def create_enzyme_df(path_to_file): """ input:path_to_file. file.gz format output:enzyme dataframe """ enzyme_fields = [ method for method in dir(Enzyme.Record()) if not method.startswith('_') ] data_matrix = [] with gzip.open(path_to_file, 'rt') as file: for record in enzyme.parse(file): data_matrix.append( [getattr(record, field) for field in enzyme_fields]) enzyme_df = pd.DataFrame(data_matrix, columns=enzyme_fields) return enzyme_df