python合并RepeatMasker预测结果中染色体的overlap区域

    awk '{for(i = 1; i <= 3; i++) 
         printf("%s ", $i); 
         printf("\n")}' result.txt >  pretreatment.txt  
         #result.txt为结果文件，pretreatment.txt为预处理结果文件

with open ('pretreatment.txt','r')as f:
    for i in f.readlines():
        if i.strip() == '//':
            continue
        c = i.strip().split('\t')
        b.append(c[0])
        a.append((c[0],int(c[1]),int(c[2])))
print ("全部染色体数量: "+str(len(a)))

c = [i for i in b_set if b.count(i) == 1]
for i in a:
    if i[0] not in c:
        continue
    a.remove(i)
    result.append((i[0],int(i[1]),int(i[2])))
print ("去重后染色体数量: "+str(len(a)))

a.sort(key = lambda x : (x[0], x[1], x[2])) 
#按照第一列，第二列，第三列分别排降升序

q = ''
start = 0
end = 0
tem1 = []
tem2 = []
gap = 50 
for i in a:
    if i[0] != q:
        if tem1:
            if tem1 not in tem2:
                tem2.append(tem1)
                tem1 = []
        q = I[0]
        start = int(i[1])
        end = int(i[2])
        continue
    if int(i[1]) < end or int(i[1]) - end < gap:
        if int(i[2]) > end:
            end = int(i[2])
            continue
        else:
            continue
    tem1.append([q,start,end])
    start = int(i[1])
    end = int(i[2])

with open ('new_result.txt','w')as f:
    for i in tem2:
        for o in I:
            print (o[0],o[1],o[2],file=f)
    for i in result:
        print (i[0],i[1],i[2],file=f)

a = []
b = []
with open ('pretreatment.txt','r')as f:
    for i in f.readlines():
        if i.strip() == '//':
            continue
        c = i.strip().split('\t')
        b.append(c[0])
        a.append((c[0],int(c[1]),int(c[2])))
print ("全部染色体数量: "+str(len(a)))
b_set = set(b)
result = []
c = [i for i in b_set if b.count(i) == 1]
for i in a:
    if i[0] not in c:
        continue
    a.remove(i)
    result.append((i[0],int(i[1]),int(i[2])))
print ("去重后染色体数量: "+str(len(a)))
a.sort(key = lambda x : (x[0], x[1], x[2]))
q = ''
start = 0
end = 0
tem1 = []
tem2 = []
gap = 50
for i in a:
    if i[0] != q:
        if tem1:
            if tem1 not in tem2:
                tem2.append(tem1)
                tem1 = []
        q = I[0]
        start = int(i[1])
        end = int(i[2])
        continue
    if int(i[1]) < end or int(i[1]) - end < gap:
        if int(i[2]) > end:
            end = int(i[2])
            continue
        else:
            continue
    tem1.append([q,start,end])
    start = int(i[1])
    end = int(i[2])
with open ('new_result.txt','w')as f:
    for i in tem2:
        for o in I:
            print (o[0],o[1],o[2],file=f)
    for i in result:
        print (i[0],i[1],i[2],file=f)