From d66ca4774aad77e947452d9ddb7eb9626027188b Mon Sep 17 00:00:00 2001
From: elserj <elserj@localhost>
Date: Fri, 23 Feb 2024 21:29:56 +0000
Subject: [PATCH] Add fasta split by header script

svn path=/; revision=686
---
 .../fasta_split_by_header_regex.pl            | 41 +++++++++++++++++++
 interactome_scripts/po_obsolete_check.pl      | 18 +-------
 2 files changed, 43 insertions(+), 16 deletions(-)
 create mode 100755 interactome_scripts/fasta_split_by_header_regex.pl

diff --git a/interactome_scripts/fasta_split_by_header_regex.pl b/interactome_scripts/fasta_split_by_header_regex.pl
new file mode 100755
index 0000000..954c2df
--- /dev/null
+++ b/interactome_scripts/fasta_split_by_header_regex.pl
@@ -0,0 +1,41 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+
+if ($#ARGV != 2) {
+    print "usage: fasta_split_by_header_regex.pl input_fasta output_file regex_pattern\n";
+    exit;
+}
+
+my $infile = $ARGV[0];
+my $outfile = $ARGV[1];
+my $regex = $ARGV[2];
+
+my $line_is_header = 0;
+my $header_matches_regex = 0;
+
+open(INFILE, "$infile") or die "Error opening input file!\n";
+
+open(OUTFILE, ">$outfile") or die "Error opening output file!\n";
+
+while(my $line = <INFILE>) {
+    chomp $line;
+
+    if ($line =~ /^>/) {
+        $line_is_header = 1;
+        $header_matches_regex = 0; # reset for new header line
+        if ($line =~ /$regex/) {
+            $header_matches_regex = 1;
+            print OUTFILE "$line\n";
+        }
+    }else{
+        $line_is_header = 0;
+        if ($header_matches_regex) {
+            print OUTFILE "$line\n";
+        }
+    }
+}
+
+close(INFILE);
+close(OUTFILE);
\ No newline at end of file
diff --git a/interactome_scripts/po_obsolete_check.pl b/interactome_scripts/po_obsolete_check.pl
index 666a7dc..50ff5ea 100755
--- a/interactome_scripts/po_obsolete_check.pl
+++ b/interactome_scripts/po_obsolete_check.pl
@@ -60,7 +60,6 @@ foreach my $term (@$obo_terms) {
 	}
 }
 
-my @source_array = ('sgn','tair','gramene','maizegdb','nasc', 'jaiswallab', 'cosmoss', 'AgBase', 'poc');
 
 my %bad_term_hash;
 
@@ -73,27 +72,15 @@ foreach my $file (@assoc_files) {
 	
 	print "checking file: $file\n";
 	
-	my $source_db;
-	foreach my $source (@source_array) {
-		if ($file =~ /$source/i) {
-			$source_db = $source;
-		}
-	}
-	
-	if ($source_db eq "") {
-		print "source not found for file $file\n";
-	}
-	
-	my $output_source_file = "$source_db" . "_obsoletes.txt";
-	open (output_source, ">>$output_source_file");
 	my $line_counter = 0;
 	while(<assoc_file>) {
 		my $line = $_;
 		$line_counter++;
+		# ignore commented lines
+		next if ($line =~ /^!/);
 		foreach my $term (keys %obs_terms_hash) {
 			if ($line =~ $term) {
 				print  output_file "match found!!!\t$file\t$term\tline number:$line_counter\n";
-				print  output_source "$file\t$term\tline:number:$line_counter\n";
 				if(!defined($bad_term_hash{$term})) {
 					$bad_term_hash{$term} = 1;
 				}else{
@@ -105,7 +92,6 @@ foreach my $file (@assoc_files) {
 		}
 	}
 	close (assoc_file);
-	close (output_source);
 }
 close (output_file);
 		
-- 
2.34.1