pontikos

import sys,gzip

vcf = gzip.open(sys.argv[1],"r")

#these 9 column headers are standard to all VCF files
STD_HEADERS=['CHROM','POS','ID','REF','ALT','QUAL','FILTER','INFO','FORMAT']
#the samples headers depend on the number of samples in the file
#which we find out once we read the #CHROM line
SAMPLE_HEADERS=[]

pontikos

import sys
i=int(sys.argv[1])
d=dict()
for l in sys.stdin.readlines():
    l=l.strip().split(',')
    k=l.pop(i)
    d[k]=d.get(k,[])+l
for k in d:
    print ','.join([k]+d[k])

pontikos

for f in `find /goon2/project99/IBDAJE_raw/Macrogen/ -type f -name '*_ANNO.csv' `
do
 ln -s $f csv/
done

pontikos

#!/bin/bash
#$ -S /bin/bash
#$ -o /dev/null
#$ -e /dev/null
#$ -cwd
#$ -V
#$ -R y
#$ -pe smp 1
#$ -l scr=1G
#$ -l tmem=2G,h_vmem=1G

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=

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

# 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

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

# 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

#!/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, '_'))