d = "dump.data.mci.I14"#可以换成40,20
d1 = "dump.data.mci.I-14"#可以换成40,20
fo = open(d,"r")
f = open(d1,"a+")
fo = fo.readlines()
n = 0
for line in fo:
    line = line.split("\t")
    ID = []
    if len(line) == 80:
        for i in line:
            ID.append(i[15:29])
        ID_set = set(ID)
        if len(ID_set) == len(ID):
            f.write("\t".join(line))
            n += 1
f.close()
print("同学，一共{}个单拷贝基因家族".format(n))

def extract(filename1,filename2,prefix,suffix):#提取单序列家族序列
    f = open(filename1, "r")
    f_list = f.readlines()
    f.close()
    fo = open(filename2, "r")
    fo_list = fo.readlines()
    fo.close()
    for i in range(len(f_list)):
        t = open(prefix + str(i) + suffix, "a+")
        f_name = f_list[i].strip("\n")
        f_name = f_name.split("\t")
        lines = []
        for ID in f_name:
            line = ""
            n = 0
            for row in fo_list:
                if ID in row:
                    n += 1
                    line += row
                elif row[0] != ">" and n == 1:
                    line += row
                elif row[0] == ">" and n == 1:
                    break
                else:
                    continue
            lines.append(line)
        t.write("".join(lines))
        t.close()
    return "提取完成"
#示例：获取dump.data.mci.I-40中的每个基因家族的序列
d = "dump.data.mci.I-14"#此变量可以赋值为dump.data.mci.I-20(或者40)
a = "E:/R学习、/基因组学/实习/genomelab-1/all_pro.faa"
prefix = "I14-"#可以改为I20-或者I40
suffix = ".faa"
extract(d,a,prefix,suffix)

def filenames(path,prefix,suffix):
    import os
    path_list = os.listdir(path)
    path_list1 = []
    for f in path_list:
        if f.find(suffix) != -1:
            path_list1.append(f)
    filename = []
    for i in range(len(path_list1)):
        filename.append(prefix + str(i) + suffix)
    return filename
def ID(filename,IDname):
    f = open(filename,"r").readlines()
    fo = open(IDname,"a+")
    for line in f:
        if line[0] == ">":
            fo.write(">"+line[16:29]+"\n")
    fo.close()
    return
def merge_seq(ID_merge_file,new_file,total_mergefilename):
    f = open(new_file, "a+")
    fo = open(ID_merge_file, "r")
    fo_list = fo.readlines()
    for i in fo_list:
        lines = i
        for I in total_mergefilename:
            seq = open(I, "r").readlines()
            n = 0
            for row in seq:
                if row.find(i[1:16].strip("\n")) != -1:
                    n += 1
                elif row[0] != ">" and n == 1:
                    row = row.strip("\n")
                    lines += row
                elif row[0] == ">" and n == 1:
                    break
                else:
                    continue
        f.write(lines + "\n")
    f.close()
    return "序列融合完毕"
if __name__ == '__main__':
    path = "E:/R学习、/基因组学/实习/results/I14"  # 20,40
    prefix = "I14-"  # 20,40
    suffix = ".afa"
    file = "I14-0.afa"  # 从中提取80个GCP名
    name = "ID_I14.faa"  # 80个GCP名字所在文件名字，此时为空
    I_filename = filenames(path, prefix, suffix)  # 获得需要合并的文件的总名称数且进行了顺序排列
    ID(file, name)  # 将80个GCP的ID储存在了name代表的文件名中
    after_mergefile = "all_I14.faa"  # 序列融合后得到的文件名称
    merge_seq(name, after_mergefile, I_filename)