ivan-krukov

#  blosum62
#  * column uses minimum score
#  BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
#  Blocks Database = /data/blocks_5.0/blocks.dat
#  Cluster Percentage: >= 62
#  Entropy =   0.6979, Expected =  -0.5209
   A  R  N  D  C  Q  E  G  H  I  L  K  M  F  P  S  T  W  Y  V  B  Z  X  *
A  4 -1 -2 -2  0 -1 -1  0 -2 -1 -1 -1 -1 -2 -1  1  0 -3 -2  0 -2 -1  0 -4 
R -1  5  0 -2 -3  1  0 -2  0 -3 -2  2 -1 -3 -2 -1 -1 -3 -2 -3 -1  0 -1 -4 
N -2  0  6  1 -3  0  0  0  1 -3 -3  0 -2 -3 -2  1  0 -4 -2 -3  3  0 -1 -4 

ivan-krukov

^\<\u\l\{-}\> \<\l\{-}\>$

ivan-krukov

tail -n+4 -q results/* | less -S

ivan-krukov

join -a 1 -a2 -e 'NA' -o '0,1.2,2.2' ce hc > join.count

ivan-krukov

#!/usr/bin/env perl
use v5.14;
use warnings;

sub hamming {
  my @a = split "", shift;
	my @b = split "", shift;
	my $distance = 0;
	for (my $n = 0; $n < scalar(@a); $n++) {
		unless (($a[$n]) eq ($b[$n])) {

ivan-krukov

#!/usr/bin/env python
#http://rosalind.info/problems/cons/

import fastaparse

letters = ["A","C","G","T"]

sequences = [i.seq for i in fastaparse.sequences("temp2")]

#create empty profile matrix

ivan-krukov

sudo ntpd -gq
sudo hwclock --systohc --utc 

ivan-krukov

#load everythin in memory

#split
def split_fasta(input_file):
	with open(input_file) as fasta_file:
		text = fasta_file.read().split(">")[1:]
		data = []
		for entry in text:
			header,sequence = entry.split("\n",1)
			sequence = sequence.replace("\n","")

ivan-krukov

def qw(s,t=str):
    return list(map(t,s.split()))

ivan-krukov

#!/usr/bin/env python

import fastaparse
import sys

sequences = [i.seq for i in fastaparse.parse_fasta(sys.argv[1])]

def substrings(string):
	n = len(string)
	for length in range(n,0,-1):