return False
return True
results_dir = sys.argv[1]
suffix = sys.argv[2]
elmfile = sys.argv[3]
elms = {}
with open(elmfile) as f:
for line in f:
elm, exp = line.strip().split('\t')
elms[elm] = True
for elm in elms:
counts = utils.count_host_elmSeqs(global_settings.TEST_GENOMES,
False, {},
results_dir, {elm:True}, suffix)
all_elmSeqs = {}
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)
js = defaultdict(dict)
for host1, host2 in itertools.combinations(host_dists, 2):
dis = utils.jensen_shannon_dists(host_dists[host1],
host_dists[host2])
js[host1][host2] = dis
js[host2][host1] = dis
if check_phylogeny(js):
print elm
use_seqs = {}
for elmSeq in seen_seqs[flu]:
elm, seq = elmSeq.split(':')
if elm == use_elm:
if flu_counts[flu][elmSeq] > 0:
use_seqs[elmSeq] = True
seen_seqs_ls.append(use_seqs)
# remove seqs seen less than 10x
#for flu in flu_counts:
# for elmSeq in
use_seqs_pre = utils_graph.unionLists(seen_seqs_ls)
counts = utils.count_host_elmSeqs(('Gallus_gallus','H_sapiens'),
False, {},
'working/Jun29/', {use_elm:True},
'.init')
use_seqs = utils_graph.unionLists([use_seqs_pre, counts['Gallus_gallus'],
counts['H_sapiens']])
host_vecs = utils.mk_count_vecs(counts, use_seqs)
host_dists = utils.mk_count_dists(host_vecs)
flu_vecs = utils.mk_count_vecs(flu_counts, use_seqs)
flu_dists = utils.mk_count_dists(flu_vecs)
# for flu in flu_dists:
# print sum(flu_dists[flu])
# sys.exit(0)
for seq, hhuman, hchicken, hf, cf in zip(use_seqs, host_dists['Gallus_gallus'],
host_dists['H_sapiens'],
(elm, stuff) = line.strip().split('\t')
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)
seen_seqs_ls = []
elm2seqs = defaultdict(dict)
flus = ("human", "chicken")
for flu in flus:
# flu_elm_file = os.path.join('results',
# flu + '.H5N1.elms')
if "human" in flu:
flu_elm_file = os.path.join("working/Jul1_year", flu + ".H3N2.2008.elms")
else:
flu_elm_file = os.path.join("working/Jul1_year/", flu + ".H5N1.2006.elms")
utils.count_flu_sampled(flu, flu_elm_file, flu_counts, seen_seqs, {}, False)
for elmseq in seen_seqs[flu]:
elm, seq = elmseq.split(":")
elm2seqs[elm][elmseq] = True
counts = utils.count_host_elmSeqs(("Gallus_gallus", "H_sapiens"), False, {}, "working/Jun29/", working_elms, ".init")
for elm in working_elms:
use_seqs = elm2seqs[elm]
host_vecs = utils.mk_count_vecs(counts, use_seqs)
host_dists = utils.mk_count_dists(host_vecs)
flu_vecs = utils.mk_count_vecs(flu_counts, use_seqs)
flu_dists = utils.mk_count_dists(flu_vecs)
flu = flu_dists["human"]
human_score_H = utils.jensen_shannon_dists(host_dists["H_sapiens"], flu)
chicken_score_H = utils.jensen_shannon_dists(host_dists["Gallus_gallus"], flu)
flu = flu_dists["chicken"]
human_score_C = utils.jensen_shannon_dists(host_dists["H_sapiens"], flu)
chicken_score_C = utils.jensen_shannon_dists(host_dists["Gallus_gallus"], flu)
flu_counts = {}
seen_seqs = {}
seen_seqs_ls = []
for flu in flus:
flu_elm_file = os.path.join('results/',
flu + '.H5N1.elms')
utils.count_flu_sampled(flu, flu_elm_file, flu_counts,
seen_seqs, mapping, do_clustering)
seen_seqs_ls.append(seen_seqs[flu])
if len(seen_seqs_ls) > 1:
all_elmSeqs = utils_graph.unionLists(seen_seqs_ls)
else:
all_elmSeqs = seen_seqs_ls[0]
host_counts = utils.count_host_elmSeqs(hosts, do_clustering, mapping,
elm_count_dir)
host_found_seqs = utils_graph.unionLists([host_counts['H_sapiens'],
host_counts['Gallus_gallus']])
use_seqs = utils_graph.unionLists([all_elmSeqs, host_found_seqs])
flu_vecs = utils.mk_count_vecs(flu_counts, use_seqs)
host_vecs = utils.mk_count_vecs(host_counts, use_seqs)
host_dists = utils.mk_count_dists(host_vecs)
flu_dists = utils.mk_count_dists(flu_vecs)
js_distances = defaultdict(dict)
for host in ('H_sapiens', 'Gallus_gallus'):
for flu in flus:
js_dis = utils.jensen_shannon_dists(host_dists[host],
flu_dists[flu])