arq5x

######################################################################################################
# Version 2.18.0
######################################################################################################

# BAM, CHROMSWEEP
time ./bedtools intersect -a random.20M.sorted.bam -b gencode.v17.exons.sorted.bed -sorted > /dev/null

real  0m20.153s
user	0m19.953s
sys	0m0.192s

arq5x

Load a GEMINI database from a VCF

$ gemini load -v nobel.vcf -t VEP --cores 23 -p samples.ped nobel.db

Launch the GEMINI web server

(this will run on your local machine on port 8088)

$ gemini browser nobel.db

arq5x

Thanks to @Adrian_H, @RoryKirchner, @genetics_blog, 
          @leonidkrugliak, @Graham_Coop, @yokofakun, 
          @pathogenomenick, @caseybergman, @Jalfoldi, 
          @Paul_R_Johnston, @gknoProject, @David_Dobbs, 
          @vsbuffalo, @robinhenig, @nccomfort, 
          @GholsonLyon, @notSoJunkDNA, @neilfws, 
          @rovingpencil, @rtraborn

In addition, please refer to Casey Bergman's collection of other books:
http://www.librarything.com/catalog/xylem&tag=genetics&collection=-1

arq5x

export SAMPLES="BLV4 NCH411GBM_CD133high NCH411GBM_CD133low NCH537P54_CD133neg NCH537P54_CD133pos NCH620P55_CD133neg NCH620P55_CD133pos NCH644GBM_CD133high NCH644GBM_CD133low NCH7Md_P43_CD133neg NCH7Md_P43_CD133pos NPC-v"

######################################
# Sort the original BAM files by name:
######################################
export GBMHOME=/net/midtier18/vol79/cphg-quinlan2/projects/gbm-seq-abounader
export STEPNAME=gbm-nmsrt
for sample in `echo $SAMPLES`
do
   export QSUB="qsub -q cphg -W group_list=CPHG -V -l select=1:mem=6000m:ncpus=1 -N $STEPNAME -m bea -M [email protected]"

arq5x

tries=0

while true; 
do
  tries=$((tries+1))
  echo "attempt number $tries"

  # try a shuffle
  bedtools shuffle -i foo.bed -g human.hg19.genome > foo.shuffled.bed
  

arq5x

# DOCS:
# https://gemini.readthedocs.org/en/latest/content/database_schema.html#genotype-information

# GEMINI SOURCE:
# https://github.com/arq5x/gemini

#########################################################################
# load a VCF for a tumor / normal pair into gemini.
# - use 4 cores
# - assume VCF has been annotated with snpEff

arq5x

##fileformat=VCFv4.1
##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description="Imprecise structural variation">
##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
##INFO=<ID=CIPOS,Number=2,Type=Integer,Description="Confidence interval around POS for imprecise variants">
##INFO=<ID=CIEND,Number=2,Type=Integer,Description="Confidence interval around END for imprecise variants">
##INFO=<ID=SVLEN,Number=.,Type=Integer,Description="Difference in length between REF and ALT alleles">
##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">
##INFO=<ID=MATEID,Number=.,Type=String,Description="ID of mate breakends">
##INFO=<ID=EVENT,Number=1,Type=String,Description="ID of event associated to breakend">
##ALT=<ID=DEL,Description="Deletion">

arq5x

#!/usr/bin/env python
import sys
import pprint

def make_grantham_dict(grantham_mat_file):

        """
	Citation:   http://www.ncbi.nlm.nih.gov/pubmed/4843792
	Provenance: http://www.genome.jp/dbget-bin/www_bget?aaindex:GRAR740104

arq5x

# compile
$ g++ zlib-example.cpp -lz -o zlib-example

# run
$ ./zlib-example
Uncompressed size is: 36
Uncompressed string is: Hello Hello Hello Hello Hello Hello!

----------

arq5x

#!/usr/bin/env python
import sys
from gemini import GeminiQuery

db = sys.argv[1]

# create a GeminiQery instance for the requested database
gq = GeminiQuery(db)