def genTaxTree(resolver, namesdict, logger, taxonomy=None, draw=False):
"""Return Phylo from TaxonNamesResolver class."""
ranks = resolver.retrieve('classification_path_ranks')
qnames = resolver.retrieve('query_name')
lineages = resolver.retrieve('classification_path')
# replace ' ' with '_' for taxon tree
qnames = [re.sub("\s", "_", e) for e in qnames]
resolved_names_bool = [e in namesdict.keys() for e in qnames]
ranks = [ranks[ei] for ei, e in enumerate(resolved_names_bool) if e]
lineages = [lineages[ei] for ei, e in enumerate(resolved_names_bool) if e]
# identify unresolved names
unresolved_names = [qnames[ei] for ei, e in enumerate(resolved_names_bool)
if not e]
idents = [qnames[ei] for ei, e in enumerate(resolved_names_bool) if e]
statement = "Unresolved names: "
for each in unresolved_names:
statement += " " + each
logger.debug(statement)
# make taxdict
taxdict = TaxDict(idents=idents, ranks=ranks, lineages=lineages,
taxonomy=taxonomy)
# make treestring
treestring = taxTree(taxdict)
if not taxonomy:
d = 22 # default_taxonomy + 1 in tnr
else:
d = len(taxonomy) + 1
# add outgroup
treestring = '({0},outgroup:{1});'.format(treestring[:-1], float(d))
tree = Phylo.read(StringIO(treestring), "newick")
if draw:
Phylo.draw_ascii(tree)
return tree
# EXPLORE TAXDICT
# a dictionary for each ident with: 'lineage', 'taxref', 'ident', 'cident' and
# 'rank' (+ 'extra')
# the lineage
taxdict['H**o sapiens']['lineage'] # N.B. not all lineages are named, ''
# the ident is the same format as lineage e.g. it could be an ID
taxdict['H**o sapiens']['ident']
# the 'cident' (Contextual Ident), the highest named taxonomic group unique to
# this ident among all other idents
taxdict['Arabidopsis thaliana']['cident'] # A. thaliana is the only plant
# the 'taxref', a holder of 'ident' and taxonomic posistion. Requires printing
# e.g. C. tytonis could only resolved to the genus level (22/01/2015)
print(taxdict['Chlorotalpa tytonis']['taxref'])
# check the taxonomy
print(taxdict.taxonomy)
# check the hierarchy, a dictionary of taxrefs ranked and grouped in the form:
# {'rank':[([taxref1, taxref2, ....],'lineage1'),
# ([taxref3, taxref4, ....],'lineage2'), ....]}
print(taxdict.hierarchy)
# we've also added an extra data slot
taxdict['H**o sapiens']['extra']
# CREATE TREE
# use the taxdict to create a Newick string
treestring = taxTree(taxdict)
# SAVE TREE
with open('example.tre', 'w') as file:
file.write(treestring)
# EXPLORE TAXDICT
# a dictionary for each ident with: 'lineage', 'taxref', 'ident', 'cident' and
# 'rank' (+ 'extra')
# the lineage
taxdict['H**o sapiens']['lineage'] # N.B. not all lineages are named, ''
# the ident is the same format as lineage e.g. it could be an ID
taxdict['H**o sapiens']['ident']
# the 'cident' (Contextual Ident), the highest named taxonomic group unique to
# this ident among all other idents
taxdict['Arabidopsis thaliana']['cident'] # A. thaliana is the only plant
# the 'taxref', a holder of 'ident' and taxonomic posistion. Requires printing
# e.g. C. tytonis could only resolved to the genus level (22/01/2015)
print(taxdict['Chlorotalpa tytonis']['taxref'])
# check the taxonomy
print(taxdict.taxonomy)
# check the hierarchy, a dictionary of taxrefs ranked and grouped in the form:
# {'rank':[([taxref1, taxref2, ....],'lineage1'),
# ([taxref3, taxref4, ....],'lineage2'), ....]}
print(taxdict.hierarchy)
# we've also added an extra data slot
taxdict['H**o sapiens']['extra']
# CREATE TREE
# use the taxdict to create a Newick string
treestring = taxTree(taxdict)
# SAVE TREE
with open('example.tre', 'w') as file:
file.write(treestring)
