Merge pull request #38 from bigbio/dev

Dev

CHANGELOG.md

@@ -1,5 +1,7 @@
 # Changelog
 
+## [v0.0.13](https://github.com/bigbio/py-pgatk/tree/v0.0.13) (2021-02-15)
+
 ## [v0.0.12](https://github.com/bigbio/py-pgatk/tree/v0.0.12) (2021-02-11)
 
 ## [v0.0.11](https://github.com/bigbio/py-pgatk/tree/v0.0.11) (2021-02-07)

pypgatk/cgenomes/cgenomes_proteindb.py

@@ -187,7 +187,7 @@ def cosmic_to_proteindb(self):
       line_counter += 1
       row = line.strip().split("\t")
       # filter out mutations from unspecified groups
-      if filter_col:
+      if filter_col is not None:
         if row[filter_col] not in self._accepted_values and self._accepted_values != ['all']:
           continue
 
@@ -221,7 +221,7 @@ def cosmic_to_proteindb(self):
           output.write(entry)
           mutation_dic[header] = 1
 
-        if self._split_by_filter_column and filter_col:
+        if self._split_by_filter_column and filter_col is not None:
           try:
             groups_mutations_dict[row[filter_col]][header] = entry
           except KeyError:
@@ -262,8 +262,10 @@ def get_value_per_sample(self, local_clinical_sample_file, filter_column):
           # check for header and re-assign columns
           if 'SAMPLE_ID' in sl and filter_column in sl:
             filter_column_col, sample_id_col = self.get_sample_headers(sl, filter_column)
-          if filter_column_col and sample_id_col:
+          if filter_column_col is not None and sample_id_col is not None:
             sample_value[sl[sample_id_col]] = sl[filter_column_col].strip().replace(' ', '_')
+          else:
+            print("No column was for {}, {} in {}".format(filter_column, 'SAMPLE_ID', local_clinical_sample_file))
     return sample_value
 
   @staticmethod
@@ -299,6 +301,7 @@ def cbioportal_to_proteindb(self):
     if self._accepted_values != ['all'] or self._split_by_filter_column:
       if self._local_clinical_sample_file:
         sample_groups_dict = self.get_value_per_sample(self._local_clinical_sample_file, self._filter_column)
+        print('sample_groups_dict', self._local_clinical_sample_file, self._filter_column)
         if sample_groups_dict == {}:
           return
       else:
@@ -353,7 +356,7 @@ def cbioportal_to_proteindb(self):
         try:
           seq = seq_dic[enst]
         except KeyError:
-          print("%s not found:" % enst)
+          print("No matching recored for gene ({}) from row {} in FASTA file:".format(enst, row))
           continue
 
         if ":" in pos:

setup.py

@@ -9,7 +9,7 @@ def readme():
 
 
 setup(name='pypgatk',
-      version='0.0.13',
+      version='0.0.14',
       description='Python tools for proteogenomics',
       url='http://github.com/bigbio/py-pgatk',
       long_description=readme(),