Merge pull request #84 from supernifty/vep_offline

correct vep stage to annotate based on offline (cached) resources CPIPE-76

pipeline/pipeline_stages_config.groovy

@@ -853,11 +853,13 @@ annotate_vep = {
         perl $VEP/variant_effect_predictor.pl --cache --dir $VEP/../vep_cache 
             -i $input.vcf 
             --vcf -o $output.vcf 
-            -species human 
+            -species homo_sapiens 
             --canonical --per_gene --protein 
             --sift=b --polyphen=b
             --symbol hgnc --force_overwrite --hgvs  --maf_1kg --maf_esp --pubmed
             --plugin Condel,$CONDEL/config,s
+            --offline
+            --verbose
     """, "vep"
 }
 

pipeline/scripts/update_gene_lists.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+'''
 ###########################################################################
 #
 # This file is part of Cpipe.
@@ -26,66 +27,78 @@
 # Usage:
 #   update_gene_lists --source dir --target dir
 ####################################################################################
+'''
 
 import argparse
 import datetime
 import glob
 import os
-import re
 import sys
 
 CATEGORY = '1'
 
-def write_log( log, msg ):
-  log.write( '%s: %s\n' % ( datetime.datetime.now().strftime( '%y%m%d-%H%M%S' ), msg ) )
+def write_log(log, msg):
+    '''
+        write date stamped msg to log
+    '''
+    log.write('%s: %s\n' % (datetime.datetime.now().strftime('%y%m%d-%H%M%S'), msg))
 
-def update_gene_lists( source_dir, target_dir, log ):
-  for filename in glob.glob( os.path.join( source_dir, '*.add.genes.txt' ) ):
-    cohort = os.path.basename( filename ).split( '.' )[0]
-    # find corresponding flagship
-    target = os.path.join( target_dir, cohort, '%s.genes.txt' % cohort ) # target/cohort/cohort.genes.txt
-    if os.path.isfile( target ):
-      # read existing genes and categories
-      genes = {}
-      for line in open( target, 'r' ):
-        if line.startswith('#'):
-          continue
-        fields = line.strip().split('\t')
-        genes[fields[0].upper()] = fields[1]
-      # read new genes
-      added = set()
-      candidates = set()
-      for line in open( filename, 'r' ):
-        if line.startswith('#'):
-          continue
-        gene = line.strip().upper()
-        candidates.add( gene )
-        if gene not in genes:
-          added.add(gene)
-          genes[gene] = CATEGORY
-
-      # write out additional
-      if len(added) > 0:
-        with open( target, 'w' ) as fh:
-          fh.write( '#version %s\n' % datetime.datetime.now().strftime( '%y%m%d' ) )
-          fh.write( '#notes %i gene(s) added: %s\n' % ( len(added), ','.join( sorted( list(added) ) ) ) )
-          for gene in sorted(genes.keys()):
-            fh.write( '%s\t%s\n' % ( gene, genes[gene] ) )
-        write_log( log, '%s: %i gene(s) added from %i candidate(s): %s' % ( cohort, len(added), len(candidates), ','.join( sorted( list(added) ) ) ) )
-      else:
-        write_log( log, '%s: no changes from %i candidate(s)' % ( cohort, len(candidates) ) )
+def update_gene_lists(source_dir, target_dir, log):
+    '''
+        adds genes from files of the form source_dir/*.add.genes.txt to gene lists in target_dir/cohort/cohort.genes.txt
+    '''
+    for filename in glob.glob(os.path.join(source_dir, '*.add.genes.txt')):
+        cohort = os.path.basename(filename).split('.')[0]
+        # find corresponding flagship
+        target = os.path.join(target_dir, cohort, '%s.genes.txt' % cohort) # target/cohort/cohort.genes.txt
+        if os.path.isfile(target):
+            # read existing genes and categories
+            genes = {}
+            for line in open(target, 'r'):
+                if line.startswith('#'):
+                    continue
+                fields = line.strip().split('\t')
+                genes[fields[0].upper()] = fields[1]
+            # read new genes
+            added = set()
+            candidates = set()
+            for line in open(filename, 'r'):
+                if line.startswith('#'):
+                    continue
+                gene = line.strip().upper()
+                candidates.add(gene)
+                if gene not in genes:
+                    added.add(gene)
+                    genes[gene] = CATEGORY
+
+            # write out additional
+            if len(added) > 0:
+                with open(target, 'w') as fh:
+                    fh.write('#version %s\n' % datetime.datetime.now().strftime('%y%m%d'))
+                    fh.write('#notes %i gene(s) added: %s\n' % (len(added), ','.join(sorted(list(added)))))
+                    for gene in sorted(genes.keys()):
+                        fh.write('%s\t%s\n' % (gene, genes[gene]))
+                write_log(log, '%s: %i gene(s) added from %i candidate(s): %s' % (cohort, len(added), len(candidates), ','.join(sorted(list(added)))))
+            else:
+                write_log(log, '%s: no changes from %i candidate(s)' % (cohort, len(candidates)))
+        else:
+            write_log(log, 'ERROR: target gene list %s does not exist' % target)
+
+def main():
+    '''
+        update gene lists from command line options
+    '''
+    parser = argparse.ArgumentParser(description='Generate bed files')
+    parser.add_argument('--source', required=True, help='source of extra genes') # input
+    parser.add_argument('--target', required=True, help='target containing gene files to update') # input
+    parser.add_argument('--log', required=False, help='write changes to this file') # input
+    args = parser.parse_args()
+    if args.log:
+        log = open(args.log, 'a+')
     else:
-      write_log( log, 'ERROR: target gene list %s does not exist' % target )
+        log = sys.stderr
 
-if __name__ == '__main__':
-  parser = argparse.ArgumentParser(description='Generate bed files')
-  parser.add_argument('--source', required=True, help='source of extra genes') # input
-  parser.add_argument('--target', required=True, help='target containing gene files to update') # input
-  parser.add_argument('--log', required=False, help='write changes to this file') # input
-  args = parser.parse_args()
-  if args.log:
-    log = open( args.log, 'a+' )
-  else:
-    log = sys.stderr
+    update_gene_lists(args.source, args.target, log)
 
-  update_gene_lists( args.source, args.target, log )
+if __name__ == '__main__':
+    main()