Download the gff files from NCBI using bash script/command
#!/bin/bash # Download the genome from NCBI using command # Create a Directory mkdir genome_gff cd genome_gff # Look for genome assembly summary and extract th...2556 days ago
Extract fasta sequence from a multifasta file with fasta header Ids
#!/usr/bin/perl use strict; use warnings; #Usage: perl my $list = shift @ARGV; my $fasta = shift @ARGV; my $out = shift @ARGV; my %select; open LIST, "...2551 days ago
Compress and decompress the sequence with perl
use strict; use warnings; my @char; while () { @char = split //; } comp(\@char); #--------------------- my $com= "r0a3m4a4j0"; my @com = split //, $com; dcomp (\@com); #dcomp sub here sub dcomp { my ($com_ref)=@_; my @com=@$com_ref; my $car; for (my $aa=0; $aa2548 days ago
2545 days ago
Calculate Dinucleotide Frequency with Perl
#!/usr/bin/perl -w use strict; my ($genome, $head, $tail); my (%mono_nt, %di_nt); $/ = ">"; open my $fasta, '2371 days ago
2502 days ago
Extract the fastq sequence with range in Perl
use Bio::DB::Fasta; open(POSITIONS,"positions.txt"); while(){ chomp; my ($seqName,$begin,$end) = split(/\s/); my $db = Bio::DB::Fasta->new('allGenomeContacted.fa'); my $seq = $db->seq("$seqName", $begin => $end); print "$seq\n"; } close(POSITIONS);2501 days ago
Genetic Algorithms demonstration with word DNA in Perl
#!/usr/bin/perl -w # GA demonstration with word DNA (512 bits) use strict; use Data::Dumper; # individuals in the population my $popsize = 1024; # a good sta...2404 days ago
Extract fasta sequence with Ids with Bash script
#!/bin/bash while IFS='' read -r line || [[ -n "$line" ]]; do echo "Text read from file: $line" samtools faidx ONT.fasta $line > $line.faa done < "$1"2387 days ago
Perl script for calculate Levenshtein distance
sub levenshtein_dist { my ($str1, $str2) = @_; my ($len1, $len2) = (length $str1, length $str2); if ($len1 == 0) { return $len2; } if ($len2 == 0) { return $len1; } my %mat; for (my $i = 0; $i2373 days ago