一：对起始，终止密码子计数

codon_table = {    'TAA':'STOP', 'TAG':'STOP', 'TGA':'STOP', 'ATG':'START'}
rna = ''
for line in open('C:\\shiyan\\honghua\\rna_test.fa','r'):
    if not line.startswith('>'):   ##判断是否为标题行，如果不是以'>'开头则是序列行，
        rna = rna + line.strip()
for frame in range(3):
    print('Reading frame'+str(frame + 1))   ## 需要遍历RNA序列三次：一次从序列第一位开始，一次从第二位开始，所以是第三位所以是range(3)
    count_STOP = 0
    count_START = 0
    for i in range(frame,len(rna),3):  ##第一次从0-len(rna), 第二次从1-len(rna),第三次从2-len(rna)
        codon = rna[i:i + 3]
        if codon in codon_table:
            if codon_table[codon] == 'STOP':
                count_STOP += 1
            if codon_table[codon] == 'START':
                count_START += 1
    print('START',count_START)
    print('STOP',count_STOP)

Reading frame1
START 81
STOP 234
Reading frame2
START 82
STOP 222
Reading frame3
START 83
STOP 204

二：写一个基于序列的二级结构元素预测的程序。

提示：使用如下偏好表，其中pref_H是α螺旋，pref_E是β折叠：

pref_H = {
    'A':1.45,
    'C':0.77,
    'D':0.98,
    'E':1.53,
    'F':1.12,
    'G':0.53,
    'H':1.24,
    'I':1.00,
    'K':1.07,
    'L':1.34,
    'M':1.20,
    'N':0.73,
    'P':0.59,
    'Q':1.17,
    'R':0.79,
    'S':0.79,
    'T':0.82,
    'V':1.14,
    'W':1.14,
    'Y':0.61
}
pref_E = {
    'A':0.97,
    'C':1.30,
    'D':0.80,
    'E':0.26,
    'F':1.28,
    'G':0.81,
    'H':0.71,
    'I':1.60,
    'K':0.74,
    'L':1.22,
    'M':1.67,
    'N':0.65,
    'P':0.62,
    'Q':1.23,
    'R':0.90,
    'S':0.72,
    'T':1.20,
    'V':1.65,
    'W':1.19,
    'Y':1.29
}
rna = ''
struc_rna = ''
for line in open('C:\\shiyan\\honghua\\Tempeture_reverse\\sequence.fasta','r'):
    if not line.startswith('>'):
     rna = rna + line.strip()
     for i in range(len(rna)):
         nt = rna[i]
         if pref_H[nt] >= 1 and pref_E[nt] < pref_H[nt]:
             struc_rna = struc_rna + 'H'
         elif pref_E[nt] >= 1 and pref_H[nt] <= pref_E[nt]:
             struc_rna = struc_rna + 'E'
         else:
             struc_rna = struc_rna + 'l'
print(struc_rna)
EHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEELHEEEEHHHEEEEELLLEEEHHLEEHEEEEEEELEEEELLEEEEEEHHHLELEEHLLHEHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEELHEEEEHHHEEEEELLLEEEHHLEEHEEEEEEELEEEELLEEEEEEHHHLELEEHLLHEEHEHLLELELHLEEHEELELEEEHLEEEEHEEEEELEHHEEEEHLEHEEHLEHHEEHEEEHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEELHEEEEHHHEEEEELLLEEEHHLEEHEEEEEEELEEEELLEEEEEEHHHLELEEHLLHEEHEHLLELELHLEEHEELELEEEHLEEEEHEEEEELEHHEEEEHLEHEEHLEHHEEHEEEEHELEHEHHLEEHEEHEEHLHHEHHEHHHEEEEEEHEHEHEHELEHEHEHELEHEHEEEEHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEELHEEEEHHHEEEEELLLEEEHHLEEHEEEEEEELEEEELLEEEEEEHHHLELEEHLLHEEHEHLLELELHLEEHEELELEEEHLEEEEHEEEEELEHHEEEEHLEHEEHLEHHEEHEEEEHELEHEHHLEEHEEHEEHLHHEHHEHHHEEEEEEHEHEHEHELEHEHEHELEHEHEEEEEHEEHHHHHHEHHEEHLEELEHHHELEEEEHLHHHELHELLHEEHHLHEHELEHHEEEEEHEEEEEEEEEEEEEEEEEEEEHEEEHEELEHHHLHELHLLEEEELEEEEHEELEEEHLHEELHEEEEHHHEEEEELLLEEEHHLEEHEEEEEEELEEEELLEEEEEEHHHLELEEHLLHEEHEHLLELELHLEEHEELELEEEHLEEEEHEEEEELEHHEEEEHLEHEEHLEHHEEHEEEEHELEHEHHLEEHEEHEEHLHHEHHEHHHEEEEEEHEHEHEHELEHEHEHELEHEHEEEEEHEEHHHHHHEHHEEHLEELEHHHELEEEEHLHHHELHELLHEEHHLHEHELEHHEEEEHLHEHEHEEEEEHLEHHEHHEHHEEEEEHEHEHHLEEHEEHHLHHHHHHLEHLLL