arq5x

attributes:
  name: cpg
  version: 0.1

recipe:
  full:
    recipe_type: bash
    recipe_cmds: 
      - > 
        mysql --user=genome --host=genome-mysql.cse.ucsc.edu \

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.

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

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

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

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

arq5x

library(ggplot2)
library(gridExtra)
cov <- read.table("/Users/arq5x/Documents/Projects/HallLab/TCGA-1KG/ForKeystone/tcga_and_1kg_span_cov.txt",header=TRUE)
span <- qplot(sample, span_cov, data=cov, fill=factor(type_num), geom="bar", 
             binwidth=1, 
             xlab="Sample", 
             ylab="Spanning coverage") +
        opts(axis.ticks = theme_blank(), 
             axis.text.x = theme_blank(), 
             axis.title.x = theme_text(size = 18, face = "bold"), 

arq5x

export BATCH1="1094PC0005 1094PC0009 1094PC0012 1094PC0013 "
export BATCH2="1094PC0016 1094PC0017 1094PC0018 1094PC0019 \
               1094PC0020 1094PC0021 1094PC0022 1094PC0023 1094PC0025 "
export BATCH3="1478PC0001B 1478PC0002 1478PC0003 1478PC0004 \
               1478PC0005 1478PC0006B 1478PC0007B 1478PC0008B \
               1478PC0009B 1478PC0010 1478PC0011 1478PC0012 \
               1478PC0013B 1478PC0014B 1478PC0015B 1478PC0016 \
               1478PC0017B 1478PC0018 1478PC0019 1478PC0020 \
               1478PC0021 1478PC0022B 1478PC0023B 1478PC0024B"
export BATCH4="1719PC0001 1719PC0002 1719PC0003 1719PC0004 \

arq5x

############################################################
# Pair the alignments.
# Keep proper, on-target (i.e. +/- 500 bp of a probe) pairs.
# Require mapping quality >= 20
############################################################
export DIR=/home/arq5x/cphg-home/projects/t1d/t1d-exome-suna/
export STEPNAME=t1d-ex-bwa-par
export GENOME=/home/arq5x/cphg-home/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa

arq5x

# Step 1: Get transcripts from UCSC refGene (hg19) into a BED file.
# Notes:
#      the awk statement reorders the "raw" columns into BED12 format
#      bed12ToBed6 converts the BED12 into discrete BED6 entries for each exon
#           - the -n option is new and in the bedtools repository
$ curl -s http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/refGene.txt.gz | \
      zcat | \
      awk '{OFS="\t"; print $3,$5,$6,$2,$9,$4,$7,$8,"0",$9,$10,$11}' | \
      bed12ToBed6 -n \
      > refGene.bed