arq5x

# get HumVar
wget ftp://genetics.bwh.harvard.edu/pph2/training/humvar-2011_12.predictions.tar.gz
tar -zxvf humvar-2011_12.predictions.tar.gz

# get db snp
wget http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/snp138.txt.gz
gunzip snp138.txt.gz

# get the deleterious SNPs
grep snp138.txt -wFf <(grep rs humvar-2011_12.deleterious.pph.output | cut -f 5) \

arq5x

tosses <- 200
experiments <- 1000
hist((rbinom(experiments, tosses, 0.5) / tosses), 
     breaks=20, xlim=c(0,1), 
     main=paste("Distribution of % heads from", experiments, 
                "experiments with", tosses, "tosses each"),
     xlab = "Fraction of tosses that were heads")

arq5x

# bedtools --version
# bedtools v2.24.0-14-gaa11ef9

########################################################
# Create a BED file of 5kb windows with 2.5kb overlap
# tiling build 37 (hg19) of the human genome
########################################################
bedtools makewindows -g hg19.txt -w 5000 -s 2500 > hg19.w5k.s2.5k.bedg

########################################################

arq5x

chmod a+x vcfsort.sh
vcfsort.sh trio.trim.vep.vcf.gz

arq5x

sudo pip install awscli
aws configure
aws s3 ls
aws s3 ls s3://gqt-data

arq5x

cat ivl.bed
chr1	10	30

cat data.bed
chr1	9	20	d1
chr1	12	18	d2
chr1	12	20	d3
chr1	15	16	d4
chr1	25	40	d5
chr1	26	30	d6

arq5x

import sys
import numpy as np

"""
	Simulate chutes and ladders.
	Reports the number of moves for 1-player to reach the end,
	followed by the list of rolls that player had.

	Run as follows for 100000 games with 1 player. Report the total
	number of moves made by the winning player:

arq5x

import sys
from itertools import *

"""
compute the complexity of each kmer passed in
given the format of the output of `jellyfish dump -ct`
complexity is measured as the number of runs divided
by the total length of the sequence.
e.g., "AAAAA" would be 1/5
and   "ACTGC" would be 5/5

arq5x

Cancer_type	Lifetime_cancer_incidence	Total_cells_tissue	Total_Stem_Cells	Stem_cell_divisions_per_year	Stem_cell_divisions_per_lifetime	LCSD
ALL	0.0041	3000000000000	135000000	12	960	129900000000
BCC	0.3	180000000000	5820000000	7.6	608	3550000000000
CLL	0.0052	3000000000000	135000000	12	960	129900000000
Colorectal	0.048	30000000000	200000000	73	5840	1168000000000
Colorectal_FAP	1	30000000000	200000000	73	5840	1168000000000
Colorectal_Lynch	0.5	30000000000	200000000	73	5840	1168000000000
Duodenum_adenocarcinoma	0.0003	680000000	4000000	24	1947	7796000000
Duodenum_adenocarcinoma_with_FAP	0.035	680000000	4000000	24	1947	7796000000
Esophageal_squamous_cell_carcinoma	0.001938	3240000000	846000	17.4	1390	1203000000

arq5x

# 1. Download BED files of 349 DHS experiments from Science, 337, no. 6099, pp. 1190-1195, 7 Sep. 2012
# http://www.uwencode.org/proj/Science_Maurano_Humbert_et_al/
wget http://www.uwencode.org/proj/Science_Maurano_Humbert_et_al/data/all_fdr0.05_hot.tgz

# 2. Unpack.
tar -zxvf all_fdr0.05_hot.tgz

# 3. Make sure all of the files are sorted lexicographically by chrom, then numerically by start.
#    This is required for the sweep allgorithm.
#    Hint: they are sorted correctly, this is just a sanity check.