python生信小练习（三）

生信菜鸟团的编程练习：

对FASTQ的操作

• 5,3段截掉几个碱基
• 序列长度分布统计
• FASTQ 转换成 FASTA
• 统计碱基个数及GC%
  对FASTA的操作
• 取互补序列
• 取反向序列
• DNA to RNA
• 大小写字母形式输出
• 每行指定长度输出序列
• 按照序列长度/名字排序
• 提取指定ID的序列
• 随机抽取序列

def trim(file, terminal5, terminal3):
    fastq = {}
    count = 1
    for line in open(file):
        if count % 4 == 1:           #取第一行作为reads name
            readID = line.strip()
            fastq[readID] = []
        elif count % 4 == 2:         #取第二行作为序列
            seq = line.strip()
            fastq[readID] = seq[terminal5 : -terminal3]           #序列切片操作，截取两端，保留中间序列，并存储为字典
        count += 1
    with open(r'E:\Bioinformatics\Python\practice\PyCharm\practice of biotrainee\trim.txt', 'w') as f:
        for key, value in fastq.items():
            print('{}\n{}'.format(key, value), file = f)

f1 = r'E:\Bioinformatics\Python\practice\chentong\notebook-master\data\test1.fq'

trim(f1, 5, 8)

def readLength(file):
    fastq = {}
    count = 1
    for line in open(file):
        if count % 4 == 1:  # 取第一行作为reads name
            readID = line.strip()
            fastq[readID] = []
        elif count % 4 == 2:  # 取第二行作为序列
            seq = line.strip()
            fastq[readID] = len(seq)  # 序列长度统计，并存储为字典
        count += 1
    for key, value in fastq.items():
        print(value)


def fq2fa(file):
    fastq = {}
    count = 1
    for line in open(file):
        if count % 4 == 1:  # 取第一行作为reads name
            readID = line.split(' ')[1:]    #去除@，取第一个空格前字符为ID
            fastq[readID] = []
        elif count % 4 == 2:  # 取第二行作为序列
            seq = line.strip()
            fastq[readID] = seq
        count += 1
    with open(r'E:\Bioinformatics\Python\practice\PyCharm\practice of biotrainee\fq2fa.txt', 'w') as f:
        for key, value in fastq.items():
            print('>{}\n{}'.format(key, value), file = f)

def countGC(file):
    count = 1
    seq = []
    for line in open(file):
        if count % 4 == 2:  # 取第二行作为序列
            seq.append(line.strip())
        count += 1
    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))

def complementary(file):
    fasta = {}
    for line in open(file):
        if line.startswith('>'):
            key = line.strip()
            fasta[key] = []
        else:
            complem = line.strip().replace('A', 't').replace('T', 'a').replace('G', 'c').replace('C', 'g').upper()
            fasta[key].append(complem)
    for key, value in fasta.items():
        print(key)
        value2 = ''.join(value)
        for i in range(0, len(value2), 60):
            print(value2[i: i + 60])

def reverse(file):
    fasta = {}
    for line in open(file):
        if line.startswith('>'):
            key = line.strip()
            fasta[key] = []
        else:
            fasta[key].append(line.strip())
    for key, value in fasta.items():
        print(key)
        rev = ''.join(value)[:: -1]
        for i in range(0, len(rev), 60):
            print(rev[i: i + 60])

def dna2rna(file):
    fasta = {}
    for line in open(file):
        if line.startswith('>'):
            key = line.strip()
            fasta[key] = []
        else:
            seq = list(line.strip())
            for i in range(len(seq)):
                if seq[i] == 'T':
                    seq[i] = 'U'
                elif seq[i] == 't':
                    seq[i] = 'u'
            fasta[key].append(''.join(seq))
    for key, value in fasta.items():
        print(key)
        value2 = ''.join(value)
        for i in range(0, len(value2), 60):
            print(value2[i: i + 60])

def upperandlower(file):
    upper = {}
    lower = {}
    for line in open(file):
        if line.startswith('>'):
            key = line.strip()
            upper[key] = []
            lower[key] = []
        else:
            upper[key].append(line.strip().upper())
            lower[key].append(line.strip().lower())
    for key, value in upper.items():
        print(key)
        value2 = ''.join(value)
        for i in range(0, len(value2), 60):
            print(value2[i: i + 60])
    for key, value in lower.items():
        print(key)
        value2 = ''.join(value)
        for i in range(0, len(value2), 60):
            print(value2[i: i + 60])

def sortLength():
    fasta = {}
    for line in open(file):
        if line.startswith('>'):
            key = line.strip()
            fasta[key] = []
        else:
            fasta[key].append(line.strip())
    for key, value in fasta.items():
        seq = ''.join(value)
        fasta[key] = seq