def main():
amino_acids = set(codon_table.values()) - set('*')
spike_nt_1, spike_aa_1 = generate_spike(30)
spike_nt_2, spike_aa_2 = generate_spike(40)
#print(spike_nt_1, spike_aa_1, spike_nt_2, spike_aa_2, sep='\n')
query = randseq(200) + binf.reverse_complement(spike_nt_2) + randseq(200) + binf.reverse_complement(spike_nt_1) + randseq(200)
subj = randseq(100, amino_acids) + spike_aa_1 + randseq(100, amino_acids) + spike_aa_2 + randseq(120, amino_acids)
binf.write_fasta_seq(sys.stdout, 'Q1', query)
binf.write_fasta_seq(sys.stdout, 'S1', subj)
def print_longest_isoforms_for_each_gene(in_file, delimiter, seq_lengths):
for header, seq in binf.parse_fasta(in_file):
seq_id, gene_id, isoform_id = extract_ids(header, delimiter)
if gene_id not in seq_lengths:
continue
max_isoform_len = find_max_isoform_length_for_gene(gene_id, seq_lengths)
if len(seq) == max_isoform_len:
binf.write_fasta_seq(sys.stdout, header, seq)
# To mark a given gene as already having had its longest isoform printed,
# remove the gene from seq_lengths.
del seq_lengths[gene_id]
def extract_exons(fasta_fname, gff_fname):
sequences = HTSeq.FastaReader(fasta_fname)
# end_included=True as (exon.end - exon.start) % 3 = 2.
gff = HTSeq.GFF_Reader(gff_fname, end_included=True)
features = defaultdict(lambda: defaultdict(list))
for feat in gff:
features[feat.name][feat.type].append(feat)
for kog, feats in features.items():
exons = feats['Exon']
exons = sorted(exons, key=lambda e: e.iv.start)
seq = ''.join([str(sequences[exon.iv]) for exon in exons])
binf.write_fasta_seq(sys.stdout, kog, seq)
def extract_exons(fasta_fname, gff_fname):
sequences = HTSeq.FastaReader(fasta_fname)
# end_included=True as (exon.end - exon.start) % 3 = 2.
gff = HTSeq.GFF_Reader(gff_fname, end_included=True)
features = defaultdict(lambda: defaultdict(list))
for feat in gff:
features[feat.name][feat.type].append(feat)
for kog, feats in features.items():
exons = feats['Exon']
exons = sorted(exons, key=lambda e: e.iv.start)
seq = ''.join([str(sequences[exon.iv]) for exon in exons])
binf.write_fasta_seq(sys.stdout, kog, seq)
def main():
amino_acids = set(codon_table.values()) - set('*')
spike_nt_1, spike_aa_1 = generate_spike(30)
spike_nt_2, spike_aa_2 = generate_spike(40)
#print(spike_nt_1, spike_aa_1, spike_nt_2, spike_aa_2, sep='\n')
query = randseq(200) + binf.reverse_complement(spike_nt_2) + randseq(
200) + binf.reverse_complement(spike_nt_1) + randseq(200)
subj = randseq(100, amino_acids) + spike_aa_1 + randseq(
100, amino_acids) + spike_aa_2 + randseq(120, amino_acids)
binf.write_fasta_seq(sys.stdout, 'Q1', query)
binf.write_fasta_seq(sys.stdout, 'S1', subj)
def print_longest_isoforms_for_each_gene(in_file, delimiter, seq_lengths):
for header, seq in binf.parse_fasta(in_file):
seq_id, gene_id, isoform_id = extract_ids(header, delimiter)
if gene_id not in seq_lengths:
continue
max_isoform_len = find_max_isoform_length_for_gene(
gene_id, seq_lengths)
if len(seq) == max_isoform_len:
binf.write_fasta_seq(sys.stdout, header, seq)
# To mark a given gene as already having had its longest isoform printed,
# remove the gene from seq_lengths.
del seq_lengths[gene_id]
def main():
seq_set_id = sys.argv[1]
munged_fasta_filename = sys.argv[2]
mapping_filename = sys.argv[3]
name_mapping = {}
count = 1
with open(munged_fasta_filename, "w") as munged_fasta_file:
for seq_id, seq in binf.parse_fasta(sys.stdin):
new_name = "%s_prot%s" % (seq_set_id, count)
name_mapping[new_name] = seq_id
binf.write_fasta_seq(munged_fasta_file, new_name, seq)
count += 1
with open(mapping_filename, "w") as mapping_file:
json.dump(name_mapping, mapping_file)
def main():
seq_set_id = sys.argv[1]
munged_fasta_filename = sys.argv[2]
mapping_filename = sys.argv[3]
name_mapping = {}
count = 1
with open(munged_fasta_filename, 'w') as munged_fasta_file:
for seq_id, seq in binf.parse_fasta(sys.stdin):
new_name = '%s_prot%s' % (seq_set_id, count)
name_mapping[new_name] = seq_id
binf.write_fasta_seq(munged_fasta_file, new_name, seq)
count += 1
with open(mapping_filename, 'w') as mapping_file:
json.dump(name_mapping, mapping_file)
