python匹配替换match_使用Perl和Python实现R match()字符串匹配替换

最新推荐文章于 2023-10-26 15:00:09 发布

weixin_39720516

最新推荐文章于 2023-10-26 15:00:09 发布

阅读量168

点赞数

文章标签： python匹配替换match

文件1，需要匹配的字符串对应列表(制表符分割的纯文本文件)：

1NC_010443.5

2NC_010444.4

3NC_010445.4

4NC_010446.5

5NC_010447.5

6NC_010448.4

7NC_010449.5

8NC_010450.4

9NC_010451.4

10NC_010452.4

11NC_010453.5

12NC_010454.4

13NC_010455.5

14NC_010456.5

15NC_010457.5

16NC_010458.4

17NC_010459.5

18NC_010460.4

XNC_010461.5

YNC_010462.3

文件2，vcf文件：

NC_010443.5112.CT496PASSDP=261;VDB=0.00422737;SGB=25.2245;RPB=0.537737;MQB=1;MQSB=1;BQB=0.570213;MQ0F=0;ICB=0.886034;HOB=0.0502959;AC=6;AN=52;DP4=189,12,25,1;MQ=60GT:PL0/0:0,12,1290/0:0,30,2240/0:0,18,1410/0:0,3,370/0:0,24,2210/0:0,27,1630/0:0,24,1880/1:114,0,190/1:114,0,1800/0:0,24,1621/1:129,15,00/1:86,0,1360/0:0,21,1950/0:0,18,1880/0:0,15,1230/1:142,0,890/0:0,15,1490/0:0,24,1620/0:0,15,1290/0:0,18,1650/0:0,60,2090/0:0,36,1950/0:0,36,1900/0:0,33,1870/0:0,69,2080/0:0,30,187

NC_010443.5370.GA999PASSDP=480;VDB=0.765525;SGB=-9.28185;RPB=0.816783;MQB=1;MQSB=1;BQB=0.884522;MQ0F=0;ICB=0.801775;HOB=0.0650888;AC=32;AN=52;DP4=113,62,139,120;MQ=60GT:PL1/1:255,33,00/1:223,0,1681/1:255,30,00/0:0,30,2551/1:255,45,01/1:255,51,01/1:255,33,00/0:0,63,2550/1:219,0,1950/1:244,0,1830/1:154,0,2500/1:178,0,1401/1:255,45,00/1:209,0,1320/1:81,0,1390/1:255,0,1511/1:255,66,00/1:208,0,2001/1:255,54,00/1:178,0,1000/1:138,0,1970/0:0,51,2551/1:255,60,00/1:202,0,2550/1:220,0,2100/1:183,0,231

NC_010443.5827.TC854PASSDP=533;VDB=0.00165659;SGB=31.1247;RPB=0.465534;MQB=1;MQSB=1;BQB=0.993696;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=279,188,28,15;MQ=60GT:PL0/0:0,42,2550/0:0,72,2550/0:0,60,2550/0:0,51,2550/0:0,57,2550/0:0,78,2550/0:0,57,2550/1:204,0,2160/1:99,0,2050/0:0,48,2550/1:162,0,1060/1:227,0,1220/0:0,33,2550/0:0,57,2550/0:0,66,2550/1:241,0,2550/0:0,45,2550/0:0,69,2550/0:0,48,2490/0:0,39,2550/0:0,69,2550/0:0,108,2550/0:0,87,2550/0:0,72,2550/0:0,60,2550/0:0,51,255

NC_010443.53014.GT999PASSDP=454;VDB=0.958589;SGB=-9.3863;RPB=0.937155;MQB=1;MQSB=1;BQB=0.0688294;MQ0F=0;ICB=0.801775;HOB=0.0650888;AC=32;AN=52;DP4=95,70,133,124;MQ=60GT:PL1/1:255,51,00/1:120,0,2281/1:255,51,00/0:0,24,2031/1:255,66,01/1:255,45,01/1:255,33,00/0:0,39,2550/1:204,0,2170/1:255,0,2300/1:255,0,640/1:110,0,1281/1:255,39,00/1:220,0,2420/1:149,0,2450/1:207,0,1451/1:255,42,00/1:152,0,1521/1:255,51,00/1:166,0,1300/1:141,0,1910/0:0,69,2551/1:255,48,00/1:171,0,1730/1:221,0,1620/1:192,0,177

NC_010443.53392.GA999PASSDP=536;VDB=0.706175;SGB=-1.74937;RPB=0.609963;MQB=1;MQSB=1;BQB=0.292344;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=47;AN=52;DP4=24,19,238,203;MQ=60GT:PL1/1:255,45,01/1:255,54,01/1:255,51,01/1:243,27,01/1:255,54,01/1:255,54,01/1:255,33,00/1:90,0,2550/1:255,0,2301/1:255,54,00/1:192,0,1000/1:7,0,2381/1:255,42,01/1:255,54,01/1:255,42,00/1:97,0,1771/1:255,54,01/1:255,48,01/1:255,57,01/1:255,27,01/1:255,90,01/1:255,72,01/1:255,75,01/1:255,105,01/1:255,84,01/1:255,108,0

NC_010443.53430.CT999PASSDP=512;VDB=0.314882;SGB=-8.61715;RPB=0.608373;MQB=1;MQSB=1;BQB=0.932661;MQ0F=0;ICB=0.0732873;HOB=0.0266272;AC=46;AN=52;DP4=28,26,212,207;MQ=60GT:PL1/1:255,42,01/1:255,48,01/1:255,42,01/1:255,30,01/1:255,57,01/1:255,63,01/1:255,30,00/1:125,0,2550/1:250,0,2391/1:255,54,00/1:157,0,1310/1:45,0,1551/1:255,42,01/1:255,48,01/1:255,42,00/1:127,0,1101/1:255,66,00/1:176,0,2551/1:255,51,01/1:237,30,01/1:255,75,01/1:255,72,01/1:255,45,01/1:255,111,01/1:255,90,01/1:255,102,0

NC_010443.54036.AG962PASSDP=508;VDB=0.3649;SGB=62.5434;RPB=0.806806;MQB=1;MQSB=1;BQB=0.46193;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=226,197,27,24;MQ=60GT:PL0/0:0,57,2550/0:0,72,2550/0:0,39,2550/0:0,51,2550/0:0,48,2550/0:0,33,2550/0:0,51,2550/1:198,0,1200/1:255,0,1770/0:0,57,2550/1:220,0,2420/1:114,0,2120/0:0,63,2550/0:0,39,2550/0:0,54,2550/1:255,0,1040/0:0,54,2550/0:0,48,2550/0:0,30,2550/0:0,36,2550/0:0,60,2550/0:0,105,2550/0:0,90,2550/0:0,72,2550/0:0,57,2550/0:0,39,255

NC_010443.54056.CT967PASSDP=507;VDB=0.171323;SGB=64.0362;RPB=0.82443;MQB=1;MQSB=1;BQB=0.938503;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=226,204,32,20;MQ=60GT:PL0/0:0,60,2550/0:0,60,2550/0:0,24,2550/0:0,51,2550/0:0,51,2550/0:0,39,2550/0:0,54,2550/1:171,0,980/1:244,0,1960/0:0,60,2550/1:231,0,2140/1:146,0,1820/0:0,63,2550/0:0,45,2550/0:0,45,2550/1:255,0,1490/0:0,45,2550/0:0,42,2550/0:0,39,2550/0:0,33,2550/0:0,60,2550/0:0,108,2550/0:0,99,2550/0:0,75,2550/0:0,72,2550/0:0,51,255

NC_010443.54285.CA999PASSDP=514;VDB=0.280171;SGB=59.5578;RPB=0.894116;MQB=1;MQSB=1;BQB=0.403017;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=207,231,17,32;MQ=60GT:PL0/0:0,45,2550/0:0,57,2550/0:0,36,2550/0:0,36,2550/0:0,45,2550/0:0,48,2550/0:0,39,2550/1:217,0,590/1:255,0,2550/0:0,48,2550/1:235,0,1010/1:176,0,2050/0:0,75,2550/0:0,81,2550/0:0,66,2550/1:227,0,1610/0:0,51,2550/0:0,57,2550/0:0,45,2550/0:0,33,2550/0:0,72,2550/0:0,84,2550/0:0,90,2550/0:0,72,2550/0:0,75,2550/0:0,57,255

NC_010443.54606.TC999PASSDP=494;VDB=0.0629205;SGB=-17.2915;RPB=0.463604;MQB=1;MQSB=1;BQB=0.302156;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=47;AN=52;DP4=19,19,226,183;MQ=60GT:PL1/1:255,60,01/1:255,51,01/1:255,75,01/1:255,48,01/1:255,39,01/1:244,30,01/1:255,78,00/1:161,0,2290/1:247,0,1501/1:255,42,00/1:177,0,1350/1:152,0,1461/1:255,36,01/1:255,48,01/1:255,51,00/1:144,0,2051/1:255,57,01/1:255,54,01/1:215,24,01/1:255,51,01/1:255,69,01/1:255,63,01/1:255,63,01/1:255,57,01/1:255,78,01/1:255,51,0

To do: 将文件2中第一列替换成文件1中相应的名称

使用Perl代码实现字符串匹配替换：

#!/usr/bin/perl

use strict;

use warnings;

use Getopt::Long;

my ($chrname, $vcf, $out);

GetOptions(

"help|?"=>\&USAGE,

"chr:s"=>\$chrname,

"vcf:s"=>\$vcf,

"o:s"=>\$out,

)or &USAGE;

&USAGE unless ($chrname && $vcf);

open(I1, "

open(I2, "

open(OUT,">$out");

my %hash;

while(){

chomp;

my($value,$key)=split/\s+/,$_;

$hash{$key}=$value;

}

while(){

chomp;

my($chr,$other)=split/\s+/,$_,2;

if(exists $hash{$chr}){

print OUT "$hash{$chr}\t$other\n";

}

close I1;

close I2;

close OUT;

sub USAGE{

my $usage=<Example: perl quiz1.pl -chr chrname.txt -vcf input.txt -o out.txtUseage:Options:-chr a file containning the original and new chromosome name list-vcf a vcf-like text file modified from a normal vcf-o result file-h helpUSAGE

print $usage;

exit;

}

脚本运行结果：

# 查看帮助文档：

suhui@suhui-ThinkCentre-E74:phython_Snakmake$ perl quiz1.pl -h

Discription: This script is to replace chromosome names.

Contact: Su Hui

Example: perl quiz1.pl -chr chrname.txt -vcf input.txt -o out.txt

Useage:

Options:

-chr a file containning the original and new chromosome name list

-vcf a vcf-like text file modified from a normal vcf

-o result file

-h help

查看结果文件：

suhui@suhui-ThinkCentre-E74:phython_Snakmake$ perl quiz1.pl -chr input1.txt -vcf input2.txt -o out.txt

suhui@suhui-ThinkCentre-E74:phython_Snakmake$ less -S out.txt

1112.CT496PASSDP=261;VDB=0.00422737;SGB=25.2245;RPB=0.537737;MQB=1;MQSB=1;BQB=0.570213;MQ0F=0;ICB=0.886034;HOB=0.0502959;AC=6;AN=52;DP4=189,12,25,1;MQ=60GT:PL0/0:0,12,1290/0:0,30,2240/0:0,18,1410/0:0,3,370/0:0,24,2210/0:0,27,1630/0:0,24,1880/1:114,0,190/1:114,0,1800/0:0,24,1621/1:129,15,00/1:86,0,1360/0:0,21,1950/0:0,18,1880/0:0,15,1230/1:142,0,890/0:0,15,1490/0:0,24,1620/0:0,15,1290/0:0,18,1650/0:0,60,2090/0:0,36,1950/0:0,36,1900/0:0,33,1870/0:0,69,2080/0:0,30,187

1370.GA999PASSDP=480;VDB=0.765525;SGB=-9.28185;RPB=0.816783;MQB=1;MQSB=1;BQB=0.884522;MQ0F=0;ICB=0.801775;HOB=0.0650888;AC=32;AN=52;DP4=113,62,139,120;MQ=60GT:PL1/1:255,33,00/1:223,0,1681/1:255,30,00/0:0,30,2551/1:255,45,01/1:255,51,01/1:255,33,00/0:0,63,2550/1:219,0,1950/1:244,0,1830/1:154,0,2500/1:178,0,1401/1:255,45,00/1:209,0,1320/1:81,0,1390/1:255,0,1511/1:255,66,00/1:208,0,2001/1:255,54,00/1:178,0,1000/1:138,0,1970/0:0,51,2551/1:255,60,00/1:202,0,2550/1:220,0,2100/1:183,0,231

1827.TC854PASSDP=533;VDB=0.00165659;SGB=31.1247;RPB=0.465534;MQB=1;MQSB=1;BQB=0.993696;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=279,188,28,15;MQ=60GT:PL0/0:0,42,2550/0:0,72,2550/0:0,60,2550/0:0,51,2550/0:0,57,2550/0:0,78,2550/0:0,57,2550/1:204,0,2160/1:99,0,2050/0:0,48,2550/1:162,0,1060/1:227,0,1220/0:0,33,2550/0:0,57,2550/0:0,66,2550/1:241,0,2550/0:0,45,2550/0:0,69,2550/0:0,48,2490/0:0,39,2550/0:0,69,2550/0:0,108,2550/0:0,87,2550/0:0,72,2550/0:0,60,2550/0:0,51,255

13014.GT999PASSDP=454;VDB=0.958589;SGB=-9.3863;RPB=0.937155;MQB=1;MQSB=1;BQB=0.0688294;MQ0F=0;ICB=0.801775;HOB=0.0650888;AC=32;AN=52;DP4=95,70,133,124;MQ=60GT:PL1/1:255,51,00/1:120,0,2281/1:255,51,00/0:0,24,2031/1:255,66,01/1:255,45,01/1:255,33,00/0:0,39,2550/1:204,0,2170/1:255,0,2300/1:255,0,640/1:110,0,1281/1:255,39,00/1:220,0,2420/1:149,0,2450/1:207,0,1451/1:255,42,00/1:152,0,1521/1:255,51,00/1:166,0,1300/1:141,0,1910/0:0,69,2551/1:255,48,00/1:171,0,1730/1:221,0,1620/1:192,0,177

13392.GA999PASSDP=536;VDB=0.706175;SGB=-1.74937;RPB=0.609963;MQB=1;MQSB=1;BQB=0.292344;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=47;AN=52;DP4=24,19,238,203;MQ=60GT:PL1/1:255,45,01/1:255,54,01/1:255,51,01/1:243,27,01/1:255,54,01/1:255,54,01/1:255,33,00/1:90,0,2550/1:255,0,2301/1:255,54,00/1:192,0,1000/1:7,0,2381/1:255,42,01/1:255,54,01/1:255,42,00/1:97,0,1771/1:255,54,01/1:255,48,01/1:255,57,01/1:255,27,01/1:255,90,01/1:255,72,01/1:255,75,01/1:255,105,01/1:255,84,01/1:255,108,0

13430.CT999PASSDP=512;VDB=0.314882;SGB=-8.61715;RPB=0.608373;MQB=1;MQSB=1;BQB=0.932661;MQ0F=0;ICB=0.0732873;HOB=0.0266272;AC=46;AN=52;DP4=28,26,212,207;MQ=60GT:PL1/1:255,42,01/1:255,48,01/1:255,42,01/1:255,30,01/1:255,57,01/1:255,63,01/1:255,30,00/1:125,0,2550/1:250,0,2391/1:255,54,00/1:157,0,1310/1:45,0,1551/1:255,42,01/1:255,48,01/1:255,42,00/1:127,0,1101/1:255,66,00/1:176,0,2551/1:255,51,01/1:237,30,01/1:255,75,01/1:255,72,01/1:255,45,01/1:255,111,01/1:255,90,01/1:255,102,0

14036.AG962PASSDP=508;VDB=0.3649;SGB=62.5434;RPB=0.806806;MQB=1;MQSB=1;BQB=0.46193;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=226,197,27,24;MQ=60GT:PL0/0:0,57,2550/0:0,72,2550/0:0,39,2550/0:0,51,2550/0:0,48,2550/0:0,33,2550/0:0,51,2550/1:198,0,1200/1:255,0,1770/0:0,57,2550/1:220,0,2420/1:114,0,2120/0:0,63,2550/0:0,39,2550/0:0,54,2550/1:255,0,1040/0:0,54,2550/0:0,48,2550/0:0,30,2550/0:0,36,2550/0:0,60,2550/0:0,105,2550/0:0,90,2550/0:0,72,2550/0:0,57,2550/0:0,39,255

14056.CT967PASSDP=507;VDB=0.171323;SGB=64.0362;RPB=0.82443;MQB=1;MQSB=1;BQB=0.938503;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=226,204,32,20;MQ=60GT:PL0/0:0,60,2550/0:0,60,2550/0:0,24,2550/0:0,51,2550/0:0,51,2550/0:0,39,2550/0:0,54,2550/1:171,0,980/1:244,0,1960/0:0,60,2550/1:231,0,2140/1:146,0,1820/0:0,63,2550/0:0,45,2550/0:0,45,2550/1:255,0,1490/0:0,45,2550/0:0,42,2550/0:0,39,2550/0:0,33,2550/0:0,60,2550/0:0,108,2550/0:0,99,2550/0:0,75,2550/0:0,72,2550/0:0,51,255

14285.CA999PASSDP=514;VDB=0.280171;SGB=59.5578;RPB=0.894116;MQB=1;MQSB=1;BQB=0.403017;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=5;AN=52;DP4=207,231,17,32;MQ=60GT:PL0/0:0,45,2550/0:0,57,2550/0:0,36,2550/0:0,36,2550/0:0,45,2550/0:0,48,2550/0:0,39,2550/1:217,0,590/1:255,0,2550/0:0,48,2550/1:235,0,1010/1:176,0,2050/0:0,75,2550/0:0,81,2550/0:0,66,2550/1:227,0,1610/0:0,51,2550/0:0,57,2550/0:0,45,2550/0:0,33,2550/0:0,72,2550/0:0,84,2550/0:0,90,2550/0:0,72,2550/0:0,75,2550/0:0,57,255

14606.TC999PASSDP=494;VDB=0.0629205;SGB=-17.2915;RPB=0.463604;MQB=1;MQSB=1;BQB=0.302156;MQ0F=0;ICB=0.0478148;HOB=0.0184911;AC=47;AN=52;DP4=19,19,226,183;MQ=60GT:PL1/1:255,60,01/1:255,51,01/1:255,75,01/1:255,48,01/1:255,39,01/1:244,30,01/1:255,78,00/1:161,0,2290/1:247,0,1501/1:255,42,00/1:177,0,1350/1:152,0,1461/1:255,36,01/1:255,48,01/1:255,51,00/1:144,0,2051/1:255,57,01/1:255,54,01/1:215,24,01/1:255,51,01/1:255,69,01/1:255,63,01/1:255,63,01/1:255,57,01/1:255,78,01/1:255,51,0

使用Python代码实现字符串匹配替换：

# -*- coding: utf-8 -*-

"""Created on Wed Mar 13 2019@author: hui.su """

#!/usr/bin/phython

import sys

import re

f1=open(sys.argv[1],"r")

f2=open(sys.argv[2],"r")

w=open(sys.argv[3],"w")

idhash={}

for line in f1.readlines():

line=line.strip()

(value,key)=re.split("\s+",line,1)

idhash[key]=value

f1.close()

for line2 in f2.readlines():

line2=line2.strip()

(chrom,other)=re.split("\s+",line2,1)

if chrom in idhash:

line2=idhash[chrom]+'\t'+other+'\n'

w.write(line2)

f2.close

w.close

脚本运行结果：

suhui@suhui-ThinkCentre-E74:phython_Snakmake$ python quiz1.py input1.txt input2.txt out_py.txt

suhui@suhui-ThinkCentre-E74:phython_Snakmake$ less -S out_py.txt

weixin_39720516

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
python匹配替换match_使用Perl和Python实现R match()字符串匹配替换

文件1，需要匹配的字符串对应列表(制表符分割的纯文本文件)：1NC_010443.52NC_010444.43NC_010445.44NC_010446.55NC_010447.56NC_010448.47NC_010449.58NC_010450.49NC_010451.410NC_010452.411NC_010453.512NC_010454.413NC_010455.514NC_01045...
复制链接

扫一扫