最近在做circos图，由于我的重复序列的gff文件不是标准格式，无法用软件生成，只好自己写一个python脚本，本脚本可处理各种类似gff格式的文件，转化为适用于circos所用的基因密度文件。有需要可以拿去使用，改一下我用#注释的那些部分就行。

import pandas as pd


filename = "F:/circos/data/newEGL/XTJ.genome.fasta.out.gff"#文件名
df =  pd.read_csv(filename,sep='\t',header=None)
fileresult = filename + '.re'
f = open(fileresult , "w")
#区间
bin = 100000
for i in range(1,10):#染色体数
    cluster_name = 'cluster0' + str(i) #染色体名称
    chr_name = df.loc[df.iloc[:,0]== cluster_name]
    chr_end_name = chr_name.iloc[:, 4]#基因终止位置所在的列数减1，记得要减1
    right = 0
    while True:
        right += bin
        if right < chr_end_name.iloc[-1]:
            left = right - bin

        else:
            left = right - bin
            right = int(chr_end_name.iloc[-1])
            len(chr_end_name[chr_end_name<right])
            bool = chr_end_name < right
            less = chr_end_name[bool]
            f.write('chr0'+str(i) + '\t' + str(left) +'\t' +str(right)+'\t' + str(len(less[less >= left])) + '\n')
            break

        len(chr_end_name[chr_end_name<right])
        bool = chr_end_name < right
        less = chr_end_name[bool]
        f.write('chr0'+str(i) + '\t' + str(left) +'\t' +str(right)+'\t' + str(len(less[less >= left])) + '\n')
print('finished')

f.close()