由于WT样品有几个重复,而每个重复都单独算出基因的TPM值,现在需要将几个重复根据geneID进行合并,以便后续求每个基因TPM的平均值。
具体perl代码如下:
open FA,"$ARGV[0]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
$hash{$temp[0]}=[$temp[3]];
}
open FA,"$ARGV[1]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
if(exists $hash{$temp[0]}){
push @{$hash{$temp[0]}},$temp[3];
$hash{$temp[0]}=$hash{$temp[0]};
}
}
open FA,"$ARGV[2]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
if(exists $hash{$temp[0]}){
push @{$hash{$temp[0]}},$temp[3];
$hash{$temp[0]}=$hash{$temp[0]};
}
}
open FA,"$ARGV[3]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
if(exists $hash{$temp[0]}){
push @{$hash{$temp[0]}},$temp[3];
$hash{$temp[0]}=$hash{$temp[0]};
}
}
open FA,"$ARGV[4]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
if(exists $hash{$temp[0]}){
push @{$hash{$temp[0]}},$temp[3];
$hash{$temp[0]}=$hash{$temp[0]};
}
}
open FA,"$ARGV[5]";
while(<FA>){
chomp;
@temp=split /\t/,$_;
if(exists $hash{$temp[0]}){
push @{$hash{$temp[0]}},$temp[3];
$hash{$temp[0]}=$hash{$temp[0]};
}
}
foreach(sort keys %hash){
print"$_\t@{$hash{$_}}\n";
}
运行代码:
perl perl_merge.pl WT_rep1.tpm.count WT_rep2.tpm.count WT_rep3.tpm.count WT_rep4.tpm.count WT_rep5.tpm.count WT_rep6.tpm.count|head -20
初步结果如下: