Pseudo - code
################################ # open DNA sequence file ################################
print "Enter in the name of the DNA sequence file:\n";
chomp (my $dna_seq = <STDIN>);
open(DNA_SEQ, $dna_seq)
or die "Can't open sequence file for input: $!";########################################################
# read sequence data into a hash - not sure if this is how I should do it?
########################################################
my %sequences;
$/ = '>'; # set to read in paragraph mode
print "\n***Discovered the following DNA sequences:***\n";
while ( <DNA_SEQ> ) {
chomp;
next unless s/^\s*(.+)//;
my $name = $1;
s/\s//g;
$sequences{$name} = $_;
print "$name found!\n";
}
close DNA_SEQ;
################################### # search for and characterize gaps ###################################
<<somehow get data from hash and present it to a loop>>
%gaptype;
<<major pseudo code below>>
foreach /\D(-+)\D/ found in each sequece # searches for gaps flanked by sequence
$position = pos($1);
$gaplength = $1;
$gaplength =~ tr/-//g; # count the number of '-' for that particular
# gap being processed
$gaptype{gaplength}++; # count the number of times each gap type appears
<<somehow get information from loop an print as seen below>>
____OUTPUT_____
Human
number of 3 base pair gaps: 2
at positions: 6, 16
number of 5 base pair gaps: 1
at positions: 25
.
.. and so on...
.
__DATA__ human acgtt---cgatacg---acgact-----t chimp acgtacgatac---actgca---ac mouse acgata---acgatcg----acgt
-- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] <http://learn.perl.org/> <http://learn.perl.org/first-response>
