def get_subtype_reference_alignment_tree(region,
subtype='B',
refname='HXB2',
type='nuc',
VERBOSE=0,
format='newick'):
'''Get filename of consensus of subtype reference alignment'''
from Bio import Phylo
from hivwholeseq.cross_sectional.filenames import (
get_subtype_reference_alignment_tree_filename)
fn = get_subtype_reference_alignment_tree_filename(region,
subtype=subtype,
refname=refname,
type=type,
VERBOSE=VERBOSE,
format=format)
if format == 'newick':
return Phylo.read(fn, format)
from hivwholeseq.utils.tree import tree_from_json
from hivwholeseq.utils.generic import read_json
return tree_from_json(read_json(fn))
ali = get_subtype_reference_alignment(region,
subtype=subtype,
refname=refname,
type=alitype,
VERBOSE=VERBOSE)
if VERBOSE >= 2:
print 'Calculate tree'
tree = build_tree_fasttree(ali, VERBOSE=VERBOSE)
if VERBOSE >= 2:
print 'Save to file, newick'
fn_out = get_subtype_reference_alignment_tree_filename(region,
subtype=subtype,
refname=refname,
type=alitype,
VERBOSE=VERBOSE,
format='newick')
Phylo.write([tree], fn_out, 'newick')
if VERBOSE >= 2:
print 'Annotate tree (for JSON format)'
from hivwholeseq.utils.nehercook.ancestral import ancestral_sequences
a = ancestral_sequences(tree, ali, alphabet='ACGT-N', copy_tree=False,
attrname='sequence', seqtype='str')
a.calc_ancestral_sequences()
del a
if VERBOSE >= 2:
