From 80bc80633c9019f0277b58f91f6b69351e1896f6 Mon Sep 17 00:00:00 2001
From: Peter Vlasveld <pvlasveld@mailfence.com>
Date: Sat, 3 Nov 2018 10:22:22 -0400
Subject: [PATCH] first commit

---
 BINS.pl | 54 ++++++++++++++++++++++++++++++++++++++++++++++
 FIB.pl  | 31 +++++++++++++++++++++++++++
 GC.pl   | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 GRPH.pl | 49 ++++++++++++++++++++++++++++++++++++++++++
 IPRB.pl | 37 ++++++++++++++++++++++++++++++++
 REVC.pl | 41 +++++++++++++++++++++++++++++++++++
 6 files changed, 278 insertions(+)
 create mode 100644 BINS.pl
 create mode 100644 FIB.pl
 create mode 100644 GC.pl
 create mode 100644 GRPH.pl
 create mode 100644 IPRB.pl
 create mode 100644 REVC.pl

diff --git a/BINS.pl b/BINS.pl
new file mode 100644
index 0000000..d1e21ba
--- /dev/null
+++ b/BINS.pl
@@ -0,0 +1,54 @@
+=pod
+Binary search program for solving Rosalind BINS problem
+Author: Peter Vlasveld
+=cut
+#!/usr/bin/perl
+use strict;
+use warnings;
+
+#take in data
+open(IN, "rosalind_bins.txt") or die "Couldn't open the input file";
+my @data = <IN>;
+close IN;
+
+#declare and fill data arrays
+my @list = split / /, $data[2];
+my @keys = split / /, $data[3];
+
+#declare arrays
+my (@outArr, @test);
+
+#run binary searches and store in @outArr
+for (@keys){
+	my $result = binSearch($_,\@list,0,$#list);
+	push(@outArr, $result);
+}
+
+#join search results into one string
+my $outStr = join(' ', @outArr);
+
+#open file and print output to it
+open(OUT, ">outlog.txt") or die "Couldn't open the output file";
+print OUT $outStr;
+close OUT;
+
+#also print the output to the console
+print $outStr, "\n";
+
+#binary search algorithm
+sub binSearch{
+	my ($key, $list_ref, $left, $right) = @_;
+
+	if ($left > $right) { return -1; }
+	
+	my $middle = int(($left + $right) / 2);
+	print "$middle\n";
+	my @array = @{$list_ref};
+	
+	if ($array[$middle] == $key) { return int($middle)+1; }
+	elsif ($array[$middle] > $key) {
+		return binSearch($key, $list_ref, int($left), int($middle-1));
+	}else{
+		return binSearch($key, $list_ref, int($middle+1), int($right));
+	}
+}
diff --git a/FIB.pl b/FIB.pl
new file mode 100644
index 0000000..38a7b29
--- /dev/null
+++ b/FIB.pl
@@ -0,0 +1,31 @@
+=pod
+Solution to the FIB Rosalind problem - a modified fibonacci algorithm
+Author: Peter Vlasveld
+=cut
+
+#!/usr/bin/perl
+use strict;
+use warnings;
+
+#take in data from file
+open(IN, "rosalind_fib.txt") or die "Couldn't open input file";
+my $data = <IN>;
+close IN;
+
+#splitinput values into array
+my @input = split / /, $data;
+
+#print output of fibonacci algorithm to console
+print fibo($input[0],$input[1]), "\n";
+
+#modified fibonacci algorithm to allow for k rabbit pairs per month rather than just 1
+sub fibo{
+	my ($num,$pairs) = @_;
+	if ($num == 0) { return 0; }
+	if ($num == 1) { return 1; }
+	my $result = fibo($num-1,$pairs);
+	
+	$result += (fibo($num-2,$pairs))*$pairs;
+	
+	return $result;
+}
diff --git a/GC.pl b/GC.pl
new file mode 100644
index 0000000..3464750
--- /dev/null
+++ b/GC.pl
@@ -0,0 +1,66 @@
+=pod
+Solution to GC Rosalind problem
+Author: Peter Vlasveld
+=cut
+
+#!/usr/bin/perl
+use strict;
+use warnings;
+
+#take in data from file
+open(IN, "rosalind_gc.txt") or die "Couldn't open input file";
+my @data = <IN>;
+close IN;
+
+#declare variables
+my @ID;
+my @sequences;
+my @tempArr;
+my $finalID;
+my $finalPerc = 0;
+
+#add first @data line to @ID
+$ID[0] = $data[0];
+
+#loop through 1..$#data
+for (1..$#data){
+	#when a line starts with >, 
+	if (substr($data[$_],0,1) eq '>'){
+		#add it to @ID, join the temp array and add it to @sequences
+		push @ID, $data[$_];
+		my $temp = join ('', @tempArr);
+		push @sequences, $temp;
+		@tempArr = undef;
+	} else {
+		#add line to temp array
+		push @tempArr, $data[$_];
+	}
+}
+
+#join last temp and add to sequences
+my $temp = join('', @tempArr);
+push @sequences, $temp;
+
+#loop through @sequences
+for (0..$#sequences){
+	$sequences[$_] =~ s/\s//g;
+	print $sequences[$_];
+	#declare percentage
+	my $percentage;
+	my $GC;
+	my $total = length $sequences[$_];
+	#determine percentage of GC in the sequence
+	$GC = ($sequences[$_] =~ tr/GC//);
+	$percentage = ($GC/$total)*100;
+	print "$percentage\n";
+	#if percentage is greater than finalPerc, then finalPerc eq percentage and finalID eq ID
+	if ($percentage>$finalPerc) {
+		$finalPerc = $percentage;
+		$finalID = $ID[$_];
+	}
+}
+
+#output id and percent
+printf("%s%f\n", $finalID, $finalPerc);
+
+
diff --git a/GRPH.pl b/GRPH.pl
new file mode 100644
index 0000000..525981a
--- /dev/null
+++ b/GRPH.pl
@@ -0,0 +1,49 @@
+=pod
+Solutions to GRPH Rosalind problem
+Author: Peter Vlasveld
+=cut
+
+#!/usr/bin/perl
+use common::sense;
+
+#take in data
+open(IN, "rosalind_grph.txt") or die "Couldn't open input file";
+my @data = <IN>;
+close IN;
+
+#declare variables
+my (@headers, @DNA, @result);
+my $temp = "";
+
+#convert FASTA data into array of DNA strings and headers
+for (@data){
+	unless (substr($_,0,1) eq '>'){
+		$temp .= substr($_,0,-1);	
+	} else {
+		push @headers, substr($_,0,-1);
+		push @DNA, $temp;
+		$temp = "";
+	}
+}
+push @DNA, $temp;
+shift @DNA;
+#print @headers,"\n",@DNA,"\n";
+
+#write which headers overlap to @result
+for my $i (0..$#DNA){
+	for my $j (0..$#DNA){
+		print "$DNA[$i]$DNA[$j]\n";
+		if ($DNA[$i] eq $DNA[$j]) { next; }
+		elsif (substr($DNA[$i],-3) eq substr($DNA[$j],0,3)){
+			push @result, substr($headers[$i],1)." ".substr($headers[$j],1);
+		}
+	}
+}
+
+#print result to file
+open(OUT, ">output.txt") or die "Couldn't open output file";
+for (@result){
+	print OUT $_,"\n";
+}
+close OUT;
+	
diff --git a/IPRB.pl b/IPRB.pl
new file mode 100644
index 0000000..f96c52b
--- /dev/null
+++ b/IPRB.pl
@@ -0,0 +1,37 @@
+=pod
+Solution to IPRB Rosalind problem
+Author: Peter Vlasveld
+=cut
+
+#!/usr/bin/perl
+use strict;
+use warnings;
+
+#take in data from file
+open(IN, "rosalind_iprb.txt") or die "Couldn't open input file";
+my $data = <IN>;
+close IN;
+
+#split dataset into array
+my @dataset = split / /, $data;
+
+#calculate total probability ratios
+my $total = $dataset[0] + $dataset[1] + $dataset[2];
+my $initmRatio = $dataset[1]/$total;
+my $initnRatio = $dataset[2]/$total;
+
+#calculate values of progeny from probability ratios and population data 
+my $sameHeteroDom = ($initmRatio * (($dataset[1]-1)/($total-1)))*0.25;
+#print $sameHeteroDom, "\n";
+my $oneAndOne1 = ($initmRatio * ($dataset[2]/($total-1)))*0.5;
+#print $oneAndOne1, "\n";
+my $oneAndOne2 = ($initnRatio * ($dataset[1]/($total-1)))*0.5;
+#print $oneAndOne2, "\n";
+my $sameHeteroRec = $initnRatio * (($dataset[2]-1)/($total-1));
+#print $sameHeteroRec, "\n";
+
+#calculate resulting progeny
+my $result = 1-($sameHeteroDom + $oneAndOne1 + $oneAndOne2 + $sameHeteroRec);
+
+#output result to console
+printf("%.5f\n", $result);
diff --git a/REVC.pl b/REVC.pl
new file mode 100644
index 0000000..ee78d46
--- /dev/null
+++ b/REVC.pl
@@ -0,0 +1,41 @@
+=pod
+Solution to the Rosalind REVC problem
+Author: Peter Vlasveld
+=cut
+
+#!/usr/bin/perl
+use strict;
+use warnings;
+use Switch;
+
+#take in dataset
+open(IN, "rosalind_revc.txt") or die "Couldn't open input file";
+my $dataset = <IN>;
+close IN;
+
+#split data into single letters
+my @dna = split //, $dataset;
+
+#declare complement array
+my @complement;
+
+#make complement array which corresponds to @dna array
+for (@dna){
+	switch($_){
+		case 'A' { push @complement, 'T'; }
+		case 'T' { push @complement, 'A'; }
+		case 'G' { push @complement, 'C'; }
+		case 'C' { push @complement, 'G'; }
+	}
+}
+
+#reverse the complement
+@complement = reverse @complement;
+
+#join back into a single string and output to a file
+my $result = join '', @complement;
+open(OUT, ">outlog.txt") or die "couldn't open output file";
+print OUT $result;
+
+#print solution to console
+print "$result\n";