| Previous changeset 2:7d3ffe28ff3f (2018-10-10) Next changeset 4:bacd91d8b05a (2018-10-21) |
|
Commit message:
Uploaded |
|
modified:
data_manager/data_manager_fetch_tx2gene.py data_manager/data_manager_fetch_tx2gene.xml tool-data/tx2gene.loc.sample tool_data_table_conf.xml.sample |
|
added:
data_manager/get_tx2gene_table.R |
| b |
| diff -r 7d3ffe28ff3f -r d71f65b854de data_manager/data_manager_fetch_tx2gene.py --- 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 |
| [ |
| b'@@ -11,6 +11,7 @@\n import zipfile\n import gzip\n import bz2\n+import subprocess\n try:\n # For Python 3.0 and later\n from urllib.request import urlopen\n@@ -93,20 +94,35 @@\n return [ bz2.BZ2File( fh.name, \'rb\') ]\n \n \n-def convert_tx2gene( fasta_filename, file_type, params ):\n- if file_type is \'tx2gene\':\n+def convert_to_tx2gene( rscript_gff_to_tx2gene, fasta_filename, file_type, params ):\n+ if file_type == \'tx2gene\':\n return #no need to extract tx2gene table\n+ #print file_type\n #If the file is actually a GFF/GTF file then extract the tx2gene\n gff_temp_filename = tempfile.NamedTemporaryFile().name\n shutil.move(fasta_filename, gff_temp_filename)\n args= [\'Rscript\']\n- args.append(RSCRIPT_GFF_TO_TX2GENE)\n- args.append(gff_temp_filename)\n- args.append(fasta_filename)\n+ args.append(rscript_gff_to_tx2gene)\n+ args.extend([\'-x\',gff_temp_filename])\n+ args.extend([\'-o\',fasta_filename])\n+ args.extend([\'-t\',file_type])\n+ tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-stderr" )\n+ return_code = subprocess.call( args=args, shell=False, stderr=tmp_stderr.fileno() )\n+ #return_code = subprocess.call( args=args, shell=False, stderr=None)\n+ if return_code:\n+ tmp_stderr.flush()\n+ tmp_stderr.seek(0)\n+ print >> sys.stderr, "Error in process call"\n+ while True:\n+ chunk = tmp_stderr.read( CHUNK_SIZE )\n+ if not chunk:\n+ break\n+ sys.stderr.write( chunk )\n+ sys.exit( return_code )\n+ tmp_stderr.close()\n \n- #assert sort_method in SORTING_METHODS, ValueError( "%s is not a valid sorting option." % sort_method )\n- #return SORTING_METHODS[ sort_method ]( fasta_filename, params )\n- \n+\n+\n def _download_file(start, fh):\n tmp = tempfile.NamedTemporaryFile()\n tmp.write(start)\n@@ -143,29 +159,29 @@\n \n \n \n-def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params):\n- for data_table_name, data_table_entry in _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ):\n+def add_fasta_to_table(rscript_gff_to_tx2gene, data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params):\n+ 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 ):\n if data_table_entry:\n _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name )\n \n \n-def download_from_url( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n+def download_from_url(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n urls = filter( bool, map( lambda x: x.strip(), params[\'param_dict\'][\'reference_source\'][\'user_url\'].split( \'\\n\' ) ) )\n fasta_readers = [ get_stream_reader(urlopen( url ), tmp_dir) for url in urls ]\n- add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params)\n+ add_fasta_to_table(rscript_gff_to_tx2gene,data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params)\n \n \n-def download_from_history( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n+def download_from_history(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n #TODO: allow multiple FASTA input files\n input_filename = params[\'param_dict\'][\'reference_source\'][\'input_fasta\']\n if isinstance( input_filename, list ):\n fasta_readers = [ get_stream_reader(open(filename, \'rb\'), tmp_dir) for filename in input_filename ]\n else:\n fasta_readers ='..b'_to_tx2gene,data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params)\n \n \n-def copy_from_directory( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n+def copy_from_directory(rscript_gff_to_tx2gene, data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):\n input_filename = params[\'param_dict\'][\'reference_source\'][\'fasta_filename\']\n create_symlink = params[\'param_dict\'][\'reference_source\'][\'create_symlink\'] == \'create_symlink\'\n if create_symlink:\n@@ -175,7 +191,7 @@\n fasta_readers = [ get_stream_reader(open(filename, \'rb\'), tmp_dir) for filename in input_filename ]\n else:\n fasta_readers = get_stream_reader(open(input_filename), tmp_dir)\n- data_table_entries = _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params )\n+ data_table_entries = _stream_fasta_to_file(rscript_gff_to_tx2gene, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params )\n for data_table_name, data_table_entry in data_table_entries:\n if data_table_entry:\n _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name )\n@@ -188,7 +204,7 @@\n return data_manager_dict\n \n \n-def _stream_fasta_to_file( fasta_stream, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, close_stream=True ):\n+def _stream_fasta_to_file( rscript_gff_to_tx2gene, fasta_stream, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params, close_stream=True ):\n fasta_base_filename = "%s_tx2gene.tab" % sequence_id\n fasta_filename = os.path.join( target_directory, fasta_base_filename )\n with open( fasta_filename, \'wb+\' ) as fasta_writer:\n@@ -220,7 +236,7 @@\n if close_stream:\n fasta_stream.close()\n \n- convert_to_tx2gene( fasta_filename, params[\'param_dict\'][\'file_type\'], params )\n+ convert_to_tx2gene( rscript_gff_to_tx2gene,fasta_filename, params[\'param_dict\'][\'file_type\'], params )\n return [ ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ]\n \n \n@@ -271,17 +287,17 @@\n #Parse Command Line\n parser = optparse.OptionParser()\n parser.add_option( \'-d\', \'--dbkey_description\', dest=\'dbkey_description\', action=\'store\', type="string", default=None, help=\'dbkey_description\' )\n+ parser.add_option( \'-b\', \'--base_dir\', dest=\'base_dir\', action=\'store\', type=\'string\', default=None, help=\'base_dir\')\n parser.add_option( \'-t\', \'--type\', dest=\'file_type\', action=\'store\', type=\'string\', default=None, help=\'file_type\')\n (options, args) = parser.parse_args()\n \n filename = args[0]\n #global DATA_TABLE_NAME\n- global RSCRIPT_GFF_TO_TX2GENE= os.path.join( options.base_dir, \'tximport.r\')\n-\n+ rscript_gff_to_tx2gene=os.path.join( options.base_dir, \'get_tx2gene_table.R\')\n \n- if options.file_type == \'gff_gtf\':\n- #DATA_TABLE_NAME= \'representative_gff\'\n- else: #file_type=\'tx2gene\'\n+ #input_type=\'gff_gtf\'\n+ #if options.file_type != \'gff_gtf\':\n+ # \tfile_type=\'tx2gene\'\n \n params = loads( open( filename ).read() )\n target_directory = params[ \'output_data\' ][0][\'extra_files_path\']\n@@ -297,7 +313,7 @@\n tmp_dir = tempfile.mkdtemp()\n #Fetch the input file\n try:\n- 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)\n+ 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)\n finally:\n cleanup_before_exit(tmp_dir)\n #save info to json file\n' |
| b |
| diff -r 7d3ffe28ff3f -r d71f65b854de data_manager/data_manager_fetch_tx2gene.xml --- 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 $file_type @@ -14,9 +19,10 @@ <param type="text" name="sequence_id" value="" label="ID for sequence" /> <param name="file_type" type="select" label="Select input type: GFF/GTF file(features will be extracted to create tx2gene table) or transcript to gene table file(tab separated)"> - <option value="gff_gtf">GFF/GTF file</option> + <option value="gtf">GTF file</option> + <option value="gff3">GFF3 file</option> <option value="tx2gene">tx2gene</option> - </param> + </param> <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Choose the source for the reference genome"> <option value="url">URL</option> |
| b |
| diff -r 7d3ffe28ff3f -r d71f65b854de data_manager/get_tx2gene_table.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/get_tx2gene_table.R Fri Oct 19 07:36:02 2018 -0400 |
| [ |
| @@ -0,0 +1,17 @@ +library(getopt) + +# we read the options from the default: commandArgs(TRUE). +spec <- matrix(c( + "input_type", "t", 1, "character", + "outfile", "o", 1, "character", + "gtfFile", "x", 1, "character"), + byrow=TRUE, ncol=4) +opt <- getopt(spec) + +suppressPackageStartupMessages({library("GenomicFeatures")}) +txdb <- makeTxDbFromGFF(opt$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) + |
| b |
| diff -r 7d3ffe28ff3f -r d71f65b854de tool-data/tx2gene.loc.sample --- 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 |
| b |
| @@ -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> |
| b |
| diff -r 7d3ffe28ff3f -r d71f65b854de tool_data_table_conf.xml.sample --- 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 |
| b |
| @@ -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> |