利用perl从大量数据中筛选我们我们需要的数据，核心思想就是根据格式的一致性，将每一行利用split转换成数组，然后输出对应的数组

#这里我们看到这样的一组数据

##reference=file:///home/wl/Data/data/yeast/ref/S288C_R64.fasta
##source=SelectVariants
#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	d90_2_1_Clean	d90_2_2_Clean	d90_2_4_Clean	d90_2_6_Clean	d90_2_7_Clean	d90_3_11_Clean	d90_3_12_Clean	d90_3_13_Clean	d90_3_14_Clean	d90_3_2_Clean	d90_3_3_Clean	d90_3_4_Clean	d90_3_6_Clean	d90_3_7_Clean	d90_3_9_Clean
I	65	.	C	A	214.64	PASS	AC=10;AF=0.357;AN=28;BaseQRankSum=3.713;DP=93;Dels=0.00;FS=0.000;HRun=0;HaplotypeScore=7.8615;InbreedingCoeff=-0.4411;MQ=51.26;MQ0=0;MQRankSum=-3.460;QD=3.46;ReadPosRankSum=0.591;SB=-0.02;comp2	GT:AD:DP:GQ:PL	0/1:3,2:6:48.17:48,0,64	0/1:4,2:6:12.64:13,0,106	0/0:5,0:5:15.03:0,15,150	0/1:8,4:12:60.60:61,0,211	./.	0/1:5,1:6:15.42:15,0,119	0/0:3,1:4:6.02:0,6,64	0/1:2,2:4:24.58:25,0,26	0/0:3,1:4:3.01:0,3,32	0/1:10,4:14:60.46:60,0,227	0/1:3,1:4:21.41:21,0,76	0/0:11,2:13:0.45:0,0,254	0/0:2,3:5:3.01:0,3,32	0/1:4,2:6:21.40:21,0,83	1/1:1,2:4:2.99:24,3,0
I	74	.	C	G	25.82	SNPFilter	AC=3;AF=0.107;AN=28;BaseQRankSum=1.463;DP=110;Dels=0.00;FS=0.000;HRun=0;HaplotypeScore=6.7908;InbreedingCoeff=-0.1875;MQ=50.37;MQ0=0;MQRankSum=-1.866;QD=1.61;ReadPosRankSum=0.338;SB=9.61;comp2	GT:AD:DP:GQ:PL	0/0:7,0:7:18.04:0,18,193	0/0:12,0:12:30.06:0,30,303	0/0:5,0:6:15.03:0,15,150	0/0:14,0:14:39.08:0,39,398	./.	0/1:4,2:6:34.35:34,0,101	0/1:4,1:5:26.48:26,0,26	0/0:3,1:4:6.02:0,6,65	0/0:4,0:4:3.01:0,3,32	0/0:12,1:14:1.52:0,2,302	0/1:3,1:5:23.49:23,0,48	0/0:15,1:16:39.09:0,39,409	0/0:5,1:6:6.01:0,6,63	0/0:6,0:6:12.03:0,12,128	0/0:5,0:5:6:0,6,56

#虽然数据很多，但是还是按照一定的顺序排列，我们下面就是利用数据的有序性，利用空格将每一行变成一个数组，然后输出，我们需要的信息。

open (YEAST,"f:\\perl\\yeast_set2.S288C.stampy.pe.recal.variants.filter.vcf")||die("can not open the file!");
while(<YEAST>)
{
if($_=~/^##/)#这一行的作用就是判断这一行是否是我们所需要的，
{
}
elsif($_=~/^#/)
{
@category= split/\s/,$_;
open(COUNTBASE,">>f:\\perl\\a.csv")||die("can not open the file!");
print COUNTBASE "             @category[0]   @category[1] @category[3] @category[4] @category[5]  \n"
}
else
{
@information=split/\s/,$_;
$number=8;
until($number>22)
{
$number++;

if(@information[$number]=~/^0\/0/)
{
open(COUNTBASE,">>f:\\perl\\a.csv")||die("can not open the file!");
printf COUNTBASE  "@category[$number]   @information[0]     @information[1]    @information[3]  @information[4]  @information[5]  S\n" ;
}
elsif(@information[9]=~/^0\/1/)
{
open(COUNTBASE,">>f:\\perl\\a.csv")||die("can not open the file!");
printf COUNTBASE  "@category[$number]   @information[0]     @information[1]    @information[3]  @information[4]  @information[5]  H\n";
}
elsif(@information[9]=~/^1\/1/)
{
open(COUNTBASE,">>f:\\perl\\a.csv")||die("can not open the file!");
printf COUNTBASE  "@category[$number]   @information[0]     @information[1]    @information[3]  @information[4]  @information[5]  Y\n";
}
}
}
}