Mercurial > repos > simonl > agile_wrapper

changeset 0:d6a426afaa46 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 1.0.0 from old tool shed archive to new tool shed repository
author simonl
date Tue, 07 Jun 2011 16:22:51 -0400
parents
children
files Users/oconnorlab/Desktop/agile/agile_wrapper.py Users/oconnorlab/Desktop/agile/agile_wrapper.xml
diffstat 2 files changed, 171 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Users/oconnorlab/Desktop/agile/agile_wrapper.py	Tue Jun 07 16:22:51 2011 -0400
@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+
+import os, sys, tempfile
+
+assert sys.version_info[:2] >= (2.4)
+
+def stop_err( msg ):
+    sys.stderr.write( "%s\n" % msg )
+    sys.exit()
+    
+def check_nib_file( dbkey, GALAXY_DATA_INDEX_DIR ):
+    nib_file = "%s/alignseq.loc" % GALAXY_DATA_INDEX_DIR
+    nib_path = ''
+    nibs = {}
+    for i, line in enumerate( file( nib_file ) ):
+        line = line.rstrip( '\r\n' )
+        if line and not line.startswith( "#" ):
+            fields = line.split( '\t' )
+            if len( fields ) < 3:
+                continue
+            if fields[0] == 'seq':
+                nibs[( fields[1] )] = fields[2]
+    if nibs.has_key( dbkey ):
+        nib_path = nibs[( dbkey )]
+    return nib_path
+
+def check_twobit_file( dbkey, GALAXY_DATA_INDEX_DIR ):
+    twobit_file = "%s/twobit.loc" % GALAXY_DATA_INDEX_DIR
+    twobit_path = ''
+    twobits = {}
+    for i, line in enumerate( file( twobit_file ) ):
+        line = line.rstrip( '\r\n' )
+        if line and not line.startswith( "#" ): 
+            fields = line.split( '\t' )
+            if len( fields ) < 2:
+                continue
+            twobits[( fields[0] )] = fields[1]
+    if twobits.has_key( dbkey ):
+        twobit_path = twobits[( dbkey )]
+    return twobit_path
+
+def __main__():
+    # I/O
+    source_format = sys.argv[1]        # 0: dbkey; 1: upload file
+    target_file = sys.argv[2]
+    query_file = sys.argv[3]
+    output_file = sys.argv[4]
+    max_sims = sys.argv[5]
+    tile_size = sys.argv[6]
+    max_freq = sys.argv[7]
+    out_type = sys.argv[8]
+    all_match = sys.argv[9]
+    
+    GALAXY_DATA_INDEX_DIR = sys.argv[10]
+
+    all_files = []
+    if source_format == '0':
+        # check target genome
+        dbkey = target_file
+        nib_path = check_nib_file( dbkey, GALAXY_DATA_INDEX_DIR )
+        twobit_path = check_twobit_file( dbkey, GALAXY_DATA_INDEX_DIR )
+        if not os.path.exists( nib_path ) and not os.path.exists( twobit_path ):
+            stop_err("No sequences are available for %s, request them by reporting this error." % dbkey)
+    
+        # check the query file, see whether all of them are legitimate sequence
+        if nib_path and os.path.isdir( nib_path ):
+            compress_files = os.listdir(nib_path)
+            target_path = nib_path
+        elif twobit_path:
+            compress_files = [twobit_path]
+            target_path = ""
+        else:
+            stop_err("Requested genome build has no available sequence.")
+            
+        for file in compress_files:
+            file = "%s/%s" % ( target_path, file )
+            file = os.path.normpath(file)
+            all_files.append(file)
+    else:
+        all_files = [target_file]
+        
+    for detail_file_path in all_files:
+        output_tempfile = tempfile.NamedTemporaryFile().name
+        if all_match == "true":
+	        command = "agile %s %s -maxSIMs=%s -tileSize=%s -maxFreq=%s -out=%s -all %s 2>&1" % ( detail_file_path, query_file, max_sims, tile_size, max_freq, out_type, output_tempfile )
+        else:
+	        command = "agile %s %s -maxSIMs=%s -tileSize=%s -maxFreq=%s -out=%s %s 2>&1" % ( detail_file_path, query_file, max_sims, tile_size, max_freq, out_type, output_tempfile )		
+
+        os.system( command )
+        os.system( 'cat %s >> %s' % ( output_tempfile, output_file ) )
+        os.remove( output_tempfile )
+        
+if __name__ == '__main__': __main__()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Users/oconnorlab/Desktop/agile/agile_wrapper.xml	Tue Jun 07 16:22:51 2011 -0400
@@ -0,0 +1,78 @@
+<tool id="agile_wrapper" name="AGILE" version="1.0.0">
+  <description> Quickly match reads to a reference genome or sequence file</description>
+  <command interpreter="python">
+    #if $source.source_select=="database" #agile_wrapper.py 0 $source.dbkey $input_query $output1 $max_sims $tile_size $max_freq $out_type $all
+    #else                                 #agile_wrapper.py 1 $source.input_target $input_query $output1 $max_sims $tile_size $max_freq $out_type $all
+    #end if# ${GALAXY_DATA_INDEX_DIR}
+  </command>
+	<inputs>
+	<conditional name="source">
+		<param name="source_select" type="select" label="Target source">
+				<option value="database">Genome Build</option>
+				<option value="input_ref">Your Upload File</option>
+		</param>
+		<when value="database">
+			<param name="dbkey" type="genomebuild" label="Genome" />
+		</when>
+		<when value="input_ref">
+			<param name="input_target" type="data" label="Reference sequence" />
+ 		</when>
+	</conditional>	
+		<param name="input_query" type="data" format="fasta" label="Query sequences file"/>
+		<param name="max_sims" type="integer" size="15" value="7" label="Maximum number of Single Imperfect Matches (SIMs) allowed as percentage of read length (-maxSIMs, default 7)" />
+		<param name="tile_size" type="integer" size="15" value="20" label="Sets the length of tuples for creating hash table (-tileSize, default 20)" help="Usually between 11 and 20."/>
+		<param name="max_freq" type="integer" size="15" value="8" label="Maximum number of occurrences of a pattern (k-tupple) allowed (-maxFreq, default 8"/>
+		<param name="all" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Output all matches? (-all, default true for MHC)"/>
+		<param name="out_type" type="select" label="Output Format (-out default pslx for MHC">
+				<option value="pslx">pslx</option>
+				<option value="psl">psl</option>
+				<option value="axt">axt</option>
+				<option value="maf">maf</option>
+				<option value="sim4">sim4</option>
+				<option value="wublast">wublast</option>				
+				<option value="blast">blast</option>
+				<option value="blast8">blast8</option>
+				<option value="blast9">blast9</option>
+		</param>
+	</inputs>
+	<outputs>
+		<data name="output1" format="tabular"/>
+	</outputs>
+	<requirements>
+	    <requirement type="binary">agile</requirement>
+	</requirements>
+	<help>
+	
+.. class:: warningmark 
+
+The default parameter values can be altered in the agile tool xml file
+
+-----
+	
+**What it does**
+ 
+This tool uses the **AGILE** alignment program, a faster replacement for the **BLAT** algorithm. Your reads file is searched against a genome build or another uploaded file. 
+
+-----
+
+**Parameters**
+
+- *Maximum Single Imperfect Matches* (**-maxSIMs**) : The number of allowable mismatches as a percentage of read length.
+
+- *Tuple Length* (**-tileSize**) : The length of tuples for craring a hash table.
+
+- *Maximum Frequency* (**-maxFreq**) : The maximum number of pattern occurrences allowed.
+
+- *All Matches* (**-all**) : Output all matches satisfying the match criteria (true/false).
+
+- *Output Format* (**-out**) : Define the output format for the match file.
+
+-----
+
+**Reference**
+ 
+ **AGILE**: Sanchit Misra, Ankit Agrawal, Wei-keng Liao, Alok Choudhary. Anatomy of a Hash-based Long Read Sequence Mapping Algorithm for Next Generation DNA Sequencing. Bioinformatics 2010; doi: 10.1093/bioinformatics/btq648.
+
+
+	</help>
+</tool>