#!/usr/bin/env perl use strict; use warnings; my %special = (PF03797 => 1); { local $/ = "//\n"; while () { my ($id) = /^ID:(\w+)/; my @data; while (/HIT:(\w+).*?SEQ_START:(\d+).*?(\d+)/g) { push @data, [ $1, $2, $3 ]; } @data = sort { $a->[2] <=> $b->[2] } @data; for my $i (0 .. $#data) { if ($special{$data[$i][0]}) { my $start = $i == 0 ? $data[$i][1] : $data[$i - 1][2] + 1; my $end = $i == $#data ? $data[$i][2] : $data[$i + 1][1] - 1; printf "%-41s %7s %4d %4d\n" => $id, $data[$i][0], $start, $end; } } } } __DATA__ ID:A0AWZ5_1___codes_before_only HIT:PF12951 SCORE:40.0 EVALUE:2.2e-10 HMM_START:2 HMM_END:32 SEQ_START:421 SEQ_END:455 HIT:PF03797 SCORE:130.7 EVALUE:3.6e-40 HMM_START:7 HMM_END:261 SEQ_START:822 SEQ_END:1073 HIT:PF12951 SCORE:38.7 EVALUE:5.5e-10 HMM_START:1 HMM_END:32 SEQ_START:515 SEQ_END:547 // ID:A0AWZ5_2___codes_before_and_after HIT:PF12951 SEQ_START:120 SEQ_END:350 HIT:PF03797 SEQ_START:822 SEQ_END:1073 HIT:PF15789 SEQ_START:1515 SEQ_END:1547 HIT:PF00267 SEQ_START:1200 SEQ_END:1350 // ID:A0AWZ5_3___codes_after_only HIT:PF03797 SEQ_START:822 SEQ_END:1073 HIT:PF15789 SEQ_START:1515 SEQ_END:1547 HIT:PF00267 SEQ_START:1200 SEQ_END:1350 // ID:A0AWZ5_4___codes_neither_before_nor_after HIT:PF03797 SEQ_START:822 SEQ_END:1073 // #### A0AWZ5_1___codes_before_only PF03797 548 1073 A0AWZ5_2___codes_before_and_after PF03797 351 1199 A0AWZ5_3___codes_after_only PF03797 822 1199 A0AWZ5_4___codes_neither_before_nor_after PF03797 822 1073