adding in tumor_f_star column for CGA pipeline (the column remains op…

…tional)
getzlab · Apr 1, 2019 · 876672d · 876672d
1 parent 7d53018
commit 876672d
Showing 1 changed file with 10 additions and 3 deletions.
diff --git a/deTiN/deTiN.py b/deTiN/deTiN.py
@@ -96,7 +96,7 @@ def __init__(self, args, ascna_probe_number_filter=200, ascna_SNP_number_filter=
     def read_call_stats_file(self):
         fields = ['contig', 'position', 'ref_allele', 'alt_allele', 'tumor_name', 'normal_name', 't_alt_count',
                   't_ref_count'
-            , 'n_alt_count', 'n_ref_count', 'failure_reasons', 'judgement']
+            , 'n_alt_count', 'n_ref_count', 'failure_reasons', 'judgement','t_lod_fstar']
         fields_type = {'contig': str, 'position': np.int, 'ref_allele': str, 'alt_allele': str, 'tumor_name': str,
                        'normal_name': str,
                        't_alt_count': np.int, 't_ref_count': np.int, 'n_alt_count': np.int, 'n_ref_count': np.int,
@@ -105,8 +105,15 @@ def read_call_stats_file(self):
             self.call_stats_table = pd.read_csv(self.call_stats_file, '\t', index_col=False,
                                                 comment='#', usecols=fields, dtype=fields_type)
         except (ValueError, LookupError):
-            print 'Error reading call stats skipping first two rows and trying again'
-            self.call_stats_table = pd.read_csv(self.call_stats_file, '\t', index_col=False,
+            try:
+                fields = ['contig', 'position', 'ref_allele', 'alt_allele', 'tumor_name', 'normal_name', 't_alt_count',
+                          't_ref_count'
+                    , 'n_alt_count', 'n_ref_count', 'failure_reasons', 'judgement']
+                self.call_stats_table = pd.read_csv(self.call_stats_file, '\t', index_col=False,
+                                                comment='#', usecols=fields, dtype=fields_type)
+            except (ValueError, LookupError):
+                print 'Error reading call stats skipping first two rows and trying again'
+                self.call_stats_table = pd.read_csv(self.call_stats_file, '\t', index_col=False,
                                                 comment='#', skiprows=2, usecols=fields, dtype=fields_type)
         if type(self.call_stats_table['contig'][0]) == str:
             self.call_stats_table['Chromosome'] = du.chr2num(np.array(self.call_stats_table['contig']))