Daniel E Cook danielecook

## pubmed pairwise.R
library(RISmed)
library(parallel)
library(ggplot2)

# Given two lists of terms, lets see how 'hot' they are together
set1 <- c("ebola","autoimmune","Diabetes","HIV","Glioblastoma","Asthma","Schizophrenia")
set2 <- c("C. elegans","D. Melanogaster","C. japonica", "M. Musculus","S. Cerevisiae")

# Generate all possible pairs
pairs <- expand.grid(set1, set2, stringsAsFactors=F)

## google_calendar.js
/**
 * Get a user's name, by accessing contacts.
 *
 * @returns {String} FullName, or UserID
 *                   if record not found in contacts.
 */
function getUserName(email){
  var user = ContactsApp.getContact(email);

  // If user in contacts, return their name

## het_polarization.py
#!bin/usr/python
'''
Heterozygote Polarization Script
usage:
bcftools view -M 2 <filename> | python het_polarization.py  | bcftools view -O b > <filename.het.polarized.bcf>

Tags variants 'pushed' to ref or alt as follows:

AA - Pushed towards reference
AB - Kept as het

## plot_peaks.R
library(data.table)
library(stringr)
library(splitstackshape)

args <- commandArgs(trailing=T)
if (length(args) == 0) {
  setwd("/Users/dancook/Dropbox/Andersen lab/LabFolders/Dan/ForOthers/Maneeshi")
}

df <- fread("Snail2_Twist_MergedPeaksPS1005kbSummit300bp_Sn_TwEBox.txt")

## fasta_sequence_lengths.sh
cat file.fa | awk '$0 ~ ">" {print c; c=0;printf substr($0,2,100) "\t"; } $0 !~ ">" {c+=length($0);} END { print c; }'

## rprofile.R
# Place in /Users/Username/.Rprofile
"
sys.source('~/Dropbox/appdata/Rprofile.r')
"


## Create a new invisible environment for all the functions to go in so it doesn't clutter your workspace.
.env <- new.env()


## generate_masked_ranges.py
#!bin/python

import gzip
import io
import sys
import os

# This file will generate a bedfile of the masked regions a fasta file.

# STDIN or arguments

## depth_of_coverage.py
#
# This script calculates the depth of coverage and breadth of coverage for a given bam.
# Outputs a dictionary containing the contig/chromosome names and the depth and breadth of coverage for each
# and for the entire genome.
#
# If you optionally specify the name of the mitochondrial chromosome (e.g. mtDNA, chrM, chrMT)
# The script will also generate breadth and depth of coverage for the nuclear genome AND the ratio
# of mtDNA:nuclearDNA; which can act as a proxy in some cases for mitochondrial count within an individual.
#
# Author: Daniel E. Cook

## import_homer_ChIP_Seq_motif_data.R
# Daniel Cook 2014
# Danielecook.com
#
# Use this function to import ChIP Seq Data generated by Homer. This data is generated using homers findMotifsGenome.pl
# command with the '-find <motif file>' argument. Generate output
# looks like this:
#
# 1. Peak/Region ID
# 2. Chromosome
# 3. Start

## test_fastq.sh
# Generate tiny FASTQs for quick testing.

function test_set() {
for r in `ls *$1*.fq.gz`; do
    gunzip -kfc $r | head -n 50000 | gzip > ${r/$1/$2}
done;
}
	library(RISmed)
	library(parallel)
	library(ggplot2)

	# Given two lists of terms, lets see how 'hot' they are together
	set1 <- c("ebola","autoimmune","Diabetes","HIV","Glioblastoma","Asthma","Schizophrenia")
	set2 <- c("C. elegans","D. Melanogaster","C. japonica", "M. Musculus","S. Cerevisiae")

	# Generate all possible pairs
	pairs <- expand.grid(set1, set2, stringsAsFactors=F)
	/**
	* Get a user's name, by accessing contacts.
	*
	* @returns {String} FullName, or UserID
	* if record not found in contacts.
	*/
	function getUserName(email){
	var user = ContactsApp.getContact(email);

	// If user in contacts, return their name
	#!bin/usr/python
	'''
	Heterozygote Polarization Script
	usage:
	bcftools view -M 2 <filename> \| python het_polarization.py \| bcftools view -O b > <filename.het.polarized.bcf>

	Tags variants 'pushed' to ref or alt as follows:

	AA - Pushed towards reference
	AB - Kept as het
	library(data.table)
	library(stringr)
	library(splitstackshape)

	args <- commandArgs(trailing=T)
	if (length(args) == 0) {
	setwd("/Users/dancook/Dropbox/Andersen lab/LabFolders/Dan/ForOthers/Maneeshi")
	}

	df <- fread("Snail2_Twist_MergedPeaksPS1005kbSummit300bp_Sn_TwEBox.txt")
	# Place in /Users/Username/.Rprofile
	"
	sys.source('~/Dropbox/appdata/Rprofile.r')
	"


	## Create a new invisible environment for all the functions to go in so it doesn't clutter your workspace.
	.env <- new.env()
	#!bin/python

	import gzip
	import io
	import sys
	import os

	# This file will generate a bedfile of the masked regions a fasta file.

	# STDIN or arguments
	#
	# This script calculates the depth of coverage and breadth of coverage for a given bam.
	# Outputs a dictionary containing the contig/chromosome names and the depth and breadth of coverage for each
	# and for the entire genome.
	#
	# If you optionally specify the name of the mitochondrial chromosome (e.g. mtDNA, chrM, chrMT)
	# The script will also generate breadth and depth of coverage for the nuclear genome AND the ratio
	# of mtDNA:nuclearDNA; which can act as a proxy in some cases for mitochondrial count within an individual.
	#
	# Author: Daniel E. Cook
	# Daniel Cook 2014
	# Danielecook.com
	#
	# Use this function to import ChIP Seq Data generated by Homer. This data is generated using homers findMotifsGenome.pl
	# command with the '-find <motif file>' argument. Generate output
	# looks like this:
	#
	# 1. Peak/Region ID
	# 2. Chromosome
	# 3. Start
	# Generate tiny FASTQs for quick testing.

	function test_set() {
	for r in `ls $1.fq.gz`; do
	gunzip -kfc $r \| head -n 50000 \| gzip > ${r/$1/$2}
	done;
	}