def test_to_pandas_data_frame_to_biom_table(self): filepath = self.get_data_path('feature-table_v100.biom') transformer1 = self.get_transformer(BIOMV100Format, pd.DataFrame) input = BIOMV100Format(filepath, mode='r') df = transformer1(input) transformer2 = self.get_transformer(pd.DataFrame, biom.Table) obs = transformer2(df) self.assertIsInstance(obs, biom.Table)
def cluster_closed_reference(sequences: QIIME1DemuxFormat, reference_database: NinjaOpsDBDirFmt) \ -> (BIOMV100Format, QIIME1DemuxFormat): # Input paths supplied to ninja.py. sequences_fp = str(sequences) reference_database_dir = os.path.join(str(reference_database), 'db') # Output directory to store ninja.py results. output_dirfmt = model.DirectoryFormat() output_dir = str(output_dirfmt) cmd = [ 'ninja.py', '--input', sequences_fp, '--database', reference_database_dir, '--output', output_dir, '--full_output' ] run_command(cmd) biom_fp = os.path.join(output_dir, 'ninja_otutable.biom') output_biom_fmt = BIOMV100Format(biom_fp, mode='r') # Keep a reference to the DirectoryFormat this BIOM file resides in so that # the directory isn't deleted when `output_dirfmt` goes out of scope upon # function exit. The directory will be cleaned up appropriately when # `output_biom_fmt` is cleaned up and avoids copying the BIOM file. output_biom_fmt.__dirfmt = output_dirfmt # Get the set of IDs that failed to hit the reference database. failed_ids = set() failed_ids_fp = os.path.join(output_dir, 'ninja_fail.txt') with open(failed_ids_fp, 'r') as fh: for line in fh: id = line.rstrip('\n') failed_ids.add(id) # Filter the input sequences to only those that failed to hit the reference # database. output_failures_fmt = QIIME1DemuxFormat() with output_failures_fmt.open() as fh: for seq in skbio.io.read(sequences_fp, format='fasta'): id = seq.metadata['id'] if id in failed_ids: # Turning off roundtripping options to speed up writing. We can # safely turn these options off because we know the sequence # IDs are rountrip-safe since we're reading them from a FASTA # file. # # http://scikit-bio.org/docs/latest/generated/ # skbio.io.format.fasta.html#writer-specific-parameters seq.write(fh, id_whitespace_replacement=None, description_newline_replacement=None) return output_biom_fmt, output_failures_fmt
def test_biomv100_format_validate_negative(self): filepath = self.get_data_path('feature-table_v210.biom') format = BIOMV100Format(filepath, mode='r') with self.assertRaisesRegex(ValidationError, 'BIOMV100Format'): format.validate()
def test_biomv100_format_validate_positive(self): filepath = self.get_data_path('feature-table_v100.biom') format = BIOMV100Format(filepath, mode='r') format.validate()