image.png
我們知道.hic 文件是高度壓縮的二進制文件，便于存儲和分析。那么如果我們想要從.hic提取某一區域的交互信息的話，該如何操作呢？這就涉及到了juicer dump。
https://github.com/aidenlab/juicer/wiki/Data-Extraction
Juicer dump 有以下參數：
Usage:
juicebox dump <observed/oe> <NONE/VC/VC_SQRT/KR> <hicFile(s)> <chr1>[:x1:x2] <chr2>[:y1:y2] <BP/FRAG> <binsize> [outfile]
dump <norm/expected> <NONE/VC/VC_SQRT/KR> <hicFile(s)> <chr> <BP/FRAG> <binsize> [outfile]
dump <loops/domains> <hicFile URL> [outfile]
示例：
juicer_tools dump observed NONE sam1.chr20.hic 20:32679500:32680500 20 BP 10000 extract_matrix.txt
提取的矩陣主要有三列：（start，end，contacts）
提取矩陣示例：
120000 32680000 1.0
350000 32680000 2.0
370000 32680000 1.0
560000 32680000 1.0
850000 32680000 1.0
980000 32680000 1.0
1190000 32680000 2.0
1270000 32680000 1.0
1300000 32680000 1.0
1800000 32680000 1.0
那么如果我們想要進行可視化的話，可以參照以下代碼轉換成HiTC格式的矩陣：
#! /usr/bin/env python3
import time
import math
import unittest
import re,sys,os
import numpy as np
import pandas as pd
from scipy import sparse
#step 1 juicer 提取矩陣
#start,end 設定
class trans_hic():
def __init__(self):
self.hic=""
self.start=0
self.end=100000
self.juicer_tools=""
self.outdir=""
self.bin=10000
self.genome='hg19'
self.juicer_dump_mat=""
self.hitc_matrix=""
self.prefix="sam1"
def extract_matrix(self):
chr=self.chr;start=self.start;end=self.end
chrom=self.chr.replace('chr','')
juicer_dump_mat="{}/{}_{}_{}_{}_dump.mat".format(self.outdir,self.prefix,chr,start,end)
self.juicer_dump_mat=juicer_dump_mat
region="{0}:{1}:{2} {0}:{1}:{2}".format(chrom,str(start),str(end))
cmd="/opt/juicer/scripts/juicer_tools dump observed NONE {} {} BP {} {}".format(self.hic,region,self.bin,juicer_dump_mat)
print(cmd)
os.system(cmd)
def reform_matrix(self):
#-----------HiTC matrix---------------------
chr=self.chr;start=self.start;end=self.end;bin=self.bin;genome=self.genome
self.hitc_matrix="{}/{}_{}_{}_{}_hitc.mat".format(self.outdir,self.prefix,chr,start,end)
print('juicer dump matrix....')
print(self.juicer_dump_mat)
mat=pd.read_table(self.juicer_dump_mat,names=['frag1','frag2','contacts'])
#print('matrix head.....')
#print(mat.head())
min=math.ceil(int(start)/bin)*bin
max=int(int(end)/bin)*bin
N=int(end/bin)-math.ceil(start/bin)+1
#---------------------- add header --------------------------
inddf=np.arange(N)
headers_ref=[genome for x in inddf]
bin_num_df=pd.Series(inddf).apply(lambda x : str(x))
headers_ref=pd.Series(headers_ref)
chromdf=pd.Series([chr for x in list(range(N))])
startdf=pd.Series(inddf*bin+min)
enddf=pd.Series((inddf+1)*bin+min)
headers_suf=chromdf.str.cat(startdf.apply(lambda x :str(x)),sep=':')
headers_suf=headers_suf.str.cat(enddf.apply(lambda x:str(x)),sep="-")
headers=bin_num_df.str.cat([headers_ref,headers_suf],sep="|")
headers=list(headers)
mat['b1']=mat['frag1'].apply(lambda x: (x-min)/bin)
mat['b2']=mat['frag2'].apply(lambda x: (x-min)/bin)
counts=sparse.coo_matrix((mat['contacts'],(mat['b1'],mat['b2'])),shape=(N, N),dtype=float).toarray()
diag_matrix=np.diag(np.diag(counts))
counts=counts.T + counts
counts=counts-diag_matrix-diag_matrix
df=pd.DataFrame(counts)
df.columns=headers
df.index=headers
#print('DataFrame.....')
#print(df.head())
df.to_csv(self.hitc_matrix,sep="\t")
return df
def z_score_norm(self):
print('z-score normlizaion ....................')
df=self.reform_matrix()
print('befor zscore.......')
print(df.head())
dsc = pd.DataFrame(np.ravel(df)).describe(include=[np.number])
df = (df - dsc.ix['mean',0])/dsc.ix['std',0]
print('after zscore....')
print(df.head())
return df
class Test_trans(unittest.TestCase):
def test_trans(self):
trhic=trans_hic()
trhic.outdir="/Test"
trhic.hic="sam1.chr1.hic"
trhic.chr='chr1'
trhic.start=62932570
trhic.end=63564575
trhic.extract_matrix()
trhic.reform_matrix()
if __name__ == '__main__':
unittest.main()
來查看一下結果。
image.png
