updates

bin/bootstrap.py

@@ -1129,7 +1129,7 @@ def tool(name,
     time.sleep(5) # wait 5 seconds
 
     os.system("set +e") # make sure that the shell scripts are still executed if there are errors
-    v = "human_v97"
+    v = "human_v98"
     ############################################################################
     # List all dependencies
     ############################################################################

bin/build_report_fusions_map.py

@@ -344,6 +344,13 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None ,tmp_dir = None):
                       dest = "input_candidate_fusion_genes_reads_filename",
                       help = """The input list of candidate fusion genes and ids of the supporting reads, for example 'candidate_fusion-genes_not-filtered_supporting_paired-reads.txt'. This is processed even further.""")
 
+    parser.add_option("--input_unmapped_reads",
+                      action = "store",
+                      type = "string",
+                      dest = "input_unmapped_reads_filename",
+                      help = """The input list of ids of reads that are unmapped (that are mapping over the fusion junction).""")
+
+
     parser.add_option("--input_candidate_fusions_missing_mates",
                       action = "store",
                       type = "string",
@@ -650,6 +657,10 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None ,tmp_dir = None):
     candidate_fusions.pop(0) # remove the header
     candidate_fusions = dict([( tuple(myorder(line[0], line[1])), line[2]) for line in candidate_fusions if line[6].lower() == 'further_analysis'])
 
+    unmapped_reads = set()
+    if options.input_unmapped_reads_filename:
+        print "Reading...",options.input_unmapped_reads_filename
+        unmapped_reads = set([line.rstrip('\r\n') for line in file(options.input_unmapped_reads_filename,'r').readlines()])
 
     print "Reading...",options.input_candidate_fusion_genes_reads_filename
     # 0  - Fusion_gene_symbol_1
@@ -736,9 +747,9 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None ,tmp_dir = None):
         if not pairs:
             pairs = candidate_fusions_reads.get((g2,g1),None)
             if not pairs:
-                print g1
-                print g2
-                print pairs
+                print >>sys.stderr,g1
+                print >>sys.stderr,g2
+                print >>sys.stderr,pairs
                 print "Error: something wrong!"
                 sys.exit(1)
         pairs = set(pairs)
@@ -882,7 +893,10 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None ,tmp_dir = None):
         vvv = sorted(vv)
         for v in vvv:
             if v in support_pair:
-                da.append(">%s_supports_fusion_pair\n"%(v,))
+                if v[:-2] in unmapped_reads:
+                    da.append(">%s_supports_fusion_pair_and_junction\n"%(v,))
+                else:
+                    da.append(">%s_supports_fusion_pair\n"%(v,))
             else:
                 da.append(">%s_supports_fusion_junction\n"%(v,))
             da.append("%s\n"%(fasta[v],))
@@ -909,7 +923,10 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None ,tmp_dir = None):
         vvv = sorted(vv)
         for v in vvv:
             if v in support_pair:
-                da.append("@%s_supports_fusion_pair%s\n"%(v[:-2],v[-2:]))
+                if v[:-2] in unmapped_reads:
+                    da.append("@%s_supports_fusion_pair_and_junction%s\n"%(v[:-2],v[-2:]))
+                else:
+                    da.append("@%s_supports_fusion_pair%s\n"%(v[:-2],v[-2:]))
             else:
                 da.append("@%s_supports_fusion_junction%s\n"%(v[:-2],v[-2:]))
             sq = fastq[v]

bin/build_report_fusions_psl.py

@@ -326,6 +326,14 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None, tmp_dir = None):
                       dest = "input_candidate_fusion_genes_reads_filename",
                       help = """The input list of candidate fusion genes and ids of the supporting reads, for example 'candidate_fusion-genes_not-filtered_supporting_paired-reads.txt'. This is processed even further.""")
 
+
+    parser.add_option("--input_unmapped_reads",
+                      action = "store",
+                      type = "string",
+                      dest = "input_unmapped_reads_filename",
+                      help = """The input list of ids of reads that are unmapped (that are mapping over the fusion junction).""")
+
+
     parser.add_option("--output_super_summary",
                       action = "store",
                       type = "string",
@@ -483,6 +491,13 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None, tmp_dir = None):
     #          'fusion_sequence'                                      # 20
     #          ]
 
+
+    unmapped_reads = set()
+    if options.input_unmapped_reads_filename:
+        print "Reading...",options.input_unmapped_reads_filename
+        unmapped_reads = set([line.rstrip('\r\n') for line in file(options.input_unmapped_reads_filename,'r').readlines()])
+
+
     print "Reading...",options.input_fusion_psl_filename
     data = [line.rstrip('\r\n').split('\t') for line in file(options.input_fusion_psl_filename,'r') if line.rstrip('\r\n')]
     header = data.pop(0)

bin/build_report_fusions_psl2.py

@@ -378,6 +378,14 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None, tmp_dir = None):
                       dest = "input_candidate_fusion_genes_reads_filename",
                       help = """The input list of candidate fusion genes and ids of the supporting reads, for example 'candidate_fusion-genes_not-filtered_supporting_paired-reads.txt'. This is processed even further.""")
 
+
+    parser.add_option("--input_unmapped_reads",
+                      action = "store",
+                      type = "string",
+                      dest = "input_unmapped_reads_filename",
+                      help = """The input list of ids of reads that are unmapped (that are mapping over the fusion junction).""")
+
+
     parser.add_option("--output_super_summary",
                       action = "store",
                       type = "string",
@@ -541,6 +549,13 @@ def give_me_assembly(fasta, kmer = 31, velvet_dir = None, tmp_dir = None):
     #          'fusion_sequence'                                      # 20
     #          ]
 
+
+    unmapped_reads = set()
+    if options.input_unmapped_reads_filename:
+        print "Reading...",options.input_unmapped_reads_filename
+        unmapped_reads = set([line.rstrip('\r\n') for line in file(options.input_unmapped_reads_filename,'r').readlines()])
+
+
     print "Reading...",options.input_fusion_psl_filename
     data = [line.rstrip('\r\n').split('\t') for line in file(options.input_fusion_psl_filename,'r') if line.rstrip('\r\n')]
     header = data.pop(0)

bin/fusioncatcher-build.py

@@ -1203,10 +1203,10 @@ def format_epilog(self, formatter):
     job.add('',outdir('celllines.txt'),kind='output',command_line='no')
     job.run()
 
-    job.add(_FC_+'get_prostates.py',kind='program')
+    job.add(_FC_+'get_prostate_cancer.py',kind='program')
     job.add('--organism',options.organism,kind='parameter')
     job.add('--output',out_dir,kind='output',checksum='no')
-    job.add('',outdir('prostates.txt'),kind='output',command_line='no')
+    job.add('',outdir('prostate_cancer.txt'),kind='output',command_line='no')
     job.run()
 
     job.add(_FC_+'get_pancreases.py',kind='program')
@@ -1776,6 +1776,12 @@ def format_epilog(self, formatter):
     job.add('',outdir('gtex.txt'),kind='output',command_line='no')
     job.run()
 
+    job.add(_FC_+'get_oncokb.py',kind='program')
+    job.add('--organism',options.organism,kind='parameter')
+    job.add('--output',out_dir,kind='output',checksum='no')
+    job.add('',outdir('oncokb.txt'),kind='output',command_line='no')
+    job.run()
+
     job.add(_FC_+'get_rtcircrna.py',kind='program')
     job.add('--organism',options.organism,kind='parameter')
     job.add('--output',out_dir,kind='output',checksum='no')