def main(args):
aaseqs = bioio.multisequence()
if args.start_sequence:
args.start_sequence = args.start_sequence.upper().encode('ASCII')
for infile in args.files:
mseq = bioio.load(infile, options=args.io_opts)
cout('reading %d sequences from %s' % (len(mseq), infile))
for seq in mseq:
aaseq = seq.clone()
if args.start_sequence:
# we use search restriction pattern function to locate
# the position
target_seq = funcs.uppercased(funcs.degapped(seq))
res = funcs.search_restriction_site(target_seq,
args.start_sequence)
if len(res) != 1:
continue
print(target_seq[res[0][0]:res[0][0] + 30])
aaseq.set_sequence(
funcs.translated(target_seq, start_pos=res[0][0] + 1))
else:
aaseq.set_sequence(
funcs.translated(seq, start_pos=args.start_codon))
aaseqs.append(aaseq)
bioio.save(aaseqs, args.outfile)
def count_allele(mseqs):
full_mseqs = multisequence()
for grp in mseqs:
full_mseqs.extend(mseqs[grp])
na_profiles = profiles.na_profile(full_mseqs, additional_ignore=b'X')
consensus_seq = na_profiles.consensus(0.1)
allele_counts = {}
for grp in mseqs:
allele_count = np.zeros((len(consensus_seq), 2))
mseq = mseqs[grp]
for j in range(len(mseq)):
seq = mseq[j].seq
for i in range(len(consensus_seq)):
if seq[i] == b'N':
allele_count[i, 0] += 1
allele_count[i, 1] += 1
elif seq[i] == b'X':
continue
elif seq[i] == consensus_seq[i]:
allele_count[i, 0] += 2
else:
allele_count[i, 1] += 2
allele_counts[grp] = allele_count
return allele_counts
def copy_to_msa(self):
msa = bioio.multisequence()
indices = list(self._index_selections)
indices.sort()
for idx in indices:
msa.append(self.model()[idx])
return msa
def to_genotype_array(mseqs):
# genotype array is array of site vs sample vs [0,0]
# 0 for the major allele, 1 for the minor allele
# create matrix profile first
full_mseqs = multisequence()
indexes = {}
idx = 0
for grp in mseqs:
full_mseqs.extend(mseqs[grp])
indexes[grp] = list(range(idx, idx + len(mseqs[grp])))
idx += len(mseqs[grp])
na_profiles = profiles.na_profile(full_mseqs, additional_ignore=b'X')
consensus_seq = na_profiles.consensus(0.1)
genotype_array = np.zeros((len(consensus_seq), len(full_mseqs), 2),
dtype=int)
for i, j in itertools.product(range(len(full_mseqs)),
range(len(consensus_seq))):
seq = full_mseqs[0].seq
if seq[j] == b'N':
genotype_array[j, i] == [0, 1]
elif seq[j] == b'X':
genotype_array[j, i] == [-1, -1]
elif seq[j] == consensus_seq[j]:
genotype_array[j, i] == [0, 0]
else:
genotype_array[j, i] == [1, 1]
return genotype_array, indexes
def main(args):
tables = []
container = bioio.multisequence()
n = 1
for infile in args.files:
mseqs = bioio.load(infile)
mseqs.sort(lambda x: x.label)
for s in mseqs:
tables.append((
n,
s.label,
s.attr.get('collection_date', ''),
s.attr.get('country', ''),
s.attr.get('isolate', ''),
s.definition,
))
container.append(bioio.biosequence('%04d' % n, s.seq.upper()))
n += 1
# write to output file
tabfile = open(args.tabfile, 'w')
tabfile.write('LABEL\tACCNO\tDATE\tCOUNTRY\tISOLATE\tDEFINITION\n')
tables.sort()
for r in tables:
tabfile.write('%04d\t%s\t%s\t%s\t%s\t%s\n' % r)
tabfile.close()
bioio.save(container, args.outfile)
def __init__(self, dna_msa, start_atg, msa_signals=None):
super(TranslatedMSA, self).__init__(bioio.multisequence())
self._src_msa = dna_msa
self._start_atg = start_atg
self._na = False
self.retranslate()
def seq2fst(args):
# open and read sequence file
cerr('[I - reading sequence file %s]' % args.infile)
seqs = load(args.infile)
# open and read group/meta file using groupfile/metafile if available
if args.groupfile or args.metafile:
cerr('[I - reading group information file]')
group_parser = grpparser.GroupParser(args)
group_parser.parse()
group_seqs = {}
for seq in seqs:
try:
grp = group_parser.group_info[seq.label.decode('ASCII')]
except KeyError:
cerr('[W - sample %s is not assign to any group]' %
seq.label.decode('ASCII'))
continue
if grp in group_seqs:
group_seqs[grp].append(seq)
else:
ms = multisequence()
ms.append(seq)
group_seqs[grp] = ms
else:
cexit('[ERR - seq2fst.py requires group information!]')
for grp_seq in group_seqs:
cerr('[I - group %s has %d sample(s)]' %
(grp_seq, len(group_seqs[grp_seq])))
if args.sitefile:
# perform FST site-wise
FST_sites = calc_site_fst(group_seqs, args.nantozero)
with open(args.sitefile, 'w') as fout:
for (label, mat) in FST_sites:
fout.write(label)
fout.write('\t')
np.savetxt(fout,
mat,
fmt='%5.4f',
delimiter='\t',
newline='\t')
fout.write('\n')
cerr('[I - site FST written to %s]' % (args.sitefile))
return
FST_mat, groups = calc_fst(group_seqs)
with open(args.outfile, 'w') as fout:
fout.write('\t'.join(groups))
fout.write('\n')
np.savetxt(fout, FST_mat, fmt='%5.4f', delimiter='\t')
def copy_to_msa(self):
segments = self.normalize_position()
src_mseqs = self.model()
dest_mseqs = bioio.multisequence()
#print segments
for s in src_mseqs:
dest_mseqs.append(s.clone().set_sequence(b''.join(
[s[x:y + 1] for (y, x) in segments])))
return dest_mseqs
def concat_sequencs( multiseqs ):
seqnames = {}
new_mseq = bioio.multisequence()
for seq in multiseqs[0]:
s = seq.clone()
s.set_sequence( s.get_sequence() )
new_mseq.append( s )
seqnames[s.get_label()] = True
for multiseq in multiseqs[1:]:
label = s.get_label()
if
def main(args):
container = None
for infile in args.files:
obj = bioio.load(infile, options=args.io_opts or [])
cout('reading %d sequences from %s' % (len(obj), infile))
if container is None:
container = obj
else:
container += obj
append_attributes(container, args.src, args.src_isolate, args.definition)
if args.accno:
set_label_to_accno(container)
if args.degap:
container.degap()
if args.minlen > 0 or args.maxlen > 0 or args.maxN > 0:
new_container = bioio.multisequence()
for s in container:
if args.minlen > 0 and len(s) < args.minlen:
continue
if args.maxlen > 0 and len(s) > args.maxlen:
continue
if args.maxN > 0 and s.seq.count(b'N') / len(s) > args.maxN:
continue
new_container.append(s)
container = new_container
if args.sort:
if args.sort.startswith('len'):
container.sort(lambda x: len(x), reverse=True)
elif args.sort.startswith('lab'):
container.sort(lambda x: x.label)
if args.summary:
for s in container:
seq = s.seq.upper()
print(">%s\nA:%d\tC:%d\tG:%d\tT:%d\t-:%d" %
(s.label.decode('ASCII'), seq.count(b'A'), seq.count(b'C'),
seq.count(b'G'), seq.count(b'T'), seq.count(b'-')))
if args.outfile:
bioio.save(container, args.outfile, options=args.io_opts or [])
def main( args ):
aaseqs = bioio.multisequence()
for infile in args.files:
mseq = bioio.load( infile, options = args.io_opts )
cout('reading %d sequences from %s' % (len(mseq), infile))
for seq in mseq:
aaseq = seq.clone()
aaseq.set_sequence( funcs.translated(seq, start_pos = args.start_codon ) )
aaseqs.append( aaseq )
bioio.save( aaseqs, args.outfile )
def dereplicate(mseq):
from seqpy.core.bioio import biosequence, multisequence
dedups = {}
for s in mseq:
if str(s.seq) in dedups:
dedups[str(s.seq)][1].append( s.label )
else:
dedups[str(s.seq)] = (s.seq, [ s.label ] )
dedupseqs = multisequence()
for (k, v) in dedups.items():
dedupseqs.append( biosequence( '#'.join( v[1] ), v[0] ) )
return dedupseqs
def gather_consensus( args ):
# set output directory
args.outdir = args.indir + '-results' if not args.outdir else args.outdir
# open input file
cons = multisequence()
header = None
stat_lines = []
if args.add:
seqs = load(args.add)
cons.extend( seqs )
for indir in sorted(os.listdir(args.indir)):
seqpath = os.path.join(args.indir, indir, args.consfile)
print(args.indir, indir, args.consfile, seqpath)
try:
seqs = load(seqpath)
except FileNotFoundError:
cerr('[WARN: no such file: %s]' % (seqpath) )
continue
cons.append( seqs[0] )
statpath = os.path.join(args.indir, indir, args.statfile)
with open(statpath) as fin:
lines = fin.read().split('\n')
if not header:
header = lines[0].strip()
stat_lines.append( lines[1].strip() )
try:
os.mkdir(args.outdir)
except:
pass
save( cons, os.path.join(args.outdir, 'consensus.fas' ) )
with open( os.path.join(args.outdir, 'stats.tsv'), 'w') as fout:
fout.write(header)
fout.write('\n')
fout.write('\n'.join(stat_lines))
cerr(f'[Writing results to directory {args.outdir}]')
def main(args):
mseq = bioio.multisequence()
for infile in args.files:
trace = bioio.load(infile)
result = traceutils.trim(trace, args.winsize, args.qual_threshold)
if not result:
continue
bases, quals, upstream_trim, downstream_trim = result
seq = bioio.biosequence(infile, bases)
seq.add_attr('upstream_trim', str(upstream_trim))
seq.add_attr('downstream_trim', str(downstream_trim))
mseq.append(seq)
bioio.save(mseq, args.outfile)
def seq2pi(args):
# open and read sequence file
cerr('[I - reading sequence file %s]' % args.infile)
seqs = load(args.infile)
# open and read group/meta file using groupfile/metafile if available
if args.groupfile or args.metafile:
cerr('[I - reading group information file]')
group_parser = grpparser.GroupParser(args)
group_parser.parse()
group_seqs = {}
for seq in seqs:
try:
grp = group_parser.group_info[seq.label.decode('ASCII')]
except KeyError:
cerr('[W - sample %s is not assign to any group]' %
seq.label.decode('ASCII'))
continue
if grp in group_seqs:
group_seqs[grp].append(seq)
else:
ms = multisequence()
ms.append(seq)
group_seqs[grp] = ms
else:
group_seqs = {'ALL': seqs}
print('Groups:')
outf = open(args.outfile, 'w') if args.outfile else None
if outf:
outf.write('GROUP\tN\tPI\tSTDDEV\n')
for g in group_seqs:
avg, stddev = calc_pi(group_seqs[g])
cout(' %20s [%3d]: %f +- %f' % (g, len(group_seqs[g]), avg, stddev))
if outf:
outf.write('%s\t%d\t%5.4f\t%5.4f\n' %
(g, len(group_seqs[g]), avg, stddev))
if outf:
cerr('[I - result written to %s' % args.outfile)
def main(args):
circseqs = bioio.multisequence()
mseq = bioio.load(args.infile, options=args.io_opts)
rseq = bioio.load(args.reffile)
for seq in mseq:
circseq = seq.clone()
if args.minlen > 0 and len(seq) > args.minlen:
print('seq:', circseq.label)
circseq.set_sequence(
recircularize_sequence(seq.seq,
rseq[0].seq,
max_mismatch=args.max_mismatch))
else:
circseq.set_sequence(seq.seq)
circseqs.append(circseq)
bioio.save(circseqs, args.outfile)
def main(args):
import dendropy
tree = dendropy.Tree.get(path=args.treefile, schema="newick")
pdc = tree.phylogenetic_distance_matrix()
cerr('Reading: %d taxa' % len(tree.taxon_namespace))
if args.collect > 0:
ref_seqs = bioio.load(args.reffile)
ref_taxa = []
for taxon in tree.taxon_namespace:
if ref_seqs.get_by_label(taxon.label) != None:
print('appended')
ref_taxa.append(taxon)
cerr('Referenced: %d taxa' % len(ref_taxa))
collected_taxa = set()
for t1 in ref_taxa:
d = []
for t2 in tree.taxon_namespace[:-1]:
d.append((pdc(t1, t2), t2))
d.sort()
for i in range(args.collect):
collected_taxa.add(d[i][1])
collected_taxa.add(t1)
cerr('Collected: %d taxa' % len(collected_taxa))
db_seqs = bioio.load(args.dbfile)
mseq = bioio.multisequence()
for taxon in collected_taxa:
mseq.append(db_seqs.get_by_label(taxon.label))
bioio.save(mseq, args.outfile)
def main(args):
circseqs = bioio.multisequence()
mseq = bioio.load(args.infile, options=args.io_opts)
rseq = bioio.load(args.reffile)
for seq in mseq:
if seq.label != 'NODE_2_length_4501_cov_41.785': continue
if len(seq) < len(rseq[0]):
cerr('WARNING: %s is shorter than reference' % seq.label)
circseq = seq.clone()
if args.minlen > 0 and len(seq) > args.minlen:
print('seq:', circseq.label)
circseq.set_sequence(
recircularize_sequence(seq.seq,
rseq[0].seq,
max_mismatch=args.max_mismatch))
else:
circseq.set_sequence(seq.seq)
circseqs.append(circseq)
bioio.save(circseqs, args.outfile)
def init_params(self):
self.mseq = bioio.multisequence()
self.chr_used = defaultdict(int)
def file_new(self):
obj = bioio.multisequence()
obj.set_filename('untitled')
self.view( obj )