def run_epa_once(self, reftree, th):
reftree_fname = self.cfg.tmp_fname("final_ref_%NAME%.tre")
job_name = self.cfg.subst_name("final_epa_%NAME%")
reftree.write(outfile=reftree_fname)
# IMPORTANT: don't load the model, since it's invalid for the pruned true !!!
optmod_fname=""
epa_result = self.raxml.run_epa(job_name, self.refalign_fname, reftree_fname, optmod_fname)
reftree_epalbl_str = epa_result.get_std_newick_tree()
placements = epa_result.get_placement()
# update branchid-taxonomy mapping to account for possible changes in branch numbering
reftree_tax = Tree(reftree_epalbl_str)
th.set_bf_unrooted_tree(reftree_tax)
bid_tax_map = th.get_bid_taxonomy_map()
cl = TaxClassifyHelper(self.cfg, bid_tax_map, self.brlen_pv, self.rate, self.node_height)
for place in placements:
seq_name = place["n"][0]
# get original taxonomic label
orig_ranks = self.get_orig_ranks(seq_name)
# get EPA tax label
ranks, lws = cl.classify_seq(place["p"])
# check if they match
mis_rec = self.check_seq_tax_labels(seq_name, orig_ranks, ranks, lws)
if not self.cfg.debug:
self.raxml.cleanup(job_name)
FileUtils.remove_if_exists(reftree_fname)
def build_hmm_profile(self, json_builder):
print "Building the HMMER profile...\n"
# this stupid workaround is needed because RAxML outputs the reduced
# alignment in relaxed PHYLIP format, which is not supported by HMMER
refalign_fasta = self.cfg.tmp_fname("%NAME%_ref_reduced.fa")
self.reduced_refalign_seqs.write(outfile=refalign_fasta)
hmm = hmmer(self.cfg, refalign_fasta)
fprofile = hmm.build_hmm_profile()
json_builder.set_hmm_profile(fprofile)
if not self.cfg.debug:
FileUtils.remove_if_exists(refalign_fasta)
FileUtils.remove_if_exists(fprofile)
def run_test(self):
self.raxml = RaxmlWrapper(self.cfg)
print "Number of sequences in the reference: %d\n" % self.reftree_size
self.refjson.get_raxml_readable_tree(self.reftree_fname)
self.refalign_fname = self.refjson.get_alignment(self.tmp_refaln)
self.refjson.get_binary_model(self.optmod_fname)
if self.ranktest:
print "Running the leave-one-rank-out test...\n"
subtree_count = self.run_leave_subtree_out_test()
print "Running the leave-one-sequence-out test...\n"
self.run_leave_seq_out_test()
if len(self.mislabels) > 0:
print "Leave-one-out test identified %d suspicious sequences; running final EPA test to check them...\n" % len(self.mislabels)
self.write_mislabels(final=False)
self.run_final_epa_test()
self.sort_mislabels()
self.write_mislabels()
print "\nPercentage of mislabeled sequences: %.2f %%" % (float(len(self.mislabels)) / self.reftree_size * 100)
if not self.cfg.debug:
FileUtils.remove_if_exists(self.reftree_fname)
FileUtils.remove_if_exists(self.optmod_fname)
FileUtils.remove_if_exists(self.refalign_fname)
def cleanup(self):
FileUtils.remove_if_exists(self.outgr_fname)
FileUtils.remove_if_exists(self.reftree_mfu_fname)
FileUtils.remove_if_exists(self.reftree_bfu_fname)
FileUtils.remove_if_exists(self.optmod_fname)
FileUtils.remove_if_exists(self.lblalign_fname)
FileUtils.remove_if_exists(self.outgr_fname)
FileUtils.remove_if_exists(self.reduced_refalign_fname)
FileUtils.remove_if_exists(self.refalign_fname)
def cleanup(self):
FileUtils.remove_if_exists(self.tmp_refaln)
def cleanup(self):
FileUtils.remove_if_exists(self.tmp_refaln)
FileUtils.remove_if_exists(self.epa_alignment)
FileUtils.remove_if_exists(self.hmmprofile)
FileUtils.remove_if_exists(self.tmpquery)
FileUtils.remove_if_exists(self.noalign)
def classify(self, query_fname, fout = None, method = "1", minlw = 0.0, pv = 0.02, minp = 0.9, ptp = False):
if self.jplace_fname:
jp = EpaJsonParser(self.jplace_fname)
else:
self.checkinput(query_fname, minp)
raxml = RaxmlWrapper(config)
reftree_fname = self.cfg.tmp_fname("ref_%NAME%.tre")
self.refjson.get_raxml_readable_tree(reftree_fname)
optmod_fname = self.cfg.tmp_fname("%NAME%.opt")
self.refjson.get_binary_model(optmod_fname)
job_name = self.cfg.subst_name("epa_%NAME%")
reftree_str = self.refjson.get_raxml_readable_tree()
reftree = Tree(reftree_str)
self.reftree_size = len(reftree.get_leaves())
# IMPORTANT: set EPA heuristic rate based on tree size!
self.cfg.resolve_auto_settings(self.reftree_size)
# If we're loading the pre-optimized model, we MUST set the same rate het. mode as in the ref file
if self.cfg.epa_load_optmod:
self.cfg.raxml_model = self.refjson.get_ratehet_model()
reduced_align_fname = raxml.reduce_alignment(self.epa_alignment)
jp = raxml.run_epa(job_name, reduced_align_fname, reftree_fname, optmod_fname)
placements = jp.get_placement()
if fout:
fo = open(fout, "w")
else:
fo = None
output2 = ""
for place in placements:
output = None
taxon_name = place["n"][0]
origin_taxon_name = EpacConfig.strip_query_prefix(taxon_name)
edges = place["p"]
# edges = self.erlang_filter(edges, p = pv)
if len(edges) > 0:
ranks, lws = self.classify_helper.classify_seq(edges, method, minlw)
isnovo = self.novelty_check(place_edge = str(edges[0][0]), ranks =ranks, lws = lws, minlw = minlw)
rankout = self.print_ranks(ranks, lws, minlw)
if rankout == None:
output2 = output2 + origin_taxon_name+ "\t\t\t?\n"
else:
output = "%s\t%s\t" % (origin_taxon_name, self.print_ranks(ranks, lws, minlw))
if isnovo:
output += "*"
else:
output +="o"
if self.cfg.verbose:
print(output)
if fo:
fo.write(output + "\n")
else:
output2 = output2 + origin_taxon_name+ "\t\t\t?\n"
if os.path.exists(self.noalign):
with open(self.noalign) as fnoa:
lines = fnoa.readlines()
for line in lines:
taxon_name = line.strip()[1:]
origin_taxon_name = EpacConfig.strip_query_prefix(taxon_name)
output = "%s\t\t\t?" % origin_taxon_name
if self.cfg.verbose:
print(output)
if fo:
fo.write(output + "\n")
if self.cfg.verbose:
print(output2)
if fo:
fo.write(output2)
fo.close()
#############################################
#
# EPA-PTP species delimitation
#
#############################################
if ptp:
full_aln = SeqGroup(self.epa_alignment)
species_list = epa_2_ptp(epa_jp = jp, ref_jp = self.refjson, full_alignment = full_aln, min_lw = 0.5, debug = self.cfg.debug)
if self.cfg.verbose:
print "Species clusters:"
if fout:
fo2 = open(fout+".species", "w")
else:
fo2 = None
for sp_cluster in species_list:
translated_taxa = []
for taxon in sp_cluster:
origin_taxon_name = EpacConfig.strip_query_prefix(taxon)
translated_taxa.append(origin_taxon_name)
s = ",".join(translated_taxa)
if fo2:
fo2.write(s + "\n")
if self.cfg.verbose:
print s
if fo2:
fo2.close()
#############################################
if not self.jplace_fname:
if not self.cfg.debug:
raxml.cleanup(job_name)
FileUtils.remove_if_exists(reduced_align_fname)
FileUtils.remove_if_exists(reftree_fname)
FileUtils.remove_if_exists(optmod_fname)
