Mercurial > repos > ieguinoa > data_manager_fetch_tx2gene

changeset 3:d71f65b854de draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author ieguinoa
date Fri, 19 Oct 2018 07:36:02 -0400
parents 7d3ffe28ff3f
children bacd91d8b05a
files data_manager/data_manager_fetch_tx2gene.py data_manager/data_manager_fetch_tx2gene.xml data_manager/get_tx2gene_table.R tool-data/tx2gene.loc.sample tool_data_table_conf.xml.sample
diffstat 5 files changed, 67 insertions(+), 28 deletions(-) [+]
line wrap: on
line diff
--- a/data_manager/data_manager_fetch_tx2gene.py	Wed Oct 10 11:44:17 2018 -0400
+++ b/data_manager/data_manager_fetch_tx2gene.py	Fri Oct 19 07:36:02 2018 -0400
@@ -11,6 +11,7 @@
 import zipfile
 import gzip
 import bz2
+import subprocess
 try:
     # For Python 3.0 and later
     from urllib.request import urlopen
@@ -93,20 +94,35 @@
     return [ bz2.BZ2File( fh.name, 'rb') ]
 
 
-def convert_tx2gene( fasta_filename, file_type, params ):
-    if file_type is 'tx2gene':
+def convert_to_tx2gene( rscript_gff_to_tx2gene, fasta_filename, file_type, params ):
+    if file_type == 'tx2gene':
         return   #no need to extract tx2gene table
+    #print file_type
     #If the file is actually a GFF/GTF file then extract the tx2gene
     gff_temp_filename = tempfile.NamedTemporaryFile().name
     shutil.move(fasta_filename, gff_temp_filename)
     args= ['Rscript']
-    args.append(RSCRIPT_GFF_TO_TX2GENE)
-    args.append(gff_temp_filename)
-    args.append(fasta_filename)
+    args.append(rscript_gff_to_tx2gene)
+    args.extend(['-x',gff_temp_filename])
+    args.extend(['-o',fasta_filename])
+    args.extend(['-t',file_type])
+    tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-stderr" )
+    return_code = subprocess.call( args=args, shell=False, stderr=tmp_stderr.fileno() )
+    #return_code = subprocess.call( args=args, shell=False, stderr=None)
+    if return_code:
+        tmp_stderr.flush()
+        tmp_stderr.seek(0)
+        print >> sys.stderr, "Error in process call"
+        while True:
+            chunk = tmp_stderr.read( CHUNK_SIZE )
+            if not chunk:
+                break
+            sys.stderr.write( chunk )
+        sys.exit( return_code )
+    tmp_stderr.close()
 
-    #assert sort_method in SORTING_METHODS, ValueError( "%s is not a valid sorting option." % sort_method )
-    #return SORTING_METHODS[ sort_method ]( fasta_filename, params )
-    
+
+
 def _download_file(start, fh):
     tmp = tempfile.NamedTemporaryFile()
     tmp.write(start)
@@ -143,29 +159,29 @@
 
 
 
-def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params):
-    for data_table_name, data_table_entry in _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ):
+def add_fasta_to_table(rscript_gff_to_tx2gene, data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params):
+    for data_table_name, data_table_entry in _stream_fasta_to_file(rscript_gff_to_tx2gene, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ):
         if data_table_entry:
             _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name )
 
 
-def download_from_url( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
+def download_from_url(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
     urls = filter( bool, map( lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split( '\n' ) ) )
     fasta_readers = [ get_stream_reader(urlopen( url ), tmp_dir) for url in urls ]
-    add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params)
+    add_fasta_to_table(rscript_gff_to_tx2gene,data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params)
 
 
-def download_from_history( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
+def download_from_history(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
     #TODO: allow multiple FASTA input files
     input_filename = params['param_dict']['reference_source']['input_fasta']
     if isinstance( input_filename, list ):
         fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ]
     else:
         fasta_readers = get_stream_reader(open(input_filename), tmp_dir)
-    add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params)
+    add_fasta_to_table(rscript_gff_to_tx2gene,data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params)
 
 
-def copy_from_directory( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
+def copy_from_directory(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
     input_filename = params['param_dict']['reference_source']['fasta_filename']
     create_symlink = params['param_dict']['reference_source']['create_symlink'] == 'create_symlink'
     if create_symlink:
@@ -175,7 +191,7 @@
             fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ]
         else:
             fasta_readers = get_stream_reader(open(input_filename), tmp_dir)
-        data_table_entries = _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params )
+        data_table_entries = _stream_fasta_to_file(rscript_gff_to_tx2gene, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params )
     for data_table_name, data_table_entry in data_table_entries:
         if data_table_entry:
             _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name )
@@ -188,7 +204,7 @@
     return data_manager_dict
 
 
-def _stream_fasta_to_file( fasta_stream, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, close_stream=True ):
+def _stream_fasta_to_file( rscript_gff_to_tx2gene, fasta_stream, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, close_stream=True ):
     fasta_base_filename = "%s_tx2gene.tab" % sequence_id
     fasta_filename = os.path.join( target_directory, fasta_base_filename )
     with open( fasta_filename, 'wb+' ) as fasta_writer:
@@ -220,7 +236,7 @@
             if close_stream:
                 fasta_stream.close()
 
-    convert_to_tx2gene( fasta_filename, params['param_dict']['file_type'], params )
+    convert_to_tx2gene( rscript_gff_to_tx2gene,fasta_filename, params['param_dict']['file_type'], params )
     return [ ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ]
 
 
@@ -271,17 +287,17 @@
     #Parse Command Line
     parser = optparse.OptionParser()
     parser.add_option( '-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description' )
+    parser.add_option( '-b', '--base_dir', dest='base_dir', action='store', type='string', default=None, help='base_dir')
     parser.add_option( '-t', '--type', dest='file_type', action='store', type='string', default=None, help='file_type')
     (options, args) = parser.parse_args()
     
     filename = args[0]
     #global DATA_TABLE_NAME
-    global RSCRIPT_GFF_TO_TX2GENE= os.path.join( options.base_dir, 'tximport.r')
-
+    rscript_gff_to_tx2gene=os.path.join( options.base_dir, 'get_tx2gene_table.R')
 
-    if options.file_type == 'gff_gtf':
-        #DATA_TABLE_NAME= 'representative_gff'
-    else:   #file_type='tx2gene'
+    #input_type='gff_gtf'
+    #if options.file_type != 'gff_gtf':
+    # 	file_type='tx2gene'
         
     params = loads( open( filename ).read() )
     target_directory = params[ 'output_data' ][0]['extra_files_path']
@@ -297,7 +313,7 @@
     tmp_dir = tempfile.mkdtemp()
     #Fetch the input file
     try:
-        REFERENCE_SOURCE_TO_DOWNLOAD[ params['param_dict']['reference_source']['reference_source_selector'] ]( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir)
+        REFERENCE_SOURCE_TO_DOWNLOAD[ params['param_dict']['reference_source']['reference_source_selector'] ]( rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir)
     finally:
         cleanup_before_exit(tmp_dir)
     #save info to json file
--- a/data_manager/data_manager_fetch_tx2gene.xml	Wed Oct 10 11:44:17 2018 -0400
+++ b/data_manager/data_manager_fetch_tx2gene.xml	Fri Oct 19 07:36:02 2018 -0400
@@ -1,5 +1,10 @@
 <tool id="data_manager_fetch_tx2gene" name="Create entries in tx2gene data table" version="0.0.1" tool_type="manage_data">
     <description>fetching</description>
+    <requirements>
+        <requirement type="package" version="1.26.4">bioconductor-genomicfeatures</requirement>
+        <requirement type="package">r-getopt</requirement>
+    </requirements>
+
     <command><![CDATA[
        python "$__tool_directory__"/data_manager_fetch_tx2gene.py "${out_file}"
        --type $file_type
@@ -14,9 +19,10 @@
         <param type="text" name="sequence_id" value="" label="ID for sequence" />
  
         <param name="file_type" type="select" label="Select input type: GFF/GTF file(features will be extracted to create tx2gene table) or transcript to gene table file(tab separated)">
-                <option value="gff_gtf">GFF/GTF file</option>
+                <option value="gtf">GTF file</option>
+                <option value="gff3">GFF3 file</option>
                 <option value="tx2gene">tx2gene</option>
-            </param>
+        </param>
 	<conditional name="reference_source">
 	    <param name="reference_source_selector" type="select" label="Choose the source for the reference genome">
 		<option value="url">URL</option>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/get_tx2gene_table.R	Fri Oct 19 07:36:02 2018 -0400
@@ -0,0 +1,17 @@
+library(getopt)
+
+# we read the options from the default: commandArgs(TRUE).
+spec <- matrix(c(
+  "input_type", "t", 1, "character",
+  "outfile", "o", 1, "character",
+  "gtfFile", "x", 1, "character"),
+  byrow=TRUE, ncol=4)
+opt <- getopt(spec)
+
+suppressPackageStartupMessages({library("GenomicFeatures")})
+txdb <- makeTxDbFromGFF(opt$gtfFile, format=opt$input_type)
+k <- keys(txdb, keytype = "GENEID")
+df <- select(txdb, keys = k, keytype = "GENEID", columns = "TXNAME")
+tx2gene <- df[, 2:1] # tx ID, then gene ID
+write.table(tx2gene,file = opt$outfile, quote = FALSE, sep = " ",row.names = FALSE,col.names = FALSE)
+
--- a/tool-data/tx2gene.loc.sample	Wed Oct 10 11:44:17 2018 -0400
+++ b/tool-data/tx2gene.loc.sample	Fri Oct 19 07:36:02 2018 -0400
@@ -1,3 +1,3 @@
 #The tx2gene.loc file has this format:
 #
-#<unique_build_id>	<dbkey>	<display_name>	<path_to_gff_file>
+#<unique_build_id>	<dbkey>	<display_name>	<path_to_tx2gene_file>
--- a/tool_data_table_conf.xml.sample	Wed Oct 10 11:44:17 2018 -0400
+++ b/tool_data_table_conf.xml.sample	Fri Oct 19 07:36:02 2018 -0400
@@ -1,4 +1,4 @@
 <?xml version="1.0"?>
 <tables>
-	<table name="tx2gene_table" comment_char="#" allow_duplicate_entries="False"><columns>value, dbkey, name, path</columns><file path="tool-data/tx2gene.loc" /></table>
+	<table name="tx2gene" comment_char="#" allow_duplicate_entries="False"><columns>value, dbkey, name, path</columns><file path="tool-data/tx2gene.loc" /></table>
 </tables>