17_11_2015.pl

#!/usr/bin/perl 

use diagnostics;
use strict;
use warnings;
use Getopt::Long;

# Defining bin size and parameters

my $data =  "table.tsv";
my $AAfilterContains = <>;
my $AAfilterTerm = "None";
my $binmax = <>;
my $binmin = <>;
my $binsize = <>;
my @sorted;

handleopts();

sub handleopts {
        if (!GetOptions (
                "bin-max=i" => \$binmax,
                "file=s" => \$data,
                "bin-min=i" => \$binmin,
                "bin-size=i" => \$binsize,
                "aa-filter-contains=s" => \$AAfilterContains,
                "aa-filter-term=s" => \$AAfilterTerm)){
                print STDERR "Error, failed to obtain information from user\n";
                print "Help_page\n";
                exit(0);
        }
}
open(IFILE, $data) or die "Error, could not open input file\n";

my @lines = <IFILE>;
my @MZvalues;
my $AA;
my $line;
my %hash;
foreach my $line (@lines) {
        if ($AAfilterContains =~ /[a-zA-z]/) {
                my $MZvalue = processAA($line);
        } else {
                my $MZvalue = processMZValue($line);
        }
}
sub processMZValue {
        my $line = shift;
 
        next if ($line =~ /^$/);        # this error-proofs the read so that at every loop it will ig$
        my @column = split( /\t|\n/, $line );   # splits the column
        my $mzcol = $column[3];
        if ( $mzcol =~ /(\d+)/ ) {
                my $mzcolmatch = $1;
                # capture m/z value for the current row in table

                print "$mzcolmatch\n" or die "Nope";
                push @MZvalues, $mzcolmatch;

                my $AA = $column[2];
                $hash{$AA}->{"AAnum"}++;
                push @{$hash{$AA}{'mass'}{'mzcol'}}, $mzcolmatch;
                push @{$hash{$AA}{'mass'}{'aa'}}, $AA;
                my $aakey;
#               foreach my $aakey (sort keys %hash) {
                        print scalar($hash{$aakey}{'mass'})
#               }
        }
}
sub processAA {
        my $line = shift;
        chomp($AAfilterContains);
                next if ($line =~ /^$/);
                my @AAcolumn = split( /\t|\n/, $line );
                my $AAfilcolumn = $AAcolumn[2];
                if ( $AAfilcolumn =~ /$AAfilterContains/) {
                        my $AAmatch = $1;
                        print "Here's one\n";
                }
}



exit;

17_11_2015_v02.pl

#!/usr/bin/perl 

package ProNTo::IonStats;

use diagnostics;
use strict;
use warnings;
use Getopt::Long;


our @ISA = qw(Exporter);

# Defining bin size and parameters

our @EXPORT_OK = qw();

my $data =  "table.tsv";
my $AAfilterContains = <>;
my $AAfilterTerm = "None";
my $binmax = <>;
my $binmin = <>;
my $binsize = <>;
my @sortedmzvals;
my $usage;

handleopts();

sub handleopts {
        if (!GetOptions (
                "bin-max=i" => \$binmax,
                "file=s" => \$data,
                "bin-min=i" => \$binmin,
                "bin-size=i" => \$binsize,
                "aa-filter-contains=s" => \$AAfilterContains,
                "aa-filter-term=s" => \$AAfilterTerm)){
                print STDERR "Error, failed to obtain information from user\n";
                print "Help_page\n";
                exit(0);
        }
}
open(IFILE, $data) or die "Error, could not open input file\n";

my @lines = <IFILE>;
my @MZvalues;
my %MZaavalues;
my $AA;
my $line;
my @array;
foreach my $line (@lines) {
        if ($AAfilterContains =~ /[a-zA-z]/) {
                my $MZvalue = processAA($line);
        } else {
                my $MZvalue = processMZValue($line);
        }
}
sub processMZValue {
        my $array = shift;
        my $line = shift;
        next if ($line =~ /^$/);        # this error-proofs the read so that at every loop it will ig$
        my @column = split( /\t|\n/, $line );   # splits the column
        my $mzcol = $column[3];
        for ( my $i = 0; $i < @lines; $i++) {$MZvalues[$array-1][$i] = $array[$i];}

#       if ( $mzcol =~ /(\d+)/ ) {
#               my $mzcolmatch = $1;
                # capture m/z value for the current row in table

#                print "$mzcolmatch\n" or die "Nope";
#                push @MZvalues, $mzcolmatch;
#       }
}
sub processAA {
        my $line = shift;
                chomp($AAfilterContains);
                next if ($line =~ /^$/);
                my @AAcolumn = split( /\t|\n/, $line );
                my $AAfilcolumn = $AAcolumn[2];
                if ( $AAfilcolumn =~ /$AAfilterContains/) {
                        my $mz = $AAcolumn[3];
                        my $AAmatch = $1;
                        $MZaavalues{$AAfilcolumn}->{"AA"}++;
                        push @{$MZaavalues{$AAfilcolumn}}, $mz;
                        print "Here's one\n";
                }
}

exit;

new_ion_stats.pl

#!/usr/bin/perl 

use diagnostics;
use strict;
use warnings;
use Getopt::Long;

# Defining bin size and parameters

my $data =  "table.tsv";
my $AAfilterContains = <>;
my $AAfilterTerm = "None";
my $binmax = <>;
my $binmin = <>;
my $binsize = <>;
my @sorted;

handleopts();

sub handleopts {
        if (!GetOptions (
                "bin-width=i" => \$binmax,
                "file=s" => \$data,
                "bin-value=i" => \$binmin,
                "bin-size=i" => \$binsize,
                "aa-filter-contains=s" => \$AAfilterContains,
                "aa-filter-term=s" => \$AAfilterTerm)){
                print STDERR "Error, failed to obtain information from user\n";
                print "Help_page\n";
                exit(0);
        }
}
open(IFILE, $data) or die "Error, could not open input file\n";

my @lines = <IFILE>;
my @MZvalues;
my $AA;
my $line;
foreach my $line (@lines) {
        if ($AAfilterContains =~ /[a-zA-z]/) {
                my $MZvalue = processAA($line);
        } else {
                my $MZvalue = processMZValue($line);
        }
}
sub processMZValue {
        my $line = shift;
        next if ($line =~ /^$/);        # this error-proofs the read so that at every loop it will ig$
        my @column = split( /\t|\n/, $line );   # splits the column
        my $mzcol = $column[3];
        if ( $mzcol =~ /(\d+)/ ) {
                my $mzcolmatch = $1;
                # capture m/z value for the current row in table

                print "$mzcolmatch\n" or die "Nope";
                push @MZvalues, $mzcolmatch;
        }
}
sub processAA {
        my $line = shift;
        chomp($AAfilterContains);
                next if ($line =~ /^$/);
                my @AAcolumn = split( /\t|\n/, $line );
                my $AAfilcolumn = $AAcolumn[2];
                if ( $AAfilcolumn =~ /$AAfilterContains/) {
                        my $AAmatch = $1;
                        print "Here's one\n";
                }
}
exit;

old_ion_stats.pl

#!/usr/bin/perl 

use diagnostics;
use strict;
use warnings;
use Getopt::Long;

# Defining bin size and parameters

my $data =  "table.tsv";
my $AAfilterContains = <>;
my $AAfilterTerm = "None";
my $binmax = <>;
my $binmin = <>;
my $binsize = <>;
my @sorted;

handleopts();

sub handleopts {
        if (!GetOptions (
                "bin-width=i" => \$binmax,
                "file=s" => \$data,
                "bin-value=i" => \$binmin,
                "bin-size=i" => \$binsize,
                "aa-filter-contains=s" => \$AAfilterContains,
                "aa-filter-term=s" => \$AAfilterTerm)){
                print STDERR "Error, failed to obtain information from user\n";
                print "Help_page\n";
                exit(0);
        }
}

open(IFILE, $data) or die "Error, could not open input file\n";

# READING THE DATA

my @lines = <IFILE>;
my @MZvalues;
my $AA = shift;
my $AAfilcolumn;
if ($AAfilterContains =~ /[a-zA-z]/) {
                chomp($AAfilterContains);
                foreach my $AA (@lines) {
                        next if ($AA =~ /^$/);
                        my @AAcolumn = split( /\t|\n/, $AA );
                        my $AAfilcolumn = $AAcolumn[2];
                        if ( $AAfilcolumn =~ /$AAfilterContains/) {
                                my $AAmatch = $1;
                                print "Here's one\n";
                        }
                }
} else {
        foreach my $line (@lines) {
                my $MZvalue = processMzValue($line, $AAfilterTerm);
        }
}
sub processMzValue {
        # take the first parameter to the subroutine as a scalar variable, called line
        my $line = shift;
        if ($AAfilterTerm ne "None") {

                # Specify the terminus and residues in the format:
                #       --aa-filter-term N:RKH
                # to indicate N-terminal R, K, or H residues
                # or
                #       --aa-filter-term C:WQD
                # to indicate C-terminal W, Q, or D residues
                my $terminus =~ /(^.):(.+)/;
                # The above regular expression has 2 match groups:
                #       $1 is the terminus (C or N)
                #       $2 is one or more residues

                processAA($2, $1);
        }

        next if ($line =~ /^$/);        # this error-proofs the read so that at every loop it will ig$
        my @column = split( /\t|\n/, $line );   # splits the column
        my $mzcol = $column[3];
        if ( $mzcol =~ /(\d+)/ ) {
                my $mzcolmatch = $1;
                # capture m/z value for the current row in table

                print "$mzcolmatch\n" or die "Nope";
                push @MZvalues, $mzcolmatch;
        }
}

sub processAA {
        # Filter for amino acid composition/terminal residue to generate stats
}


# Take values in @MZvalues and puts them into bins

@sorted = sort (@MZvalues);
print "\n@sorted\n";

print "\nAll done\n";
exit;