BOL: Owner

Concatenate two given sequences, and find the length of the new sequence and also print out the second codon of the sequence

Nishi Singh — Thu, 03 Sep 2020 06:47:43 -0500

#!/usr/bin/perl
use strict;
use warnings;

#assign strings to variables
my $DNA = "GATTACACAT";
my $polyA = "AAAA";

#concatenate two strings
my $modifiedDNA = $DNA.$polyA;

#calculate the length of $modifiedDNA and
#print out the value of the variable and its length
my $DNAlength = length($modifiedDNA);
print "Modified DNA: $modifiedDNA has length $DNAlength\n";

#extract the second codon in $modifiedDNA
my $codon = substr($modifiedDNA,3,3);
print "Second codon is $codon\n";

Parse a genbank file using regular expressions

Nishi Singh — Tue, 10 May 2016 11:56:26 -0500

#! /usr/local/bin/perl -w

$genbank = "genbank_file.txt";

open (GENBANK, $genbank) || die "cannot open $gb_report for reading: $!";

# Flag for multiline translation; 1 means translation "in progress"  
$trans = 0;

while ()
{
   if (/(LOCUS\s*)(\w*)(.*)/) { 
       print "Locus: $2\n"; 
   }
   elsif (/(VERSION.*GI:)(\d*)/) { 
      print "GI: $2\n"; 
   }
   elsif (/(DEFINITION\s*)(.*)(\.)/) {
      print "Sequence name: $2\n";
   }
   elsif (/(ORGANISM\s*)(.*)/) {
      print "Organism: $2\n";
   }
   elsif(/(gene)(\s*)(\d*)(\.\.)(\d*)/) {
      print "Gene length: $5\n";
   }
   elsif (/(CDS\s*)(\d*)(\.\.)(\d*)/)  {
   # ex: CDS             357..1541
      $cds_start = $2;
      $cds_end = $4;
      print "CDS: $cds_start - $cds_end\n";
   }
   elsif (/(\/translation=")(.*)/)  {  # protein product begins
      print "Translation: ";
      $protein = $2;
      $trans = 1;
   }
   elsif ($trans)  {   # translation still going on
      if (!/"/)  {  # no terminal quote; translation continues
         $protein .= $_;
      }
      elsif (/(.*)(")/)  {  # terminal quote; end of translation
         $protein .= $1;
         $protein =~ s/\s*//g;
         print "$protein\n";
         $trans = 0;
      }
      else  {
         print "Problems: end of translation product not found.\n";
      }
   }
   else  {
      # Skip this data
   }
}

Check if your coputer ready to use BioPerl

Nishi Singh — Tue, 10 May 2016 11:48:50 -0500

#!/usr/bin/perl
use strict;
use warnings;

#bioperl example code
use strict;
use warnings;

#make the bioperl module (class) accessible to your program
use Bio::Seq;

print"ok - ready to use Bio::Seq";

Read lines from input file – print lines that match a regular expression

Nishi Singh — Tue, 10 May 2016 11:46:19 -0500

#!/usr/bin/perl
use strict;
use warnings;

my $line;

#read the line-by-line for each line ask if it matches the regex print it if it matches

while($line = ){
        chomp $line;
        if ($line =~ /^ATG?C*[ATCG]+?A{3,10}$/) {
                print "$line\n";
        }
}

exit();

__DATA__
ATGCCCAA
ATGCCCAAAA
ATGCCCAAAAAAAAAAAAAAAAA
AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD

For a given DNA sequence find its RNA transcript, find its reverse complement and check if the reverse complement contains a start codon

Nishi Singh — Tue, 10 May 2016 11:42:30 -0500

#!/usr/bin/perl
use strict;
use warnings;

my $DNA = "GATTACACAT";

#transcribe DNA to RNA - T changes to U
my $RNA = $DNA;
$RNA =~ s/T/U/g;
print "RNA sequence is $RNA\n";

#find the reverse complement of $DNA using substitution operator
#first - reverse the sequence
my $rcDNA = reverse($DNA);

$rcDNA =~ s/T/A/g;
$rcDNA =~ s/A/T/g;
$rcDNA =~ s/G/C/g;
$rcDNA =~ s/C/G/g;

print "Reverse complement of $DNA is $rcDNA\n"; #did it work?

#find the reverse complement of $DNA using translation operator
#first - reverse the sequence
$rcDNA = reverse($DNA);
#then - complement the sequence
$rcDNA =~ tr/ACGT/TGCA/;
#then - print the reverse complement
print "Reverse complement of $DNA is $rcDNA\n";

#look for a start codon in the reverse sequence
if($rcDNA =~ /ATG/){
	print "Start codon found\n";
}
else{
	print "Start codon not found\n";
}

Count the frequency of base G in a given DNA sequence

Nishi Singh — Tue, 10 May 2016 11:38:32 -0500

#!/usr/bin/perl
use strict;
use warnings;

my $DNA = "GATTACACAT";

#initialize $countG and $currentPos
my $countG = 0;
my $currentPos = 0;

#calculate the length of $DNA
my $DNAlength = length($DNA);

#for each letter in the sequence check if it is the base G
#if 'yes' increment $countG
while($currentPos < $DNAlength){
	my $base = substr($DNA,$currentPos,1);
	if($base eq "G"){
		$countG++;
	}
	$currentPos++;
} #end of while loop

#print out the number of Gs
print "There are $countG G bases\n";

Concatenate two given sequences, and find the length of the new sequence and also print out the second codon of the sequence

Nishi Singh — Tue, 10 May 2016 11:36:27 -0500

#!/usr/bin/perl
use strict;
use warnings;

#assign strings to variables
my $DNA = "GATTACACAT";
my $polyA = "AAAA";

#concatenate two strings
my $modifiedDNA = $DNA.$polyA;

#calculate the length of $modifiedDNA and
#print out the value of the variable and its length
my $DNAlength = length($modifiedDNA);
print "Modified DNA: $modifiedDNA has length $DNAlength\n";

#extract the second codon in $modifiedDNA
my $codon = substr($modifiedDNA,3,3);
print "Second codon is $codon\n";