def run_anc(input_dict,run_id = None):
assert run_id
rank_name = input_dict['rank_name']
taxon_id = input_dict['taxid']
aliname = input_dict['aliname']
BT = getBTOL()
p_node = ncbi.get_node(taxon_id)
seqnodes = BT.investigatePhylum(p_node = p_node)
recs, seqelts, seqtuples = seq_recs(seqnodes)
align = align_seqnodes(recs)
tree = phyml.tree(align, run_id = run_id)
rstfile= paml.run_paml(tree, align, run_id = run_id)
anc_tree = paml.rst_parser(rstfile)
anc_alignment = [SeqRecord(elt.m['seq'],
id = None,
name = elt.name,
annotations = {'scores':elt.m['probs']})
for elt in anc_tree.get_nonterminals()]
out_dict = dict(anc_tree=anc_tree,
anc_align= anc_alignment,
term_tree = tree,
term_align = align)
return out_dict
def run(**kwargs):
BT = getBTOL(**mem.sr(kwargs))
seqnodes = BT.investigatePhylum(**kwargs)
recs, seqelts, seqtuples = seq_recs(seqnodes)
align = align_seqnodes(recs)
tree = phyml.tree(align)
rstfile= paml.run_paml(tree, align)
anc_tree = paml.rst_parser(rstfile)
anc_alignment = [SeqRecord(elt.m['seq'],
id = None,
name = elt.name,
annotations = {'scores':elt.m['probs']})
for elt in anc_tree.get_nonterminals()]
return (tree, anc_tree), (align, anc_alignment)
def seq_dists(ali,run_id, tree = True):
import Levenshtein
n = len(ali)
dists = zeros((n,n))
if tree:
ali_named = align.MultipleSeqAlignment(ali)
maps = {}
for idx, a in enumerate(ali_named):
a.id = 'S{0:05}'.format(idx)
maps[a.id] = idx
tree = phyml.tree(ali_named, run_id = run_id, bionj = True)
for n1 in tree.get_terminals():
for n2 in tree.get_terminals():
dists[maps[n1.name],maps[n2.name]] = \
tree.distance(n1,n2)
else:
for i in range(n):
for j in range(i):
dists[i,j] = Levenshtein.distance(str(ali[i].seq), str(ali[j].seq))
dists[j,i] = dists[i,j]
return dists
def eval_seq_group(gap_seqs, rfid, run_id, inp_run_id, reset = True,
draw_alis = draw_all_easy,
clade_alignment_method = clade_alignment_method,
max_structs = 5):
rutils = utils
data = butils.load_data(inp_run_id, 'output')
structs = data['structs']
energies = data['energies']
esrt = argsort(energies)[::-1]
s_inds = esrt[:max_structs]
structs, energies = [structs[i] for i in s_inds], [energies[i] for i in s_inds]
refseq = data['seq']
nq = len(gap_seqs)
ns = len(structs)
names = ['N{1:04}'.format(rfid, idx) for idx in range(nq)]
seqs = [rutils.ungapped_seq(gap_seqs[i], names[i]) for i in range(nq)]
profiles = mem.getOrSet(setProfiles,
**mem.rc({},
seq = refseq, structs = structs, run_id = rfid,
reset = reset,
on_fail = 'compute',
register = 'tuprof_{0}'.format(rfid)))
if draw_alis:
draw_cm_muscle_congruencies(seqs, profiles,
run_id, reset = reset)
if clade_alignment_method == 'cm':
alis, refs, all_pairs =\
mem.getOrSet(setAlignments,
**mem.rc({},
seqs = seqs, profiles = profiles,
run_id = rfid, ali_type = 'struct',
reset = reset,
on_fail = 'compute',
register = 'tuali_struct_{0}'.format(rfid)))
else:
raise Exception('No methods besides cm are yet implemented')
seq_group_data = {}
seq_group_data['seqs'] = gap_seqs
seq_group_data['structs'] = []
for i, struct in enumerate(structs):
struct_data = {}
ali = alis[i]
ref = refs[i]
pairs = all_pairs[i]
#NOTE THAT DUE TO AN AWKWARD SYNTAX DECISION,
#I AM ALLOWING FOR THE POSSIBILITY THAT EACH
#ALI ELT HAS DIFFERENT PAIRS.
#
#ALL OF MY ROUTINES SO FAR ONLY USE A SINGLE
#PAIR SET AND SO I USE PAIRS[0] EXCLUSIVELY
struct_data.update(ref = ref[0],
pairs = pairs[0],
ali = ali)
rid = '{0}_{1}'.format(run_id, i)
if clade_tree_method == 'bionj':
tree = phyml.tree(ali, run_id = rid, bionj = True)
else: tree = get_phase_tree(ali, pairs[0], run_id)
for i, ct in enumerate(tree.get_terminals()):
seq = filter(lambda x: x.id == ct.name, ali)[0]
ct.m = {'seq':seq,
'probs':array([1 for j in range(len(seq))])}
if clade_ancestor_method == 'independent':
ml_tree = get_ml_ancestor_tree(tree, ali,
'{0}_paml{1}'.format(run_id, i))
else:
ml_tree = get_structure_ancestor_tree(\
tree, ali,'{0}_stree{1}'.format(run_id, i))
muts, times, gaps, irresolvables = tree_conservation.count_struct(ml_tree, pairs[0])
struct_data.update(muts = muts, times = times,
gaps = gaps, irresolvables = irresolvables)
seq_group_data['structs'].append(struct_data)
return seq_group_data
def draw_cm_muscle_congruencies(seqs, profiles, run_id, reset = True):
print 'computing alignments...'
print ' ...using muscle'
malis, mrefs, mpairs =\
mem.getOrSet(setAlignments,
**mem.rc({},
seqs = seqs, profiles = profiles,
run_id = run_id, ali_type = 'muscle',
reset = reset,
on_fail = 'compute',
register = 'tuali_musc_{0}'.format(run_id)))
print ' ...using cmalign.'
salis, srefs, spairs =\
mem.getOrSet(setAlignments,
**mem.rc({},
seqs = seqs, profiles = profiles,
run_id = run_id, ali_type = 'struct',
reset = reset,
on_fail = 'compute',
register = 'tuali__struct_{0}'.format(run_id)))
print ' ...making trees.'
for idx, alis in enumerate(zip(malis, salis)):
m, s = alis
mtree = phyml.tree(m,run_id, bionj = True)
stree = phyml.tree(s,run_id, bionj = True)
maps = dict([(elt.id,i) for i, elt in enumerate(m)])
mdists = zeros((len(maps),len(maps)))
sdists = zeros((len(maps),len(maps)))
for n1 in mtree.get_terminals():
for n2 in mtree.get_terminals():
mdists[maps[n1.name],maps[n2.name]] = \
mtree.distance(n1,n2)
for n1 in stree.get_terminals():
for n2 in stree.get_terminals():
sdists[maps[n1.name],maps[n2.name]] = \
stree.distance(n1,n2)
tree_similarity(sdists, mdists, '{0}_struct_{1}'.format(run_id,idx), k = len(sdists - 1))
tree_similarity(sdists, mdists, '{0}_struct_{1}'.format(run_id,idx), k = 6)
f = myplots.fignum(4, (8,10))
ct = mycolors.getct(len(mtree.get_terminals()))
import networkx
for t, sp, ttype in zip([mtree, stree], [211,212], ['sequence', 'structural']):
a = f.add_subplot(sp)
layout = 'neato'
G = phylo.to_networkx(t)
Gi = networkx.convert_node_labels_to_integers(G, discard_old_labels=False)
posi = networkx.pygraphviz_layout(Gi, layout, args = '')
posn = dict((n, posi[Gi.node_labels[n]]) for n in G)
networkx.draw(G, posn, labels = dict([(n, '') for n in G.nodes()]),
node_size = [100 if n.name in maps.keys() else 0 for n in G.nodes()],
width = 1, edge_color = 'black',
ax = a,
node_color = [ct[maps.get(n.name, -1)] for n in G.nodes()] )
a.annotate('Embedded tree for {0} alignment.'.format(ttype),
[0,1], xycoords = 'axes fraction', va = 'top',
xytext = [10,0],textcoords = 'offset pixels')
a.annotate('Total branch length is {0}'.format(t.total_branch_length()),
[1,0], xycoords = 'axes fraction', ha = 'right',
xytext = [-10,10],textcoords = 'offset pixels')
#phylo.draw_graphviz( mtree, label_func = lambda x: '',
# node_color = [ct[maps.get(n.name, -1)] for n in G.nodes()] +\
# [ct[0] for n in mtree.get_nonterminals()], axes = ax)
datafile = cfg.dataPath('figs/gpm2/pt2_mus_cm_tree_embeddings_{0}_struct_{1}.ps'.format(run_id, idx))
f.savefig(datafile, dpi = 200, format = 'ps')
