def get_gc(some_gbk):
"""
Get GC content for contigs in genbank file, output file for circs line plot
"""
with open (some_gbk, 'r') as file_handle:
gc_points = []
sp_name = None
for record in SeqIO.parse(file_handle, 'gb'):
for b in range(len(record))[500::1000]:
gc_cont = SeqUtils.GC(record.seq[b-500:b+499])
gc_points.append((record.name, b-500, b+499, gc_cont))
sp_name = kv.parse_genbank_name(some_gbk)
sp_strain = sp_name[2]
with open('circos/GC/gc_{}.txt'.format(os.path.basename(some_gbk)[:-13]), 'w+') as out_handle:
values = [x[3] for x in gc_points]
stats = (min(values), max(values), np.average(values), np.std(values))
out_handle.write("# Min: {}\n# Max: {}\n# Avg, Std: {}, {}\n".format(
stats[0], stats[1], stats[2], stats[3]
)
)
for point in gc_points:
out_handle.write('{0}{1} {2} {3} {4}\n'.format(
sp_strain,
point[0],
point[1],
point[2],
point[3]
)
)
return stats
def get_karyotype(some_gbk):
"""
Convert Genbank file into Karyotype file for Circos
- Each contig is a "chromosome"
- format: 'chr - ID LABEL START END COLOR'
"""
with open (some_gbk, 'r') as file_handle:
contigs = []
sp_name = None
for record in SeqIO.parse(file_handle, 'gb'):
sp_name = kv.parse_genbank_name(some_gbk)
contigs.append((record.name, len(record)))
sp_strain = sp_name[2]
if not os.path.isdir('circos/karyotypes/'):
os.makedirs('circos/karyotypes/')
with open('circos/karyotypes/karyotype_{}.txt'.format(os.path.basename(some_gbk)[:-13]), 'w+') as karyotype:
color = [np.random.randint(0,255), np.random.randint(0,255), np.random.randint(0,255)]
for contig in contigs:
if contig[1] > 1000:
karyotype.write('chr - {0}{1} {2} {3} {4} {5},{6},{7}\n'.format(
sp_strain,
contig[0],
contig[0],
'1',
contig[1],
*color
)
)
else:
break
