pontikos

#!/bin/bash
#CADDpath="`dirname \"$0\"`"
#CADDpath="`( cd \"$CADDpath/..\" && pwd )`"
set +x

CADDpath=/share/apps/genomics/CADD_v1.3/
if [ -z "$VEPpath" ] ; then source ${CADDpath}/bin/config.sh; fi
echo $VEPpath

NCORES=`expr $(lscpu | grep '^CPU(s):' | cut -f2 -d: | tr -d ' ') - 2`

pontikos

melt(data.matrix(X))->m2

pontikos

import sys
import requests

# print urls of fastq files to download
# obtain access token by following instructions here:
# https://support.basespace.illumina.com/knowledgebase/articles/403618-python-run-downloader

AccessToken=sys.argv[1]

# user

pontikos

from __future__ import print_function
import sys
import re
from selenium import webdriver
from random import randint
from time import sleep


dr = webdriver.PhantomJS()
#dr.get('http://www.genecards.org')

pontikos

#!/usr/bin/env Rscript

library(Rsamtools)

# '/cluster/scratch3/vyp-scratch2/reference_datasets/Kaviar/Kaviar-160204-Public/vcfs/Kaviar-160204-Public-hg38.vcf.gz'
#f <- '/cluster/scratch3/vyp-scratch2/reference_datasets/Kaviar/Kaviar-160204-Public/vcfs/Kaviar-160204-Public-hg19.vcf.gz'

read('rare_shared_2006_2006A.csv')->d

x <- do.call('rbind', strsplit(d$VARIANT_ID, '_'))

pontikos

# chrom sizes in hg19

declare -A sizes
sizes["chr1"]=249250621
sizes["chr2"]=243199373
sizes["chr3"]=198022430
sizes["chr4"]=191154276
sizes["chr5"]=180915260
sizes["chr6"]=171115067
sizes["chr7"]=159138663

pontikos

On the results page of the imputation, in Chrome, open you javascript console and run this:

copy(document.body.innerHTML);

This will copy the javacript rendered page to you clipboard. Now paste it in a document say download_page.html.

Then run this python script to extract the urls:

from __future__ import print_function

pontikos

# bars and stars algorithm
N=5
for n in range(0,N):
    x=[1]*n
    for i in range(0,(len(x)+1)):
        for j in range(i,(len(x)+1)):
            print 100-n, sum(x[0:i]), sum(x[i:j]), sum(x[j:len(x)])

pontikos

ibrary(snpStats)

d <- read.plink('all.bed','all.bim','all.fam')
print(dim(X <- d$genotypes))

# snps were everyone is the same thing are boring
#snp.qc <- col.summary(X)
#X <- X[,snp.qc$MAF > 0]
# also should remove singleton variants i.e only present in a single person

pontikos

#! /bin/env bash

function error() { >&2 echo -e "\033[31m$*\033[0m"; }
function stop() { error "$*"; exit 1; }
try() { "$@" || stop "cannot $*"; }

file=$1
#doesn't work for double extension .gvcf.gz
ext="${file##*.}"
search=