1.序列长度分布统计
dict = {}
output=open('/home/yt/PycharmProjects/test/1.fastq.result','w')
with open('/home/yt/Desktop/1.fastq') as input_fastq:
for index , line in enumerate(input_fastq):
if index % 4 == 0:
id = line.strip('\n')
dict[id] = ''
if index % 4 == 1:
dict[id] = len(line.strip('\n'))
#print(dict)
count_0_50 = 0
count_50_120 = 0
for k,v in dict.items():
if 0 < v < 50:
count_0_50 += 1
if 50 <= v < 120:
count_50_120 += 1
print("count_0_50:",count_0_50)
print("count_50_80:",count_50_120)
2.FASTQ转换成FASTA
def fastaq_2_fasta(fastaq):
fasta_dict = {}
fasta_q_split = fastaq.split('\n+\n')[:-1]
for fastaq in fasta_q_split:
fasta = fastaq.split('\n')[-2:]
fasta_dict['>' + fasta[0]] = fasta[1]
return fasta_dict
file_read_name = '/home/yt/Desktop/1.fastq'
with open(file_read_name) as fastafile:
fileRead = fastafile.read()
fasta = fastaq_2_fasta(fileRead)
file_save_name = '/home/yt/PycharmProjects/test/1.fastaq_to_fasta.fasta'
with open(file_save_name, 'w') as save_file:
for name in fasta:
string = name + '\n' + fasta[name] + '\n'
save_file.write(string)
3.统计各种碱基个数及GC%
dict = {}
seq = []
with open('/home/yt/Desktop/1.fastq') as input_fastq:
for index , line in enumerate(input_fastq):
if index % 4 == 0:
id = line.strip('\n')
dict[id] = ''
if index % 4 == 1:
seq.append(line.strip())
seq1 = ''.join(seq)
gc = 0
for i in seq1:
if i == 'G' or i == 'C':
gc += 1
print('The number of length is {}'.format(len(seq1)))
print('GC% is {}%'.format(gc / len(seq1) * 100))
