arq5x

export PBTHOME=/home/arq5x/cphg-home/projects/pybedtools

shuffle 1094PC0012.bed > a.shuf.full.bed
shuffle 1094PC0012.bed > b.shuf.full.bed
head -1000 a.shuf.full.bed > a.shuf.1e3.bed; head -1000 b.shuf.full.bed > b.shuf.1e3.bed
head -10000 a.shuf.full.bed > a.shuf.1e4.bed; head -10000 b.shuf.full.bed > b.shuf.1e4.bed
head -100000 a.shuf.full.bed > a.shuf.1e5.bed; head -100000 b.shuf.full.bed > b.shuf.1e5.bed
head -1000000 a.shuf.full.bed > a.shuf.1e6.bed; head -1000000 b.shuf.full.bed > b.shuf.1e6.bed
head -10000000 a.shuf.full.bed > a.shuf.1e7.bed; head -10000000 b.shuf.full.bed > b.shuf.1e7.bed
head -100000000 a.shuf.full.bed > a.shuf.1e8.bed; head -100000000 b.shuf.full.bed > b.shuf.1e8.bed

arq5x

from pybedtools import BedTool
snps = BedTool('../test/data/snps.bed.gz')
genes = BedTool('../test/data/hg19.gff')

intergenic_snps = (snps - genes)
nearby = genes.closest(intergenic_snps,
d=True,
stream=True)
for gene in nearby:
if int(gene[-1]) < 5000:

arq5x

#!/usr/bin/env python

"""
get_bam_allele.py
Usage: python get_bam_allele.py [BAM] [BED]
"""

from pybedtools import BedTool
import sys

arq5x

#!/usr/bin/env python

from collections import namedtuple, defaultdict
from pybedtools import BedTool
import argparse

Point    = namedtuple('Point', ['id', 'pos', 'type'])
Interval = namedtuple('Interval', ['chrom', 'start', 'end'])

arq5x

nldksvnasl

dfbv
dfgb

zdf
gfg
ncg
hn
fghn

arq5x

import ez_setup
ez_setup.use_setuptools()

import glob
import os
import sys
from setuptools import setup
from distutils.extension import Extension

if 'setuptools.extension' in sys.modules:

arq5x

# Note, these instructions assume OS X.
# Alternatives to the afplay command likely exist on
# other POSIX systems.  Google is your friend.

# NOTE: Obviously, you can put the MP3 file where ever you so desire.


# 1. Make a new directory called "ka-ching" under /usr/share/
sudo mkdir /usr/share/ka-ching

arq5x

read 11960......................................................................12030
exon                                                   12010..............................<snip>12057
overlap (21bp)                                              ********************

arq5x

# Create SNPs-only subset of the 1000G callset VCF
$ curl -s http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/working/20120316_phase1_integrated_release_version2/ALL.chr22.phase1_release_v2.20101123.snps_indels_svs.vcf.gz | \
zcat | \
awk '$0 ~ /^#/ ||  $0 ~ "VT=SNP"'  | \
gzip > ALL.chr22.phase1_release_v2.20101123.snps_indels_svs.snpsonly.vcf.gz

# Use VCFTools to convert to TPED
$ vcftools

VCFtools (v0.1.8)

arq5x

##########################################
# Step 0. setup a list of sample names.  
# Assume that each of your gzipped
# FASTQ files is named as follows:
# sample1.1.fq.gz
# sample1.2.fq.gz
# sample2.1.fq.gz
# sample2.2.fq.gz
# ...
# sampleN.1.fq.gz