jrjhealey

# Extract fasta files by their descriptors stored in a separate file.
# Requires biopython

from Bio import SeqIO
import sys
import argparse

def getKeys(args):
	"""Turns the input key file into a list. May be memory intensive."""

jrjhealey

# -*- coding: utf-8 -*-

"""
This script takes the .hhr files output by HHSuite and
turns the quite verbose file in to a fully tabulated
version with all the fields separated one, one line per
file. Thus, the file can be viewed simply in Excel etc.
It requires the non-standard pandas module.
"""

jrjhealey

#!/usr/bin/python

# This script is designed to take a genbank file and 'slice out'/'subset'
# regions (genes/operons etc.) and produce a separate file. This can be
# done explicitly by telling the script which base sites to use, or can
# 'decide' for itself by blasting a fasta of the sequence you're inter-
# ed in against the Genbank you want to slice a record out of.

# Note, the script (obviously) does not preseve the index number of the
# bases from the original 

jrjhealey

# This script will calculate Shannon entropy from a MSA.

# Dependencies:

# Biopython, Matplotlib [optionally], Math

"""
Shannon's entropy equation (latex format):
    H=-\sum_{i=1}^{M} P_i\,log_2\,P_i
    Entropy is a measure of the uncertainty of a probability distribution (p1, ..... , pM)