more single barcode fixes. revert picard threads to fixed number inst…

…ead of auto-scaling due to limit on open file handles
broadinstitute · Apr 29, 2015 · e6041dd · e6041dd
1 parent ec1285c
commit e6041dd
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 7 deletions.
diff --git a/broad_utils.py b/broad_utils.py
@@ -186,15 +186,16 @@ def main_extract_barcodes(args):
 def make_params_file(inFile, bamDir, outFile):
     'Create input file for illumina_basecalls'
     if any(row.get('barcode_2') for row in util.file.read_tabfile_dict(inFile)):
-        header = ['BARCODE_1', 'BARCODE_2', 'OUTPUT', 'SAMPLE_ALIAS', 'LIBRARY_NAME']
+        header = ['OUTPUT', 'SAMPLE_ALIAS', 'LIBRARY_NAME', 'BARCODE_1', 'BARCODE_2']
     else:
-        header = ['BARCODE_1', 'OUTPUT', 'SAMPLE_ALIAS', 'LIBRARY_NAME']
+        header = ['BARCODE', 'OUTPUT', 'SAMPLE_ALIAS', 'LIBRARY_NAME']
     with open(outFile, 'wt') as outf:
         outf.write('\t'.join(header)+'\n')
         rows = list(util.file.read_tabfile_dict(inFile))
         rows.append({'barcode_1':'N','barcode_2':'N','sample':'Unmatched'})
         for row in rows:
-            out  = {'BARCODE_1':row['barcode_1'],
+            out  = {'BARCODE':row['barcode_1'],
+                    'BARCODE_1':row['barcode_1'],
                     'BARCODE_2':row.get('barcode_2',''),
                     'SAMPLE_ALIAS':row['sample'],
                     'LIBRARY_NAME':row['sample']}

diff --git a/tools/picard.py b/tools/picard.py
@@ -158,7 +158,7 @@ class ExtractIlluminaBarcodesTool(PicardTools) :
     jvmMemDefault = '8g'
     defaults = {'read_structure':'101T8B8B101T',
         'max_mismatches':0, 'minimum_base_quality':25,
-        'num_processors':0}
+        'num_processors':8}
     option_list = ('read_structure', 'max_mismatches', 'minimum_base_quality',
         'min_mismatch_delta', 'max_no_calls', 'minimum_quality',
         'compress_outputs', 'num_processors')
@@ -190,7 +190,7 @@ class IlluminaBasecallsToSamTool(PicardTools) :
     defaults = {'read_structure':'101T8B8B101T', 'sequencing_center':'BI',
         'adapters_to_check': ('PAIRED_END', 'NEXTERA_V1', 'NEXTERA_V2'),
         'max_reads_in_ram_per_tile':100000, 'max_records_in_ram':100000,
-        'num_processors':0, 'force_gc':False}
+        'num_processors':8, 'force_gc':False}
     option_list = ('read_structure', 'sequencing_center', 'adapters_to_check',
         'platform', 'max_reads_in_ram_per_tile', 'max_records_in_ram', 'num_processors',
         'apply_eamss_filter', 'force_gc', 'first_tile', 'tile_limit',
@@ -212,7 +212,11 @@ def execute(self, basecalls_dir, barcodes_dir,
         opts += ['BASECALLS_DIR='+basecalls_dir,
                 'BARCODES_DIR='+barcodes_dir,
                 'LANE='+str(lane),
-                'RUN_BARCODE='+run_barcode,
-                'LIBRARY_PARAMS='+library_params]
+                'RUN_BARCODE='+run_barcode]
+        if 'BARCODE' in util.file.readFlatFileHeader(library_params):
+            # yes, it's deprecated, but it's the only way to do single-barcode pools
+            opts.append('BARCODE_PARAMS='+library_params)
+        else:
+            opts.append('LIBRARY_PARAMS='+library_params)
         PicardTools.execute(self, self.subtoolName, opts, JVMmemory)