【Python小试】统计一条核酸序列中频数非0或为2的双核苷酸

概念

双核苷酸由任意2个碱基组成

测试1

dna = "AATGATGAACGAC"
#一一列举
dinucleotides = ['AA','AT','AG','AC',
                 'TA','TT','TG','TC',
                 'GA','GT','GG','GC',
                 'CA','CT','CG','CT']

all_counts = {}
for dinucleotide in dinucleotides:
    count = dna.count(dinucleotide)
    if count > 0:
        all_counts[dinucleotide] = count
print(all_counts)

for dinucleotide in all_counts.keys():
    if all_counts.get(dinucleotide, 0) == 2:
        print(dinucleotide)

测试2

dna = "AATGATGAACGAC"
bases = ['A','T','G','C']
all_counts = {}
#循环生成
for base1 in bases:
    for base2 in bases:
        dinucleotide = base1 + base2
        count = dna.count(dinucleotide)
        if count > 0:
            all_counts[dinucleotide] = count
print(all_counts)

for dinucleotide in all_counts.keys():
    if all_counts.get(dinucleotide, 0) == 2:
        print(dinucleotide)

结果

AA

AT

AC

TG