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)

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

# -*- 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

# 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

#!/bin/bash
ethernet=$(ifconfig en0 | awk '/ether/{print $2}')
wifi=$(ifconfig en1 | awk '/ether/{print $2}')
echo "Ethernet MAC Address: $ethernet"
echo "Wifi MAC Address: $wifi"

jrjhealey

#!/bin/bash

# Script to retrieve PDBs via the command line from the PDB HTTP/FTP

# Capture inputs

usage()
{
cat << EOF
usage: $0 options

jrjhealey

# Getting python logging info output in a colour coded and customised manner.
# Stolen from M. Galardini and https://stackoverflow.com/questions/384076/how-can-i-color-python-logging-output/2532931#2532931

import logging
import sys

BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE = range(8)

COLORS = {
    'WARNING'  : YELLOW,

jrjhealey

#!/bin/bash


#### Print out all fastas ending in a certain string. ####
# Change *"$string" to *"$string"* to find containing,
# or "$string"* to find starts with.

file="$1"
string="$2"

jrjhealey

"""
This script pulls in homologs of proteins from PDB
as determined by HHSuite. It then employs pychimera and
UCSF Chimera to structurally match them and get an
indication of how well they score (RMSD) in order
to pick the best simulation.
"""
import os
import subprocess
import sys

jrjhealey

#!/usr/bin/env Rscript

# Plotting surface plots via ggplot2/plotly
# Usage:
# $ Rscript CDmeltplot.R -i data.csv -o filename


############################################################
# General purpose heatmap plotting script for consistency. #
# This script can be slow as it was designed to be pretty  #