obenshaindw

import boto3
from botocore.exceptions import ClientError
import requests
import getpass
import os
import time


username = input('Username:')
password = getpass.getpass()

obenshaindw

#!/bin/bash

MFF_DIRECTORY=$1

for mffzip in "$MFF_DIRECTORY"*.mff.zip; do
  echo "Renaming $mffzip directories to just ${mffzip%.zip}"
  mv "$mffzip" "${mffzip%.zip}";
done

for mff in *.mff; do

obenshaindw

#!/bin/bash
## NDA AWS Token Generator
## Author: NIMH Data Archives
##         http://ndar.nih.gov
## License: MIT
##          https://opensource.org/licenses/MIT

##############################################################################
#
# Script to retrieve generated AWS Tokens from NIMHDA

obenshaindw

#!/bin/bash
# Pass in s3 URL=$1 

# Set up Pathing
    ## Drop s3://
    pname=${1#*//}
    ## Drop Bucket Name, i.e., NDAR_Central*, NDAR_Results, etc.
    pname=${pname#*/}
    ## Get text after last /
    fname=${1##*/}

obenshaindw

echo $1
# Use grep REGEX to extract portion of s3 URL to reuse as zip file name.
folder=`echo $1 | grep -Eio '\/([0-9]+)\/$' | grep -Eio '([0-9]+)'`
mkdir ./$folder
echo s3cmd get --recursive $1 ./$folder
s3cmd get --recursive $1 ./$folder
echo zip -r $folder ./$folder/*
zip -r $folder ./$folder/*
echo rm -rf ./$folder/
rm -rf ./$folder/

obenshaindw

use strict;
use warnings;
use Vcf;

my $filename = $ARGV[0];

open ( my $handle, "<", $filename);
my $vcf = Vcf->new(fh=>$handle);
    $vcf->parse_header();
vcf_iterate();

obenshaindw

#!/usr/bin/bash
#
# make_gz.sh
#

# Call this script with a list of s3 locations with VCF files to parse
# aws --profile NDAR s3 ls s3:/S3_URL/ | awk '{print $4}' | xargs -n1 -P4 sh make_gz.sh
# xargs -n1 -P4 accepts one argument and runs 4 parallel processes
#

obenshaindw

#GATK Method <- Slower and keeps original ID plut dbSNP rsID
# R=Reference FASTA
# V=VCF file to add IDs to
# --dbsnp = dbsnp VCF -- download from NCBI FTP

java -jar GenomeAnalysisTK.jar -R /reference/Homo_sapiens_assembly19.fasta -T VariantAnnotator -V vcf_to_add_id_to.vcf --dbsnp /reference/dbsnp_137.b37.vcf.gz --out /data/Broad.chr1.annotated.vcf

#bcftools Method <- Faster, replaces existing ID with dbSNP rsID
/usr/bin/htslib/bcftools/bcftools annotate -a /reference/dbsnp_137.b37.vcf.gz -c ID vcf_to_add_id_to.vcf

obenshaindw

/usr/bin/htslib/bcftools view -H vcf_with_bad_header.vcf > vcf_header.vcf
vim vcf_header.vcf
#Make changes to header
/usr/bin/htslib/bcftools/bcftools reheader -h vcf_header vcf_with_bad_header.vcf  -o reheadered.vcf

obenshaindw

/usr/bin/htslib/bcftools/bcftools view vcf_with_chr.vcf | sed "s/chr//g" | /usr/bin/htslib/htslib/bgzip -c > BCM_hg19.reheader.no_chr.vcf.gz