seen_elms = defaultdict(dict)
for host in ls_of_hosts:
host_elmCounts[host] = defaultdict(utils.init_zero)
with open(results_dir + 'elmdict_' + host + '.redo') as f:
for line in f:
(elm, seq, count, fq) = line.strip().split('\t')
if elm in use_elms:
host_elmCounts[host][elm] += int(count)
seen_elms[elm][host] = True
#use_elms = {}
#for elm in seen_elms:
# if len(seen_elms[elm]) == len(ls_of_hosts):
# use_elms[elm] = True
# print len(use_elms)
return (host_elmCounts, use_elms)
use_elms = {}
with open(use_elms_file) as f:
for line in f:
(elm, stuff) = line.strip().split('\t')
use_elms[elm] = True
hosts = global_settings.GENOMES
if use_freqs == 'T':
host_elmCounts, elms = get_host_freqs(hosts, use_elms)
else:
host_elmCounts, elms = get_host_counts(hosts, use_elms)
host_vecs = utils.mk_count_vecs(host_elmCounts, elms)
host_dists = utils.mk_count_dists(host_vecs)
utils_plot.phylogeny_js(out_file, host_dists)
use_elms[elm] = True
do_clustering = True
if distance_file == 'NA':
do_clustering = False
if do_clustering:
dis_file = os.path.join(results_dir, distance_file)
mapping = utils.get_clusters(dis_file, dis_cutoff_init,
dis_cutoff_meta)
else:
mapping = {}
counts = utils.count_host_elmSeqs(global_settings.TEST_GENOMES,
do_clustering, mapping,
results_dir, use_elms, suffix)
ls = []
for host in counts:
ls.append(counts[host])
all_elmSeqs = {}
#all_elmSeqs = utils_graph.intersectLists(ls)
for host in counts:
for elmSeq in counts[host]:
all_elmSeqs[elmSeq] = True
host_vecs = utils.mk_count_vecs(counts, all_elmSeqs)
host_dists = utils.mk_count_dists(host_vecs)
utils_plot.phylogeny_js(os.path.join(results_dir,
out_file), host_dists)
