def pick_longest_rep(fasta_filename, gff_filename, group_filename,
output_filename):
"""
For each group, select the representative record to be the longest
"""
fastad = LazyFastaReader(fasta_filename)
fout = FastaWriter(output_filename)
coords = {}
for line in open(gff_filename):
# ex: chr1 PacBio transcript 27567 29336 . - . gene_id "PB.1"; transcript_id "PB.1.1";
raw = line.strip().split('\t')
if raw[2] == 'transcript':
tid = raw[-1].split('; ')[1].split()[1][1:-2]
coords[tid] = "{0}:{1}-{2}({3})".format(raw[0], raw[3], raw[4],
raw[6])
for line in open(group_filename):
pb_id, members = line.strip().split('\t')
best_id = None
best_seq = None
max_len = 0
for x in members.split(','):
if len(fastad[x].sequence) >= max_len:
best_id = x
best_seq = fastad[x].sequence
max_len = len(fastad[x].sequence)
fout.writeRecord("{0}|{1}|{2}".format(pb_id, coords[pb_id], best_id),
best_seq)
fout.close()
def pick_longest_rep(fasta_filename, gff_filename, group_filename, output_filename):
"""
For each group, select the representative record to be the longest
"""
fastad = LazyFastaReader(fasta_filename)
fout = FastaWriter(output_filename)
coords = {}
for line in open(gff_filename):
# ex: chr1 PacBio transcript 27567 29336 . - . gene_id "PB.1"; transcript_id "PB.1.1";
raw = line.strip().split("\t")
if raw[2] == "transcript":
tid = raw[-1].split("; ")[1].split()[1][1:-2]
coords[tid] = "{0}:{1}-{2}({3})".format(raw[0], raw[3], raw[4], raw[6])
for line in open(group_filename):
pb_id, members = line.strip().split("\t")
best_id = None
best_seq = None
max_len = 0
for x in members.split(","):
if len(fastad[x].sequence) >= max_len:
best_id = x
best_seq = fastad[x].sequence
max_len = len(fastad[x].sequence)
fout.writeRecord("{0}|{1}|{2}".format(pb_id, coords[pb_id], best_id), best_seq)
fout.close()
def convert_to_dazz_fasta(self):
"""
Convert input fasta/fastq file to daligner-compatibe fasta with ids:
<prefix>/<index>/0_<seqlen>
Also write out mappings to pickle
"""
i = 1
reader = FastaReader(self.input_filename) if self.filetype == "fasta" else FastqReader(self.input_filename)
f = FastaWriter(self.dazz_filename)
for r in reader:
f.writeRecord("{p}/{i}/0_{len}".format(p=self.dazz_movie_name, i=i, len=len(r.sequence)), r.sequence)
self.dazz_mapping[i] = r.id
i += 1
f.close()
with open(self.dazz_filename + ".pickle", "w") as f:
dump(self.dazz_mapping, f)
def convert_to_dazz_fasta(self):
"""
Convert input fasta/fastq file to daligner-compatibe fasta with ids:
<prefix>/<index>/0_<seqlen>
Also write out mappings to pickle
"""
i = 1
reader = FastaReader(self.input_filename) if self.filetype == 'fasta' else \
FastqReader(self.input_filename)
f = FastaWriter(self.dazz_filename)
for r in reader:
f.writeRecord("{p}/{i}/0_{len}".format(p=self.dazz_movie_name, i=i, len=len(r.sequence)), r.sequence)
self.dazz_mapping[i] = r.id
i += 1
f.close()
with open(self.dazz_filename + '.pickle', 'w') as f:
dump(self.dazz_mapping, f)
