def test_filter_genomes(self):
me = Database()
header = ('# assembly_accession', 'assembly_level')
data = (('GCF_000000001.1', 'Chromosome'), ('GCF_000000002.1',
'Complete Genome'),
('GCF_000000003.2', 'Scaffold'), ('GCF_000000004.1', 'Contig'),
('GCA_000000004.1', 'Contig'))
df = pd.DataFrame(data, columns=header)
me.complete = False
me.genoids = None
me.exclude = False
# drop duplicates
me.df = df.copy()
me.filter_genomes()
self.assertEqual(me.df.shape[0], 4)
self.assertListEqual(
me.df['genome'].tolist(),
['G000000001', 'G000000002', 'G000000003', 'G000000004'])
self.assertEqual(
me.df.query('accession == "GCF_000000004.1"').shape[0], 1)
# complete genomes only
me.complete = True
me.df = df.copy()
me.filter_genomes()
self.assertListEqual(me.df['accnov'].tolist(),
['GCF_000000001', 'GCF_000000002'])
# include certain genomes
me.complete = False
me.genoids = 'G000000001,G000000003'
me.df = df.copy()
me.filter_genomes()
self.assertListEqual(me.df['accession'].tolist(),
['GCF_000000001.1', 'GCF_000000003.2'])
# exclude certain genomes
me.genoids = ['GCF_000000002.1', 'GCF_000000004']
me.exclude = True
me.df = df.copy()
me.filter_genomes()
self.assertListEqual(me.df['accession'].tolist(),
['GCF_000000001.1', 'GCF_000000003.2'])
def test_identify_taxonomy(self):
me = Database()
header = ('organism_name', 'taxid', 'species', 'species_taxid')
data = (('Escherichia coli UMN026', '585056', 'E. coli', '562'),
('Escherichia coli O104:H4', '1038927', 'E. coli', '562'),
('Klebsiella aerogenes', '548', 'Klebsiella aerogenes',
'548'), ('unclassified Gammaproteobacteria', '118884', '',
''), ('Plasmid pPY113', '126792', '', ''))
df = pd.DataFrame(data, columns=header)
# organism names must be capital and latinate
me.capital = True
me.block = None
me.latin = True
me.taxids = None
me.exclude = False
me.taxdump = taxdump_from_text(taxdump_proteo)
me.df = df.copy()
me.identify_taxonomy()
self.assertNotIn('species_taxid', me.df.columns)
self.assertListEqual(me.df.index.tolist(), [0, 1, 2])
self.assertListEqual(me.df['species'].tolist(), ['562', '562', '548'])
# block word
me.block = 'plasmid'
me.latin = False
me.df = df.copy()
me.identify_taxonomy()
self.assertListEqual(me.df.index.tolist(), [0, 1, 2])
# no Escherichia
me.taxids = '561'
me.exclude = True
me.df = df.copy()
me.identify_taxonomy()
self.assertListEqual(me.df.index.tolist(), [2])
