def extract_ss(input_path, suffix, tree_file):
tree = Tree(tree_file, format=1)
leaves_set = set(tree.get_leaf_names())
msa = SeqGroup(input_path.alignment, "fasta")
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
new_msa = SeqGroup()
for entry in msa.iter_entries():
label = entry[0]
sequence = entry[1]
if (label in leaves_set):
new_msa.set_seq(label, sequence)
open(output_path.alignment, "w").write(new_msa.write(format="fasta"))
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
def extract_ss(input_path, suffix, tree_file):
print(
"Extracting alignment generated with the support selection tree thinning technique..."
)
tree = Tree(tree_file, format=1)
leaves_set = set(tree.get_leaf_names())
msa = SeqGroup(input_path.alignment, "fasta")
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
new_msa = SeqGroup()
for entry in msa.iter_entries():
label = entry[0]
sequence = entry[1]
if (label in leaves_set):
new_msa.set_seq(label, sequence)
open(output_path.alignment, "w").write(new_msa.write(format="fasta"))
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
print("New version of the snapshot: " + output_path.path)
for name, seq, _ in alg_aa:
try:
cdna = F.id2seq[F.name2id[name]]
except KeyError:
print "cdna for %s not found" % name
continue
cdna_aln = ""
for pos in seq:
if pos != "-":
cdna_aln += cdna[:3]
cdna = cdna[3:]
else:
cdna_aln += "---"
# Last the stop codon
cdna_aln += cdna[:3]
alg_dna.set_seq(name, cdna_aln)
print "Input protein alignment contains %s aa sequences" % len(alg_aa)
print "Output cdna alignment contains %s cdna sequences" % len(alg_dna)
print
alg_dna.write(outfile=infile.replace(".clustalo", ".clustalo.cdna.aln"))
F = parser.fasta.read_fasta(sys.argv[2])
for infile in infiles:
print infile
if os.stat(infile).st_size == 0:
continue
alg_aa = SeqGroup(infile)
alg_dna = SeqGroup()
for name, seq, _ in alg_aa:
try:
cdna = F.id2seq[F.name2id[name]]
except KeyError:
print "cdna for %s not found" % name
continue
cdna_aln = ""
for pos in seq:
if pos != "-":
cdna_aln += cdna[:3]
cdna = cdna[3:]
else:
cdna_aln += "---"
# Last the stop codon
cdna_aln += cdna[:3]
alg_dna.set_seq(name, cdna_aln)
print "Input protein alignment contains %s aa sequences" % len(alg_aa)
print "Output cdna alignment contains %s cdna sequences" % len(alg_dna)
print
alg_dna.write(outfile=infile.replace(".clustalo", ".clustalo.cdna.aln"))
