请问用Linux或Perl如何从蛋白质序列文件中取出存储在另一个文件中的10个蛋白质ID的Fasta格式序列

Posted 2023-05-07

参考技术A #!/usr/bin/perl -w

use strict;
#contact perlcoder weixin
my %hash;
while(<DATA>)

    if($_=~/\\S+/)
    
        
    
    else
    
       next;    
    
    chomp;
    my ($key)=$_=~/>(\\S+)/;
    my $value=<DATA>;
    chomp($value);
    $hash$key=$value;    


print $hash'Gh_A04G0739',"\\n";


__DATA__
>Gh_A12G2559              
ATGGCTACTTTCTTTGGCTATTTTAC
>Gh_A12G2554              
ATGGCGGGAACTATCCAATCCCTAAT
>Gh_A04G0755              
ATGGCCTCCGATCAGACCCTTTTTCA
>Gh_A04G0739              
ATGGAGAAAGCAAAACCTGAAGCACC
>Gh_A04G0738              
ATGGCGCAGGTTTTAGACGACGCTGA
>Gh_A07G1346              
ATGGTTCATTGTCTGCCAAAGGTTTC
>Gh_A07G1331              
ATGGCAGACAAGGATTCTTCAAGGCC
>Gh_A07G1334              
ATGACGACGCCAACTCGAGATGCAAT
>Gh_A07G1335              
ATGGCCGCAACTAGATTCCTCTCTCA
>Gh_A08G1510              
ATGGCTACTGCACCGATAAAGTCTCA
>Gh_A08G1433              
ATGGGTAAAACACCTACTGGCAAGGA

来自：求助得到的回答 参考技术A 最好输入输出都有样例，贴出来。

否则无法给出答复

perl 和python 翻译序列

把人的P53的cDNA序列转录为RNA，再翻译为蛋白质；

perl

use strict;open IN,"c:/Users/11852/Desktop/human_TP53_cDNA.fasta";my $cdna;
while (my $line=<IN>){ chomp $line; if ($line=~ ">"){ next; } $cdna.=$line; }print "the length of cdna\t".length($cdna)."\n".$cdna."\n";
$cdna=~ tr/T/U/;close IN;
open IN,"c:/Users/11852/Desktop/codon_table.txt";my %codon_dic;while (my$line =<IN>){ chomp $line; my @li=split(/\t/,$line); my$codon=$li[0]; $codon=~tr/T/U/; $codon_dic{$codon}=$li[1];}my $protein;for (my$i=0;$i<length($cdna);$i+=3){ my$j=substr($cdna,$i,3); my$a= $codon_dic{$j}; if ($a eq "Stop"){ next; } $protein .= $a;}print $protein;

python

fin=open("data/human_TP53_cDNA.fasta")tp53_cdna=""tp53_mrna=""tp53_protein=""for line in fin: if line[0]==">": continue tp53_cdna+=line.strip()print("TP53 cDNA sequence (Length: ", len(tp53_cdna), "): ",  tp53_cdna, sep="") tp53_mrna=tp53_cnda.replace("T","U")print("TP53 mRNA sequence (Length: ", len(tp53_mrna), "): ",  tp53_mrna, sep="")codon_dic={}f_codon=open("data/codon_table.txt","rt")for line in f_codon: sp=line.strip().split("\t") codon=sp[0].replace("T","U") aa=sp[1] codon_dic[codon]=aafor i in range(0,len(tp53_mrna),3): aa=codon_dic[tp53_mrna[i:i+3]] if aa=="Stop": break tp53_protein+=aaprint("TP53 protein sequence (Length: ", len( tp53_protein), "): ", tp53_protein, sep="")fin.close()f_codon.close()