ryanlayer

git clone --recursive https://github.com/jbelyeu/SV-plaudit.git
cd SV-plaudit
samtools view -b ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/phase3/data/NA12892/high_coverage_alignment/NA12892.mapped.ILLUMINA.bwa.CEU.high_coverage_pcr_free.20130906.bam 22 > NA12892.22.bam
samtools view -b ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/phase3/data/NA12891/high_coverage_alignment/NA12891.mapped.ILLUMINA.bwa.CEU.high_coverage_pcr_free.20130906.bam 22 > NA12891.22.bam
samtools view -b ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/phase3/data/NA12878/high_coverage_alignment/NA12878.mapped.ILLUMINA.bwa.CEU.high_coverage_pcr_free.20130906.bam 22 > NA12878.22.bam
samtools index NA12878.22.bam
samtools index NA12891.22.bam
samtools index NA12892.22.bam
bcftools view -c 1 -s NA12878 ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/phase3/integrated_sv_map/ALL.wgs.integrated_sv_map_v2.20130502.svs.genotypes.vcf.gz > NA12878.22.vcf
mkdir sv_imgs

ryanlayer

from cyvcf2 import VCF
import numpy as np

my_vcf = VCF('-')

#print my_vcf.raw_header,
samples = np.array(my_vcf.samples)

for variant in my_vcf:
    gts =  variant.gt_types

ryanlayer

import sys
import re
from operator import itemgetter

char_map = { '0':  u'\u2070', \
             '1':  u'\u00B9', \
             '2':  u'\u00B2', \
             '3':  u'\u00B3', \
             '4':  u'\u2074', \
             '5':  u'\u2075', \

ryanlayer

BAM=$1

OUT_DIR=$2

LUMPY_HOME=$HOME/src/lumpy-sv
SAMBAMBA=$HOME/bin/sambamba
SAMBLASTER=$HOME/bin/samblaster
BAMLIBS=$LUMPY_HOME/scripts/bamkit/bamlibs.py
SAMTOBAM="$SAMBAMBA view -S -f bam -l 0"
SAMSORT="$SAMBAMBA sort -m 1G --tmpdir "

ryanlayer

WIN=100
SAMPLE="NA12878"
SAMPLE_BAM="NA12878_S1.bam"

cnvnator -root $SAMPLE.$WIN.root -genome GRCh37 -tree $SAMPLE_BAM
cnvnator -genome GRCh37 -root $SAMPLE.$WIN.root -his $WIN -d /shared/genomes/b37/full/chroms
cnvnator -root $SAMPLE.$WIN.root -stat $WIN
cnvnator -root $SAMPLE.$WIN.root -partition $WIN
cnvnator -root $SAMPLE.$WIN.root -call $WIN > $SAMPLE.$WIN.cnvcalls.txt

ryanlayer

cd ~/src/
wget http://root.cern.ch/download/root_v6.04.02.source.tar.gz

module load gcc/4.9.2
module load python/2.7.10

tar zxvf root_v6.04.02.source.tar.gz
cd root-6.04.02/
./configure
make

ryanlayer

wget --trust-server-names http://bit.ly/gqt_bcf
bcftools index chr11.11q14.3.bcf
gqt convert bcf -i chr11.11q14.3.bcf
wget --trust-server-names http://bit.ly/gqt_ped
head 1kg.phase3.ped
gqt convert ped -i chr11.11q14.3.bcf -p 1kg.phase3.ped
cat 1kg.phase3.ped | grep GBR | head
cat 1kg.phase3.ped | grep GBR | cut -f2 > GBR.txt
cat 1kg.phase3.ped | grep YRI | cut -f2 > YRI.txt
time vcftools \

ryanlayer

wget ftp://ftp-trace.ncbi.nih.gov/giab/ftp/data/NA12878/variant_calls/RTG/cohort-illumina-wgs.vcf.gz
bcftools index cohort-illumina-wgs.vcf.gz
gqt convert bcf -i cohort-illumina-wgs.vcf.gz
wget --trust-server-names http://bit.ly/ceph_ped
head ceph1463.ped
gqt convert ped \
    -i cohort-illumina-wgs.vcf.gz \
    -p ceph1463.ped
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \

ryanlayer

BAM=your.bam
OUT_DIR=what_lumpy_needs

LUMPY_HOME=$HOME/src/lumpy-sv
SAMBAMBA=$HOME/bin/sambamba
SAMBLASTER=$HOME/bin/samblaster
SAMTOBAM="$SAMBAMBA view -S -f bam -l 0"
SAMSORT="$SAMBAMBA sort -m 1G --tmpdir "
PAIREND_DISTRO=$LUMPY_HOME/scripts/pairend_distro.py
BAMGROUPREADS=$LUMPY_HOME/scripts/bamkit/bamgroupreads.py

ryanlayer

git clone https://github.com/samtools/htslib.git
cd htslib
make
cd ..
wget http://www.sqlite.org/2014/sqlite-amalgamation-3080701.zip
unzip sqlite-amalgamation-3080701.zip
git clone https://github.com/ryanlayer/gqt.git
cd gqt
make
cd test/func