def scaffold_hybrid_tree_foundation_tree(
otu_map: OtuMapFormat,
extension_taxonomy: TSVTaxonomyFormat,
extension_sequences: DNAFASTAFormat,
foundation_tree: NewickFormat,
foundation_taxonomy: TSVTaxonomyFormat,
graft_level: str = _ghost_tree_defaults['graft_level'],
) -> NewickFormat:
otu_map_fh = otu_map.open()
extension_taxonomy_fh = extension_taxonomy.open()
extension_sequences_fh = extension_sequences.open()
foundation_alignment_fh = foundation_tree.open()
if foundation_taxonomy:
foundation_taxonomy_fh = foundation_taxonomy.open()
else:
foundation_taxonomy_fh = None
with tempfile.TemporaryDirectory() as tmp:
# need ghost_tree.nwk here otherwise file exists
gt_path = os.path.join(tmp, 'ghost_tree')
thetree = extensions_onto_foundation(otu_map_fh, extension_taxonomy_fh,
extension_sequences_fh,
foundation_alignment_fh, gt_path,
graft_level,
foundation_taxonomy_fh)[0]
# write new file to tmp file; gets deleted when this block is done
gt_temp_file = open(tmp + 'ghost_tree', 'w')
gt_temp_file.write(thetree)
gt_temp_file.close()
return NewickFormat(tmp + 'ghost_tree', 'r')
def test_tsv_taxonomy_format_validate_positive(self):
filenames = ['2-column.tsv', '3-column.tsv', 'valid-but-messy.tsv',
'many-rows.tsv']
filepaths = [self.get_data_path(os.path.join('taxonomy', filename))
for filename in filenames]
for filepath in filepaths:
format = TSVTaxonomyFormat(filepath, mode='r')
format.validate()
def test_tsv_taxonomy_format_validate_positive(self):
filenames = ['2-column.tsv', '3-column.tsv', 'valid-but-messy.tsv',
'many-rows.tsv']
filepaths = [self.get_data_path(os.path.join('taxonomy', filename))
for filename in filenames]
for filepath in filepaths:
format = TSVTaxonomyFormat(filepath, mode='r')
format.validate()
def test_tsv_taxonomy_format_validate_negative(self):
filenames = ['empty', 'blanks', '1-column.tsv',
'headerless.tsv', 'header-only.tsv', 'jagged.tsv']
filepaths = [self.get_data_path(os.path.join('taxonomy', filename))
for filename in filenames]
for filepath in filepaths:
format = TSVTaxonomyFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'TSVTaxonomy'):
format.validate()
def test_tsv_taxonomy_format_validate_negative(self):
filenames = ['empty', 'blanks-and-comments', '1-column.tsv',
'headerless.tsv', 'header-only.tsv', 'jagged.tsv']
filepaths = [self.get_data_path(os.path.join('taxonomy', filename))
for filename in filenames]
for filepath in filepaths:
format = TSVTaxonomyFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'TSVTaxonomy'):
format.validate()
def test_tsv_taxonomy_format_column_header_lengths(self):
filenames = ['greater-column-length.tsv', 'greater-header-length.tsv']
filepaths = [self.get_data_path(os.path.join('taxonomy', filename))
for filename in filenames]
for filepath in filepaths:
format = TSVTaxonomyFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError,
'line 2.*3 values.*expected 2'):
format.validate()
def _0(ff: TSVTaxonomyFormat) -> skbio.TreeNode:
root = skbio.TreeNode('root', length=0)
with ff.open() as fh:
reader = iter(csv.reader(fh, delimiter='\t'))
next(reader) # skip header
for row in reader:
id_, taxonomy = row[:2]
taxonomy = taxonomy.split(';')
node = root
for taxon in taxonomy:
for child in node.children:
if child.name == taxon:
node = child
break
else:
child = skbio.TreeNode(taxon, length=1)
node.append(child)
node = child
node.append(skbio.TreeNode(id_, length=1))
return root
def setUp(self):
super().setUp()
# setup taxonomy to be edited
tax_fp = self.get_data_path('escherichia_shigella_taxonomy.txt')
self.taxonomy = TSVTaxonomyFormat(tax_fp, mode='r').view(pd.Series)
# setup full string replacement
replc = self.get_data_path('taxonomy-replacement-full-strings.txt')
md_replc = Metadata.load(replc)
self.md_replc_col = md_replc.get_column('replacements')
# setup substring replacement
ss_replc = self.get_data_path('taxonomy-replacement-pass.txt')
md_ss_replc = Metadata.load(ss_replc)
self.md_ss_replc_col = md_ss_replc.get_column('replacements')
# setup substring regex replacement
ssr_replc = self.get_data_path('taxonomy-replacement-regex.txt')
md_ssr_replc = Metadata.load(ssr_replc)
self.md_ssr_replc_col = md_ssr_replc.get_column('replacements')
# setup reusable dicts
self.exp_dict_00 = {
'Sal01': ('d__SUPER_DUPER_BACTERIA; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'Sal02': ('d__SUPER_DUPER_BACTERIA; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'UncultSal': ('d__SUPER_DUPER_BACTERIA; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__uncultured_Salmonella'),
'Esch01': ('d__SUPER_DUPER_BACTERIA; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; s__'),
'Shig01': ('d__SUPER_DUPER_BACTERIA; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; s__')
}
self.exp_dict_01 = {
'Sal01': ('d__Bacteria; p__LAME-PYHLA; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'Sal02': ('d__Bacteria; p__LAME-PYHLA; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'UncultSal': ('d__Bacteria; '
'p__LAME-PYHLA; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__UNCIVILIZED_Salmonella'),
'Esch01': ('d__Bacteria; p__LAME-PYHLA; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; s__'),
'Shig01': ('d__Bacteria; p__LAME-PYHLA; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; s__')
}
self.exp_dict_02 = {
'Sal01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'Sal02': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'UncultSal': ('d__Bacteria; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__uncultured_Salmonella'),
'Esch01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__unknown_Escherichia-Shigella'),
'Shig01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__unknown_Escherichia-Shigella')
}
self.exp_dict_03 = {
'Sal01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'Sal02': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__Salmonella_enterica'),
'UncultSal': ('d__Bacteria; '
'p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__UNCIVIL_Salmonella'),
'Esch01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__unknown_Escherichia-Shigella'),
'Shig01': ('d__Bacteria; p__Proteobacteria; '
'c__Gammaproteobacteria; '
'o__Enterobacterales; '
'f__Enterobacteriaceae; '
'g__Escherichia-Shigella; '
's__unknown_Escherichia-Shigella')
}