bash-2.05$ perl extract_seqs.pl
main::check_gene() called too early to check prototype at extract_seqs.pl line 22.
main::check_gene_seq() called too early to check prototype at extract_seqs.pl line 27.
main::extractseq() called too early to check prototype at extract_seqs.pl line 32.
syntax error at extract_seqs.pl line 106, near "$endpos) "
Execution of extract_seqs.pl aborted due to compilation errors.
bash-2.05$


##</code><code>##




while (<INPUT>){

    if ($_ =~ /\s{3}\<gene\sid\s\=\s\"(\d{1,6})\"\slabel\s\=\s\"([.|\.]{1,40})\"\>/){
 check_gene ($_);
    }
    
    if ($_ =~ /\s{4}\<gene_seq\sid\s\=\s\"(\d{0,6})\"\sstatus\s{0,2}\=\s{0,2}\"(.{0,50})\"\s{0,2}CDS_number\s{0,2}\=\s{0,2}\"(\d{1,3})\"\s{0,2}number_of_CDSs\s{0,2}\=\s{0,2}\"(\d{0,5})\"\s{0,2}sequence_source\s{0,2}\=\s{0,2}\"(.{0,300})\"\s{0,2}startpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}endpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}startopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\sendopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\s{0,2}complement\s{0,2}\=\s{0,2}\"(.{0,1})\"\>/){
 
 check_gene_seq ($_);
 
 $label = "$gene_seq_id.$gene_seq_status.$gene_seq_CDS_number.$gene_seq_number_of_CDSs.$gene_seq_sequence_source.$gene_seq_startpos.$gene_seq_endpos.$gene_seq_startopen.$gene_seq_endopen.$gene_seq_complement"; 
    }
    
    extractseq ($label,$gene_seq_sequence_source,$gene_seq_startpos,$gene_seq_endpos); 
}    



##</code><code>##


#!/usr/bin/perl -w


#########
### Programed 15_12_02_by Matthew Redden
#########


#use strict;

    
mkdir Output;

$input = "new_out_again_12_12_02_B_hand_edit_15_12_02.txt";

open (INPUT, "<$input");


while (<INPUT>){

    if ($_ =~ /\s{3}\<gene\sid\s\=\s\"(\d{1,6})\"\slabel\s\=\s\"([.|\.]{1,40})\"\>/){
 check_gene ($_);
    }
    
    if ($_ =~ /\s{4}\<gene_seq\sid\s\=\s\"(\d{0,6})\"\sstatus\s{0,2}\=\s{0,2}\"(.{0,50})\"\s{0,2}CDS_number\s{0,2}\=\s{0,2}\"(\d{1,3})\"\s{0,2}number_of_CDSs\s{0,2}\=\s{0,2}\"(\d{0,5})\"\s{0,2}sequence_source\s{0,2}\=\s{0,2}\"(.{0,300})\"\s{0,2}startpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}endpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}startopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\sendopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\s{0,2}complement\s{0,2}\=\s{0,2}\"(.{0,1})\"\>/){
 
 check_gene_seq ($_);
 
 $label = "$gene_seq_id.$gene_seq_status.$gene_seq_CDS_number.$gene_seq_number_of_CDSs.$gene_seq_sequence_source.$gene_seq_startpos.$gene_seq_endpos.$gene_seq_startopen.$gene_seq_endopen.$gene_seq_complement"; 
    }
    
    extractseq ($label,$gene_seq_sequence_source,$gene_seq_startpos,$gene_seq_endpos); 
}    



sub check_gene($) {
    
#   <gene id = "242" label = "SPCC576.16">
    
    my $line = $_;
    
    if ($line =~ /\s{3}\<gene\sid\s\=\s\"(\d{1,6})\"\slabel\s\=\s\"([.|\.]{1,40})\"\>/){
 
  $gene_id = $1;
  $gene_label = $2;
 
    }
    else {
 print "ERROR.  Somebody has altered the regular expression";
    }
    
    return $gene_id;
    return $gene_label;
}





sub check_gene_seq($){
    
#    <gene_seq id = "311" status = "Sanger source DNA code" CDS_number = "3" number_of_CDSs = "" sequence_source = "" startpos = "2110545" endpos = "2110823" startopen = "1" endopen = "1" complement = "C"/>
    
    if ($_ =~ /\s{4}\<gene_seq\sid\s\=\s\"(\d{0,6})\"\sstatus\s{0,2}\=\s{0,2}\"(.{0,50})\"\s{0,2}CDS_number\s{0,2}\=\s{0,2}\"(\d{1,3})\"\s{0,2}number_of_CDSs\s{0,2}\=\s{0,2}\"(\d{0,5})\"\s{0,2}sequence_source\s{0,2}\=\s{0,2}\"(.{0,300})\"\s{0,2}startpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}endpos\s{0,2}\=\s{0,2}\"(\d{0,9})\"\s{0,2}startopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\sendopen\s{0,2}\=\s{0,2}\"(\d{0,1})\"\s{0,2}complement\s{0,2}\=\s{0,2}\"(.{0,1})\"\>/){

 my $gene_seq_id = $1;
 my $gene_seq_status = $2;
 my $gene_seq_CDS_number = $3;
 my $gene_seq_number_of_CDSs = $4;
 my $gene_seq_sequence_source = $5;
 my $gene_seq_startpos = $6;
 my $gene_seq_endpos = $7;
 my $gene_seq_startopen = $8;
 my $gene_seq_endopen = $9;
 my $gene_seq_complement = $10; 
    }
    else {
 print "Error.  Someone has altered the reguar expression";
    }
    
    return $gene_seq_id;
    return $gene_seq_status;
    return $gene_seq_CDS_number;
    return $gene_seq_number_of_CDSs;
    return $gene_seq_sequence_source;
    return $gene_seq_startpoks;
    return $gene_seq_endpos;
    return $gene_seq_startopen;
    return $gene_seq_endopen;
    return $gene_seq_complement;
    
}


sub extractseq($$$$){ # Pass through the FASTA label, the location of sequence, the start pos and the end pos.    
    
    $label = $_[0];
    $gene_seq_sequence_source = $_[1]; 
    $startpos = $_[2];
    $endpos) = $_[3];
    print "$gene_seq_sequence_source\n";
    sleep 1;
 
    print "system ('extractseq $gene_seq_sequence_source extracted_seq_$label.txt -regions \"$startpos..$endpos\"')\;";
    system ("extractseq $gene_seq_sequence_source extracted_seq_$label.txt -regions \"$startpos..$endpos\""); 
}