def make_alt_1hot(ref_1hot, snp_seq_pos, ref_allele, alt_allele):
"""Return alternative allele one hot coding."""
ref_n = len(ref_allele)
alt_n = len(alt_allele)
# copy reference
alt_1hot = np.copy(ref_1hot)
if alt_n == ref_n:
# SNP
dna_io.hot1_set(alt_1hot, snp_seq_pos, alt_allele)
elif ref_n > alt_n:
# deletion
delete_len = ref_n - alt_n
if (ref_allele[0] == alt_allele[0]):
dna_io.hot1_delete(alt_1hot, snp_seq_pos + 1, delete_len)
else:
print('WARNING: Delection first nt does not match: %s %s' %
(ref_allele, alt_allele),
file=sys.stderr)
else:
# insertion
if (ref_allele[0] == alt_allele[0]):
dna_io.hot1_insert(alt_1hot, snp_seq_pos + 1, alt_allele[1:])
else:
print('WARNING: Insertion first nt does not match: %s %s' %
(ref_allele, alt_allele),
file=sys.stderr)
return alt_1hot
def make_alt_1hot(ref_1hot, snp_seq_pos, ref_allele, alt_allele):
"""Return alternative allele one hot coding."""
ref_n = len(ref_allele)
alt_n = len(alt_allele)
# copy reference
alt_1hot = np.copy(ref_1hot)
if alt_n == ref_n:
# SNP
dna_io.hot1_set(alt_1hot, snp_seq_pos, alt_allele)
elif ref_n > alt_n:
# deletion
delete_len = ref_n - alt_n
assert (ref_allele[0] == alt_allele[0])
dna_io.hot1_delete(alt_1hot, snp_seq_pos+1, delete_len)
else:
# insertion
assert (ref_allele[0] == alt_allele[0])
dna_io.hot1_insert(alt_1hot, snp_seq_pos+1, alt_allele[1:])
return alt_1hot
def alleles_1hot(gene_seq, seq_1hot, seq_snps):
''' One hot code for gene sequence alleles. '''
# initialize one hot coding
aseqs_1hot = []
# add reference allele sequence
aseqs_1hot.append(np.copy(seq_1hot))
# set all reference alleles
for snp in seq_snps:
# determine SNP position wrt sequence
snp_seq_pos = snp.pos - 1 - gene_seq.start
# verify that the reference allele matches the reference
seq_ref = dna_io.hot1_dna(aseqs_1hot[0][snp_seq_pos:snp_seq_pos +
len(snp.ref_allele), :])
if seq_ref != snp.ref_allele:
print(
'WARNING: %s - ref allele %s does not match reference genome %s; changing reference genome to match.'
% (snp.rsid, snp.ref_allele, seq_ref),
file=sys.stderr)
if len(seq_ref) == len(snp.ref_allele):
# SNP
dna_io.hot1_set(aseqs_1hot[0], snp_seq_pos, snp.ref_allele)
# not confident in these operations
# elif len(seq_ref) > len(snp.ref_allele):
# # deletion
# delete_len = len(seq_ref) - len(snp.ref_allele)
# dna_io.hot1_delete(aseqs_1hot[0], snp_seq_pos + 1, delete_len)
# else:
# # insertion
# dna_io.hot1_insert(aseqs_1hot[0], snp_seq_pos + 1, snp.ref_allele[1:])
else:
raise Exception(
'ERROR: reference mismatch indels cannot yet be handled.')
# for each SNP
for snp in seq_snps:
# determine SNP position wrt sequence
snp_seq_pos = snp.pos - 1 - gene_seq.start
# add minor allele sequence
aseqs_1hot.append(np.copy(aseqs_1hot[0]))
if len(snp.ref_allele) == len(snp.alt_alleles[0]):
# SNP
dna_io.hot1_set(aseqs_1hot[-1], snp_seq_pos, snp.alt_alleles[0])
elif len(snp.ref_allele) > len(snp.alt_alleles[0]):
# deletion
delete_len = len(snp.ref_allele) - len(snp.alt_alleles[0])
assert (snp.ref_allele[0] == snp.alt_alleles[0][0])
dna_io.hot1_delete(aseqs_1hot[-1], snp_seq_pos + 1, delete_len)
else:
# insertion
assert (snp.ref_allele[0] == snp.alt_alleles[0][0])
dna_io.hot1_insert(aseqs_1hot[-1], snp_seq_pos + 1,
snp.alt_alleles[0][1:])
# finalize
aseqs_1hot = np.array(aseqs_1hot)
return aseqs_1hot