《grep_cds_pep_from_ncbi_genomes_datas.pl》.pdf

#! /usr/bin/perl -w =head1 ####################################### =head1 name grep_cds_pep_from_ncbi_genomes_datas.pl =head1 description deal with ncbi raw data,and from which get cds ,pep and gene,mRNA and protein ID list. =head1 example perl ref_ConCri1.0_top_level.gff3.gz ccr_ref_ConCri1.0_chrUn.fa.gz mole perl gff_file gemomes_fa_file file_prefix =head1 author original from Xiangfeng Li,xflee@163.com ##2014-4-19/21## =head1 ####################################### =cut use strict; die `pod2text $0` unless @ARGV==3; my ($gff,$fa,$prefix)=@ARGV; ##deal gff file## $gff=~/gz$/ ? (open GFF,gzip -cd $gff|||die):(open GFF,$gff||die); my (%mrna,%cds,%pep); while(GFF){ chomp; next if(/^#/); my @p=split/\t/,$_; my @q=split/;/,$p[8]; my ($rna,$pep,$nt,$gene); my $chr=$p[0]; if($p[2] eq mRNA){ ($rna=$q[0])=~s/ID=//; ($nt=$q[1])=~s/Name=//; ($gene=$q[-3])=~s/gene=//; $mrna{$chr}{$rna}{strand}=$p[6]; $cds{$rna}=[$gene,$nt]; } if($p[2] eq CDS){ ($pep=$q[1])=~s/Name=//; ($rna=$q[2])=~s/Parent=//; push @{$mrna{$chr}{$rna}{nt}},[$p[3],$p[4]]; $pep{$rna}=$pep; } } close GFF; ##get id list## my %anno; open ID, ,$prefix._id_gene_cds_pep.lst||die; foreach my $i(sort keys %pep){ if($cds{$i}){ my $out=join \t,$i,$cds{$i}[0],$cds{$i}[1],$pep{$i}; print ID $out,\n; ($anno{$i}=$out)=~s/\t/\ |/g; } } close ID; ##deal fa file## my %max; $fa=~/gz$/ ? (open FA,gzip -cd $fa|||die):(open FA,$fa||die); my $raw_cds=$prefix._raw_cds; open CDS1,$raw_cds||die; my ($start,$end); $/=;FA;$/=\n; while(FA){ my $name=$1 if(/(\S+)/); my $info=(split/\ |/,$name)[-1]; $/=;