IgorFobia

#!/bin/bash
# Concatenate the sequences of a multi-FASTA file and make a new FASTA file with the new sequence

INPUT_FILE=$1
OUTPUT_FILE=$2

(echo ">concantenated"; grep -i '^[ACGTURYKMSWBDHVNX\-]*$' $INPUT_FILE | tr -d '\n' | fold -w 60; echo) > $OUTPUT_FILE

IgorFobia

#!/usr/bin/python
# Roll a FASTA file of a circular sequence, changing the starting base of the FASTA sequence to new_startN

from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord

import sys
import os

IgorFobia

import numpy as np
from scipy.stats import chisqprob, chisquare

def gtest(f_obs, f_exp=None, ddof=0):
    """
    http://en.wikipedia.org/wiki/G-test

    The G test can test for goodness of fit to a distribution

    Parameters