def fasta_get_freq(seq,start= 0,end= 0,step= 1,ksize=3,bases= 'ATCG'):
'''return count of kmer across fasta region'''
kmer_dict= kmer_dict_init(ksize= ksize,bases=bases)
if end == 0:
end= len(seq) - ksize
for ki in range(start,end,step):
kmer= seq[ki:ki+ksize]
if 'N' in kmer:
continue
get_by_path(kmer_dict, kmer[:-1])[kmer[-1]] += 1
return kmer_dict
def kmer_freq_balance(kmer_dict, mutations, fasta_len= 10000, bases= 'ACGT',ksize= 3):
'''return list of possible kmer mutations'''
mutation_sum= []
Nkmers= fasta_len - ksize
for idx in range(len(mutations)):
mut= mutations[idx]
prop= get_by_path(kmer_dict,mut[0])
prop= prop / Nkmers
mutation_sum.append(prop)
return np.array(mutation_sum).reshape(1,-1)
def vcf_muts_matrix_v1(refseq,summary,start= 0,end= 0,ksize= 3,bases='ATCG', collapse= True):
'''
Return matrix of mutation contexts by SNP in genotype array
Each mutation is mapped to list of possible mutations as a binary vector.
- v1 determines if alternative allele = reference allele in fasta.
if so, allele is switched, position idx is flagged.
'''
mutations= get_mutations(bases= bases,ksize= ksize)
kmers, kmer_idx= kmer_comp_index(mutations)
mut_lib= kmer_mut_index(mutations)
if end == 0:
end= max(summary.POS)
k5= int(ksize/2)
k3= ksize - k5
pos_mut= []
flag_reverse= []
flag_remove= []
for x in range(summary.shape[0]):
pos= int(summary.POS[x]) - 1
if pos >= start and pos <= end:
kmer= refseq[pos-k5: pos + k3]
if 'N' in kmer:
flag_remove.append(x)
continue
mut= kmer + summary.ALT[x]
if kmer[1] == summary.ALT[x]:
flag_reverse.append(x)
mut= kmer+summary.REF[x]
if len(mut) != 4:
print(kmer)
print(summary.REF[x],summary.ALT[x])
print(x,pos)
print(len(refseq),summary.shape[0])
if collapse:
mut_array=np.zeros(len(kmer_idx))
pos_mut.append(mut_array)
continue
else:
mut_array=np.zeros(len(mutations))
pos_mut.append(mut_array)
continue
if collapse:
mut_index= kmers[mut]
mut_array=np.zeros(len(kmer_idx))
else:
mut_index= get_by_path(mut_lib, list(mut))
mut_array=np.zeros(len(mutations))
mut_array[mut_index]= 1
pos_mut.append(mut_array)
pos_mut= np.array(pos_mut).T
return pos_mut, flag_reverse, flag_remove