从字符串中或文件中获取序列信息

#从长度不是特别长的fasta_string中获取序列，去除序列中的空格并全部转为大写，序列以（序列名，序列）的形式，保存到列表中
def get_sequences_from_fasta_string(fasta_string):
        assert isinstance(fasta_string,str)
        sequences=[]
        for item in fasta_string.split('>')[1:]:
            seq_name=item.split('\n')[0]
            seq=''.join(''.join(item.split('\n')[1:]).split()).upper()
            sequences.append((seq_name,seq))
        return sequences

# 将一个文件夹内的序列文件提取生成到一个fasta文件里
import glob
extend_names=['txt','seq','fasta']
s=''
for extend_name in extend_names:
    for filename in glob.glob(r'c:\users\seln\desktop\sequences\*.{}'.format(extend_name)):
        with open(filename,'r')as f:
            seq=''.join(list(filter(lambda char:char.isalpha(),
                                          f.read())))
            s+=">%s\n%s\n" % (filename.split('\\')[-1],seq)


#利用生成器，从序列数非常巨大的文件里读取序列
def get_items_from_file(filename,testfun=None):
    with open(filename) as file:
        return get_items(file,testfun)

def get_items(src,testfun=None):
    return [item for item in item_generator(src) if not testfun or testfun(item)]

def item_generator(src):
    skip_intro(src)
    des=[]
    seq=''
    for line in src:
        if line[0]=='>':
            if des:
                yield des,seq
            des=line[1:-1].split('|')
            seq=''
        else:
            seq+=line[:-1]
    yield des,seq

def skip_intro(src):
    line=src.readline()
    while line[0]!='A':
        line=src.readline()

def find_item_in_file(filename,testfun=None):
    with open(filename)as file:
        return find_item(file,testfun)

def find_item(src,testfun=None):
    gen=item_generator(src)  #生成器函数一定要赋给一个变量后使用！！！
    item=next(gen)
    if not testfun:
        return item
    else:
        try:
            while not testfun(item):
                item=next(gen)
            return item