由于WT樣品有幾個重復,而每個重復都單獨算出基因的TPM值,現(xiàn)在需要將幾個重復根據(jù)geneID進行合并,以便后續(xù)求每個基因TPM的平均值。
具體perl代碼如下:
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";
}
運行代碼:
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
初步結果如下:

image.png