def hmmer_to_markers(input, temp_dir): global refpkg fragments = MutableAlignment() fragments.read_filepath(input) reverse = dict([(name + '_rev', reverse_sequence(seq)) for (name, seq) in fragments.items()]) all_frags = MutableAlignment() all_frags.set_alignment(fragments) all_frags.set_alignment(reverse) frag_file = temp_dir + "/frags.fas" _write_fasta(all_frags, frag_file) # Now bin the fragments frag_scores = dict([(name, [-10000, 'NA', 'NA']) for name in fragments.keys()]) for gene in refpkg["genes"]: # Now run HMMER search hmmer_output = temp_dir + '/' + gene + ".out" hmmer_search(frag_file, refpkg[gene]["hmm"], hmmer_output) results = read_hmmsearch_results(hmmer_output) # Now select best direction for each frag for name, value in results.items(): bitscore = value[1] direction = 'forward' true_name = name if (name.find('_rev') != -1): true_name = true_name.replace('_rev', '') direction = 'reverse' if frag_scores[true_name][0] < bitscore: frag_scores[true_name] = [bitscore, gene, direction] # Now bin the fragments genes = dict([]) for name, val in frag_scores.items(): if (val[1] not in genes): genes[val[1]] = {} if (val[2] == 'forward'): genes[val[1]][name] = fragments[name] else: genes[val[1]][name] = reverse_sequence(fragments[name]) genes.pop("NA", None) for gene, seq in genes.items(): gene_file = temp_dir + '/' + gene + ".frags.fas.fixed" _write_fasta(seq, gene_file) binned_fragments = {} for gene, seq in genes.items(): binned_fragments[gene] = {} binned_fragments[gene]["file"] = temp_dir + '/' + gene \ + ".frags.fas.fixed" binned_fragments[gene]["nfrags"] = len(seq.keys()) return binned_fragments
def hmmer_to_markers(input, temp_dir): global marker_genes fragments = MutableAlignment() fragments.read_filepath(input) reverse = dict([(name+'_rev', reverse_sequence(seq)) for (name, seq) in fragments.items()]) all_frags = MutableAlignment() all_frags.set_alignment(fragments) all_frags.set_alignment(reverse) frag_file = temp_dir+"/frags.fas" _write_fasta(all_frags, frag_file) # Now bin the fragments frag_scores = dict([(name, [-10000, 'NA', 'NA']) for name in fragments.keys()]) gene_set = marker_genes align_name = 'sate' if (options().genes == 'cogs'): gene_set = cog_genes align_name = 'pasta' for gene in gene_set: # Now run HMMER search hmmer_search( frag_file, os.path.join( options().__getattribute__('reference').path, 'refpkg/%s.refpkg/%.profile' % (gene, align_name)), temp_dir + "/%s.out" % gene) results = read_hmmsearch_results(temp_dir + "/%s.out" % gene) # Now select best direction for each frag for name, value in results.items(): bitscore = value[1] direction = 'forward' true_name = name if (name.find('_rev') != -1): true_name = true_name.replace('_rev', '') direction = 'reverse' if frag_scores[true_name][0] < bitscore: frag_scores[true_name] = [bitscore, gene, direction] # Now bin the fragments genes = dict([]) for name, val in frag_scores.items(): if (val[1] not in genes): genes[val[1]] = {} if (val[2] == 'forward'): genes[val[1]][name] = fragments[name] else: genes[val[1]][name] = reverse_sequence(fragments[name]) genes.pop("NA", None) for gene, seq in genes.items(): gene_file = temp_dir + "/%s.frags.fas" % gene _write_fasta(seq, gene_file + ".fixed") return genes
def hmmer_to_markers(input, temp_dir): global marker_genes fragments = MutableAlignment() fragments.read_filepath(input) reverse = dict([(name + '_rev', reverse_sequence(seq)) for (name, seq) in fragments.items()]) all_frags = MutableAlignment() all_frags.set_alignment(fragments) all_frags.set_alignment(reverse) frag_file = temp_dir + "/frags.fas" _write_fasta(all_frags, frag_file) #Now bin the fragments frag_scores = dict([(name, [-10000, 'NA', 'NA']) for name in fragments.keys()]) gene_set = marker_genes align_name = 'sate' if (options().genes == 'cogs'): gene_set = cog_genes align_name = 'pasta' for gene in gene_set: #Now run HMMER search hmmer_search( frag_file, os.path.join(options().__getattribute__('reference').path, 'refpkg/%s.refpkg/%.profile' % (gene, align_name)), temp_dir + "/%s.out" % gene) results = read_hmmsearch_results(temp_dir + "/%s.out" % gene) #Now select best direction for each frag for name in results.keys(): bitscore = results[name][1] direction = 'forward' true_name = name if (name.find('_rev') != -1): true_name = true_name.replace('_rev', '') direction = 'reverse' if frag_scores[true_name][0] < bitscore: frag_scores[true_name] = [bitscore, gene, direction] #Now bin the fragments genes = dict([]) for name in frag_scores.keys(): if (frag_scores[name][1] not in genes): genes[frag_scores[name][1]] = {} if (frag_scores[name][2] == 'forward'): genes[frag_scores[name][1]][name] = fragments[name] else: genes[frag_scores[name][1]][name] = reverse_sequence( fragments[name]) genes.pop("NA", None) for gene in genes.keys(): gene_file = temp_dir + "/%s.frags.fas" % gene _write_fasta(genes[gene], gene_file + ".fixed") return genes
def hmmer_to_markers(input, temp_dir): global marker_genes fragments = MutableAlignment() fragments.read_filepath(input) reverse = dict([(name + "_rev", reverse_sequence(seq)) for (name, seq) in fragments.items()]) all_frags = MutableAlignment() all_frags.set_alignment(fragments) all_frags.set_alignment(reverse) frag_file = temp_dir + "/frags.fas" _write_fasta(all_frags, frag_file) # Now bin the fragments frag_scores = dict([(name, [-10000, "NA", "NA"]) for name in fragments.keys()]) gene_set = marker_genes align_name = "sate" if options().genes == "cogs": gene_set = cog_genes align_name = "pasta" for gene in gene_set: # Now run HMMER search hmmer_search( frag_file, os.path.join( options().__getattribute__("reference").path, "refpkg/%s.refpkg/%.profile" % (gene, align_name) ), temp_dir + "/%s.out" % gene, ) results = read_hmmsearch_results(temp_dir + "/%s.out" % gene) # Now select best direction for each frag for name in results.keys(): bitscore = results[name][1] direction = "forward" true_name = name if name.find("_rev") != -1: true_name = true_name.replace("_rev", "") direction = "reverse" if frag_scores[true_name][0] < bitscore: frag_scores[true_name] = [bitscore, gene, direction] # Now bin the fragments genes = dict([]) for name in frag_scores.keys(): if frag_scores[name][1] not in genes: genes[frag_scores[name][1]] = {} if frag_scores[name][2] == "forward": genes[frag_scores[name][1]][name] = fragments[name] else: genes[frag_scores[name][1]][name] = reverse_sequence(fragments[name]) genes.pop("NA", None) for gene in genes.keys(): gene_file = temp_dir + "/%s.frags.fas" % gene _write_fasta(genes[gene], gene_file + ".fixed") return genes
def main(): args = parse_args() sequences = MutableAlignment() assert os.path.isfile(args.input) and os.access(args.input, os.R_OK), "Input file %s does not exist\n" % args.input sequences.read_file_object(args.input) frag = MutableAlignment() full = MutableAlignment() for (key,seq) in sequences.items(): if (len(seq) <= args.threshold): frag[key]=seq else: full[key]=seq frag.write_to_path("%s.frag.fas" % args.output) full.write_to_path("%s.full.fas" % args.output)
def main(): args = parse_args() sequences = MutableAlignment() assert os.path.isfile(args.input) and os.access( args.input, os.R_OK), "Input file %s does not exist\n" % args.input sequences.read_file_object(args.input) frag = MutableAlignment() full = MutableAlignment() for (key, seq) in sequences.items(): if (len(seq) <= args.threshold): frag[key] = seq else: full[key] = seq frag.write_to_path("%s.frag.fas" % args.output) full.write_to_path("%s.full.fas" % args.output)
def testExtendedAlignment(self): print "======= starting testExtendedAlignment =========" subset = [ "SFIF", "SFII", "SCFC", "SGHD", "SDCC", "SBGE", "SFBB", "SDI", "SCGB", "SJGF", "SGBI", "SCJA", "SGAD", "SHEB", "SFHB", "SDJI", "SHED", "SJJJ", "SBBE", "SCCH", "SDJB", "SDAC", "SHEH", "SFDC", "SFEI", "SHHB", "SC", "SIAB", "SDDI", "SBCB", "SJB", "SEBD", "SFGD", "SHA", "SIDA", "SGHI", "SGIB", "SBFJ", "SFIE", "SCJF", "SJHJ", "SJBG", "SEJI", "SFFF", "SJ", "SIII", "SJHH", "SEIH", "SBDC", "SHDJ", "SJDD", "SGDB", "SIHA", "SIBB", "SECC", "SCAD", "SGBB", "SGIF", "SJHC", "SFCD", "SEAA", "SEFF", "SDFG", "SDJE", "SCFG", "SFH", "SCJ", "SDDD", "SEGD", "SCIH", "SDAG", "SCJE", "SFAJ", "SIDJ", "SE", "SHBC", "SJFF", "SCHD", "SBHA", "SEDF", "SFAF", "SEDD", "SDHD", "SGJD", "SIBH", "SGDF", "SIFA", "SJGA", "SIJB", "SFI", "SGA", "SBFC", "SBJA", "SFFC", "SFDH", "SFEE", "SBDF", "SGBJ", "SDHE", "SJIB", "SHHI", "SIDE", "SJII" ] alg = MutableAlignment() alg.read_filepath("data/simulated/test.fasta") alg.delete_all_gap() tlen = alg.get_length() frg = MutableAlignment() frg.read_filepath("data/simulated/test.fas") #print frg.get_num_taxa() pp = SeppProblem(alg.keys()) pp.fragments = frg pp.subalignment = alg cp1 = SeppProblem(subset, pp) cp2 = SeppProblem(list(set(alg.keys()) - set(subset)), pp) cp1.fragments = ReadonlySubalignment( [k for k in frg.keys() if int(k[-1]) >= 9], frg) cp2.fragments = ReadonlySubalignment( [k for k in frg.keys() if int(k[-1]) <= 1], frg) cp1labels = cp1.write_subalignment_without_allgap_columns( "data/tmp/cp1.fasta") cp2labels = cp2.write_subalignment_without_allgap_columns( "data/tmp/cp2.fasta") tmp = MutableAlignment().read_filepath("data/tmp/cp1.fasta") assert all( [not tmp.is_all_gap(pos) for pos in xrange(0, tmp.get_length())]) tmp = MutableAlignment().read_filepath("data/tmp/cp2.fasta") assert all( [not tmp.is_all_gap(pos) for pos in xrange(0, tmp.get_length())]) cp1.fragments.write_to_path("data/tmp/cp1.frags.fas") cp2.fragments.write_to_path("data/tmp/cp2.frags.fas") '''We have done the hmmalign before. don't worry about that right now''' ext1 = ExtendedAlignment(cp1.fragments) ext1.build_extended_alignment("data/tmp/cp1.fasta", "data/tmp/cp1.extended.sto") ext1.relabel_original_columns(cp1labels) ext2 = ExtendedAlignment(cp2.fragments) ext2.build_extended_alignment("data/tmp/cp2.fasta", "data/tmp/cp2.extended.sto") ext2.relabel_original_columns(cp2labels) extmerger = ExtendedAlignment([]) extmerger.merge_in(ext1) mixed = extmerger.merge_in(ext2) extmerger.write_to_path("data/tmp/extended.merged.fasta") assert extmerger.is_aligned(), "Merged alignment is not aligned" in1 = len([x for x in ext1._col_labels if x < 0]) in2 = len([x for x in ext2._col_labels if x < 0]) print "Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d" % ( extmerger.get_length(), in1, in2, tlen) assert (in1 + in2 + tlen - mixed) == extmerger.get_length( ), "Lengths don't match up after merging. Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d Mixed-insertion: %d" % ( extmerger.get_length(), in1, in2, tlen, mixed) assert (in1 + in2 - mixed) == len( list(extmerger.iter_insertion_columns()) ), "Columns are not correctly labeled after merging. Merged insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion: %d" % ( len(list(extmerger.iter_insertion_columns())), in1, in1, mixed) tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment() tmp.delete_all_gap() assert tmp.is_aligned(), "merged alignment should be aligned!" assert tmp.get_length() == tlen, "merged alignment has wrong length" assert all([alg[k] == s for (k, s) in tmp.items() ]), "merged alignment should match original alignment" print "======= finished testExtendedAlignment ========="
def testExtendedAlignment(self): print "======= starting testExtendedAlignment =========" subset = ["SFIF","SFII","SCFC","SGHD","SDCC","SBGE","SFBB","SDI","SCGB","SJGF","SGBI","SCJA","SGAD","SHEB","SFHB","SDJI","SHED","SJJJ","SBBE","SCCH","SDJB","SDAC","SHEH","SFDC","SFEI","SHHB","SC","SIAB","SDDI","SBCB","SJB","SEBD","SFGD","SHA","SIDA","SGHI","SGIB","SBFJ","SFIE","SCJF","SJHJ","SJBG","SEJI","SFFF","SJ","SIII","SJHH","SEIH","SBDC","SHDJ","SJDD","SGDB","SIHA","SIBB","SECC","SCAD","SGBB","SGIF","SJHC","SFCD","SEAA","SEFF","SDFG","SDJE","SCFG","SFH","SCJ","SDDD","SEGD","SCIH","SDAG","SCJE","SFAJ","SIDJ","SE","SHBC","SJFF","SCHD","SBHA","SEDF","SFAF","SEDD","SDHD","SGJD","SIBH","SGDF","SIFA","SJGA","SIJB","SFI","SGA","SBFC","SBJA","SFFC","SFDH","SFEE","SBDF","SGBJ","SDHE","SJIB","SHHI","SIDE","SJII"] alg = MutableAlignment() alg.read_filepath("data/simulated/test.fasta") alg.delete_all_gap() tlen = alg.get_length() frg = MutableAlignment() frg.read_filepath("data/simulated/test.fas") #print frg.get_num_taxa() pp = SeppProblem(alg.keys()) pp.fragments = frg pp.subalignment = alg cp1 = SeppProblem(subset, pp) cp2 = SeppProblem(list(set(alg.keys()) -set(subset)), pp) cp1.fragments = ReadonlySubalignment([k for k in frg.keys() if int(k[-1]) >= 9], frg) cp2.fragments = ReadonlySubalignment([k for k in frg.keys() if int(k[-1]) <= 1], frg) cp1labels = cp1.write_subalignment_without_allgap_columns("data/tmp/cp1.fasta") cp2labels = cp2.write_subalignment_without_allgap_columns("data/tmp/cp2.fasta") tmp = MutableAlignment().read_filepath("data/tmp/cp1.fasta") assert all([not tmp.is_all_gap(pos) for pos in xrange(0,tmp.get_length())]) tmp = MutableAlignment().read_filepath("data/tmp/cp2.fasta") assert all([not tmp.is_all_gap(pos) for pos in xrange(0,tmp.get_length())]) cp1.fragments.write_to_path("data/tmp/cp1.frags.fas") cp2.fragments.write_to_path("data/tmp/cp2.frags.fas") '''We have done the hmmalign before. don't worry about that right now''' ext1 = ExtendedAlignment(cp1.fragments) ext1.build_extended_alignment("data/tmp/cp1.fasta", "data/tmp/cp1.extended.sto") ext1.relabel_original_columns(cp1labels) ext2 = ExtendedAlignment(cp2.fragments) ext2.build_extended_alignment("data/tmp/cp2.fasta", "data/tmp/cp2.extended.sto") ext2.relabel_original_columns(cp2labels) extmerger = ExtendedAlignment([]) extmerger.merge_in(ext1) mixed = extmerger.merge_in(ext2) extmerger.write_to_path("data/tmp/extended.merged.fasta") assert extmerger.is_aligned(), "Merged alignment is not aligned" in1 = len([x for x in ext1._col_labels if x<0]) in2 = len([x for x in ext2._col_labels if x<0]) print "Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d" %(extmerger.get_length(),in1 , in2 , tlen) assert ( in1 + in2 + tlen - mixed) == extmerger.get_length(), "Lengths don't match up after merging. Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d Mixed-insertion: %d" %(extmerger.get_length(),in1, in2 , tlen, mixed) assert ( in1 + in2 - mixed) == len(list(extmerger.iter_insertion_columns())), "Columns are not correctly labeled after merging. Merged insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion: %d" %(len(list(extmerger.iter_insertion_columns())),in1 , in1, mixed) tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment() tmp.delete_all_gap() assert tmp.is_aligned(), "merged alignment should be aligned!" assert tmp.get_length() == tlen, "merged alignment has wrong length" assert all([alg[k] == s for (k,s) in tmp.items()]), "merged alignment should match original alignment" print "======= finished testExtendedAlignment ========="
base_alignment.get_sequence_names()) print("Orig alignment sequences: ", original_backbone.get_sequence_names()) print("Base alignment sequences: ", base_alignment.get_sequence_names()) print("num base alignment seqs: ", len(base_alignment.get_sequence_names())) frags = MutableAlignment() sequence_names = [] for file in sequence_files: seq = MutableAlignment() done = seq.read_filepath(file) print('query sequence names:', seq.get_sequence_names()) print("query sequence length:", seq.get_length()) done = sequence_names.extend(seq.get_sequence_names()) for name, seq in seq.items(): frags[name] = seq.upper() problem = SeppProblem(sequence_names) problem.set_subalignment(subbackbone) # constructs sub-base-alignment from the full alignment, delete all gaps mut_subalg = problem.subalignment.get_mutable_alignment() remaining_cols = mut_subalg.delete_all_gap() problem.annotations["ref.alignment.columns"] = remaining_cols print("num remaining_cols: ", len(remaining_cols)) problem.fragments = frags ap_alg = problem.read_extendend_alignment_and_relabel_columns( base_alignment_file, aligned_files) extendedAlignment.merge_in(ap_alg, convert_to_string=True)
for dir in dirs: print("Working on %s\n" % dir) aligned_files = glob.glob('%sFC_*/hmmalign.results.*' % dir) sequence_files = glob.glob('%sFC_*/hmmalign.frag.*' % dir) base_alignment_file = glob.glob('%s/*.fasta' % dir) base_alignment = MutableAlignment() done = base_alignment.read_filepath(base_alignment_file[0]) subbackbone = original_backbone.get_soft_sub_alignment( base_alignment.get_sequence_names()) frags = MutableAlignment() sequence_names = [] for file in sequence_files: seq = MutableAlignment() done = seq.read_filepath(file) done = sequence_names.extend(seq.get_sequence_names()) for name, seq in seq.items(): frags[name] = seq.upper() problem = SeppProblem(sequence_names) problem.set_subalignment(subbackbone) mut_subalg = problem.subalignment.get_mutable_alignment() remaining_cols = mut_subalg.delete_all_gap() problem.annotations["ref.alignment.columns"] = remaining_cols problem.fragments = frags ap_alg = problem.read_extendend_alignment_and_relabel_columns( base_alignment_file, aligned_files) extendedAlignment.merge_in(ap_alg, convert_to_string=False) extendedAlignment.write_to_path("/projects/sate8/namphuon/ultra_large/1000000/" "upp_100_10_new/upp.unmasked.fasta") extendedAlignment.remove_insertion_columns()