Shell Programming and Scripting

Reference:
1)T
2)A
3)C
4)G
5)C

#!/usr/bin/perl


use strict;
use warnings;

my ($idx, $chr, $geno, $mutation);
my @ref = ('T', 'A', 'C', 'G', 'C');
open(FILE,"<","file.txt") or die $!;
while (<FILE>) {
        next unless $_ !~ /Index/;
        next unless $_ =~ /^(\d*)\s*([a-z]*\d)\s*([a-z]*)\s*([a-z]*)/i;
        $idx = $1 - 1;
        $geno = $3;
        next unless $geno !~ /$ref[$idx]/;
        print $_;
}

> ./test.pl   
3           Chr1           AG            Exonic
4           Chr1           CC            Frameshift

 
File #1
Column 1     ....        Column 6     .....   Column 88
(Index)                   (mutation)            (Genotype)
1                             Intronic                 TT
2                             Frameshift             GT
3                             Exonic                   AT
4                             Exonic                   AA
5                             Intronic                 GC
 
File #2
Column 1      Column 2
(index)          (reference letter)
1                      A
2                      C
3                      C
4                      A
5                      G

 
4 Exonic 
5 Intronic

Column 1     ....        Column 6     .....   Column 88
(Index)                   (mutation)            (Genotype)
1                             Intronic                 TT
2                             Frameshift             GT
3                             Exonic                   AT
4                             Exonic                   AA
5                             Intronic                 GC

Column 1      Column 2
(index)          (reference letter)
1                      A
2                      C
3                      C
4                      A
5                      G

#!/usr/bin/perl


use strict;
use warnings;
my ($idx, $tmp, $geno, @ref, @data);


# file1.text is the actual data file
# We want to match data lines to reference lines
# So first we place the data lines (not columns) into an array.

open(FILE1,"<","file1.txt") or die $!;
while (<FILE1>) {
        chomp;
        # If the line does not start with a number
        # we skip this line
        next unless $_ =~ /^\d/;
        # split the line into index (idx), and all else is placed in tmp
        ($idx, $tmp) = split(/\s+/,$_,2);
        # Populate the data array with the line minus the index column
        $data[$idx] = $tmp;
}


# file2.txt is the referece file with only 2 columns
# We parse the file and split it into index and value pairs.
# Then we can use the index to match the data index and
# once we have that data we can begin to break it down to
# it's column components and match as needed/
open(FILE2,"<","file2.txt") or die $!;
while (<FILE2>) {
        chomp;
        next unless $_ =~ /^\d/;
        # Split the index and data
        /^(\d*)\s*([a-z]*)/i;
        # Split the data line columns by spaces and 
        # place these columns into a new temp array  
        my @tmparr = split(/\s+/,$data[$1]);
        # Now we can look directly at 1 (or other) column for testing
        # column 1 in my case but column 86 in yours 
        # Column 88 becomes column 86 because we -1 for removed index in first loop above and we -1 for 0 based array
        # My file1.txt had 3 colmns, removing the index leaves 2 columns, and a zero based array means we have column 0 and 1.
        next unless $tmparr[1] !~ /$2/;
        print $1 . "\t" . $data[$1] . "\n";
}

> ./test.pl   
1       Intronic                 TT
2       Frameshift             GT
3       Exonic                   AT

#!/usr/bin/perl


use strict;
use warnings;
my ($idx, $tmp, $geno, @ref, @data);
open(FILE1,"<","file1.txt") or die $!;
while (<FILE1>) {
        chomp;
        next unless $_ =~ /^\d/;
        ($idx, $tmp) = split(/\s+/,$_,2);
        $data[$idx] = $tmp;
}
open(FILE2,"<","file2.txt") or die $!;
while (<FILE2>) {
        chomp;
        next unless $_ =~ /^\d/;
        /^(\d*)\s*([a-z]*)/i;
        my @tmparr = split(/\s+/,$data[$1]);
        next unless $tmparr[1] !~ /$2/;
        print $1 . "\t" . $data[$1] . "\n";
}

next unless $tmparr[1] !~ /$2/;

next unless $tmparr[1] =~ /$2/;

#!/usr/bin/perl

use strict;
use warnings;
my ($idx, $tmp, @data);
open(FILE1,"<","file3.txt") or die $!;
while (<FILE1>) {
        chomp;
        next unless $_ =~ /^\d/;
        ($idx, $tmp) = split(/\s+/,$_,2);
        $data[$idx] = $tmp;
}
close FILE1;

open(FILE2,"<","file2.txt") or die $!;
while (<FILE2>) {
        chomp;
        next unless $_ =~ /^\d/;
        /^(\d*)\s*([a-z]*)/i;
        my @tmparr = split(/\s+/,$data[$1]);
        next unless $tmparr[86] !~ /$2/;
        print $1 . "\t" . $tmparr[4] . "\t" . $tmparr[86] . "\n";
}
close FILE2;