def run_ptp(self, jp): 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) self.cfg.log.debug("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") self.cfg.log.debug(s) if fo2: fo2.close()
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)
def classify(self, query_fname, minp = 0.9, ptp = False): if self.jplace_fname: jp = EpaJsonParser(self.jplace_fname) else: self.checkinput(query_fname, minp) self.cfg.log.info("Running RAxML-EPA to place %d query sequences...\n" % self.query_count) 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) raxml.copy_epa_jplace(job_name, self.out_jplace_fname, move=True) self.cfg.log.info("Assigning taxonomic labels based on EPA placements...\n") placements = jp.get_placement() if self.out_assign_fname: fo = open(self.out_assign_fname, "w") else: fo = None noassign_list = [] for place in placements: taxon_name = place["n"][0] origin_taxon_name = EpacConfig.strip_query_prefix(taxon_name) edges = place["p"] if len(edges) > 0: ranks, lws = self.classify_helper.classify_seq(edges) isnovo = self.novelty_check(place_edge = str(edges[0][0]), ranks=ranks, lws=lws) rankout = self.print_ranks(ranks, lws, self.cfg.min_lhw) if rankout == None: noassign_list.append(origin_taxon_name) else: output = "%s\t%s\t" % (origin_taxon_name, rankout) if isnovo: output += "*" else: output +="o" if self.cfg.verbose: print(output) if fo: fo.write(output + "\n") else: noassign_list.append(origin_taxon_name) 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) noassign_list.append(origin_taxon_name) for taxon_name in noassign_list: output = "%s\t\t\t?" % origin_taxon_name if self.cfg.verbose: print(output) if fo: fo.write(output + "\n") if fo: 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) self.cfg.log.debug("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") self.cfg.log.debug(s) if fo2: fo2.close()