Merge pull request #212 from phac-nml/fix-pointfinderdatabase-PMID-co…

…lumn

Coerce PMID column into string not integer

staramr/blast/pointfinder/PointfinderDatabaseInfo.py

@@ -37,11 +37,12 @@ def from_file(cls, file):
 
         with open(file) as f:
             line = f.readline()
-        
+
         line = line.lstrip("#")
         column_names = line.split()
 
         pointfinder_info = pd.read_csv(file, sep=r'\t|\s{4,}', index_col=False, comment='#', header=None, names=column_names, engine='python')
+        pointfinder_info["PMID"] = pointfinder_info["PMID"].astype(str)
 
         return cls(pointfinder_info, file)
 
@@ -53,7 +54,7 @@ def from_pandas_table(cls, database_info_dataframe):
         :return: A new PointfinderDatabaseInfo.
         """
         return cls(database_info_dataframe)
-    
+
     @staticmethod
     def to_codons(regex_match):
         # Sometimes, the regex will match a string with a comma and return multiple matches.
@@ -128,7 +129,7 @@ def _get_resistance_codon_match(self, gene, codon_mutation):
                         # so we need to convert to nucleotide coordinates before making the comparison.
                     & (table['Ref_codon'] == codon_mutation.get_database_amr_gene_mutation())
                     & (table['Res_codon'].str.contains(codon_mutation.get_input_genome_mutation(), regex=False))]
-        
+
         # We need to handle codon insertions as a special case:
         # Pointfinder mis-reports the position of codon insertions. For example:
         # ref:     ACG --- ACG