def test_taxtree_builder(self):
cfg = EpacConfig()
testfile_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "testfiles")
tax_fname = os.path.join(testfile_dir, "test.tax")
tax = Taxonomy(EpacConfig.REF_SEQ_PREFIX, tax_fname)
tree_fname = os.path.join(testfile_dir, "taxtree.nw")
expected_tree = Tree(tree_fname, format=8)
tb = TaxTreeBuilder(cfg, tax)
tax_tree, seq_ids = tb.build()
self.assertEqual(seq_ids, tax.get_map().keys())
self.assertEqual(tax_tree.write(format=8), expected_tree.write(format=8))
def test_taxtree_builder(self):
cfg = EpacConfig()
testfile_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "testfiles")
tax_fname = os.path.join(testfile_dir, "test.tax")
tax = Taxonomy(EpacConfig.REF_SEQ_PREFIX, tax_fname)
tree_fname = os.path.join(testfile_dir, "taxtree.nw")
expected_tree = Tree(tree_fname, format=8)
tb = TaxTreeBuilder(cfg, tax)
tax_tree, seq_ids = tb.build()
self.assertEqual(seq_ids, tax.get_map().keys())
self.assertEqual(tax_tree.write(format=8), expected_tree.write(format=8))
def build_multif_tree(self):
c = self.cfg
tb = TaxTreeBuilder(c, self.taxonomy)
(t, ids) = tb.build(c.reftree_min_rank, c.reftree_max_seqs_per_leaf, c.reftree_clades_to_include, c.reftree_clades_to_ignore)
self.reftree_ids = frozenset(ids)
self.reftree_size = len(ids)
self.reftree_multif = t
# IMPORTANT: select GAMMA or CAT model based on tree size!
self.cfg.resolve_auto_settings(self.reftree_size)
if self.cfg.debug:
refseq_fname = self.cfg.tmp_fname("%NAME%_seq_ids.txt")
# list of sequence ids which comprise the reference tree
with open(refseq_fname, "w") as f:
for sid in ids:
f.write("%s\n" % sid)
# original tree with taxonomic ranks as internal node labels
reftax_fname = self.cfg.tmp_fname("%NAME%_mfu_tax.tre")
t.write(outfile=reftax_fname, format=8)
def build_multif_tree(self):
c = self.cfg
tb = TaxTreeBuilder(c, self.taxonomy)
(t, ids) = tb.build(c.reftree_min_rank, c.reftree_max_seqs_per_leaf,
c.reftree_clades_to_include,
c.reftree_clades_to_ignore)
self.reftree_ids = frozenset(ids)
self.reftree_size = len(ids)
self.reftree_multif = t
# IMPORTANT: select GAMMA or CAT model based on tree size!
self.cfg.resolve_auto_settings(self.reftree_size)
if self.cfg.debug:
refseq_fname = self.cfg.tmp_fname("%NAME%_seq_ids.txt")
# list of sequence ids which comprise the reference tree
with open(refseq_fname, "w") as f:
for sid in ids:
f.write("%s\n" % sid)
# original tree with taxonomic ranks as internal node labels
reftax_fname = self.cfg.tmp_fname("%NAME%_mfu_tax.tre")
t.write(outfile=reftax_fname, format=8)
