">
+			<filter>output_choice_cond["output_choice"] != "neg"</filter>
+		</data>
+		<data name="output_neg" format="sff" label="Without matched ID">
+			<filter>output_choice_cond["output_choice"] != "pos"</filter>
+		</data>
+	</outputs>
+	<tests>
+	</tests>
+	<requirements>
+		<requirement type="python-module">Bio</requirement>
+	</requirements>
+	<help>
+
+**What it does**
+
+By default it divides a Standard Flowgram Format (SFF) file in two, those
+sequences with or without an ID present in the tabular file column(s) specified.
+You can opt to have a single output file of just the matching records, or just
+the non-matching ones.
+
+Note that the order of sequences in the original SFF file is preserved, as is
+any Roche XML Manifest. Also, if any sequences share an identifier (which would
+be very unusual in SFF files, duplicates are not removed).
+
+**Example Usage**
+
+You may have performed some kind of contamination search, for example running
+BLASTN against a database of cloning vectors or bacteria, giving you a tabular
+file containing read identifiers. You could use this tool to extract only the
+reads without BLAST matches (i.e. those which do not match your contaminant
+database).
+
+** Citation **
+
+This tool uses Biopython to read and write SFF files. If you use this tool in
+scientific work leading to a publication, please cite the Biopython application
+note:
+
+Cock et al 2009. Biopython: freely available Python tools for computational
+molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
+http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
+
+	</help>
+</tool>