# This file contains installation instructions for the programs used in Module 4.
# It assumes that you are running on linux
# The following commands will download and compile the software within your current working directory
# If you want to run the programs by just typing 'bwa' or 'samtools' you will need to add
# the directories created below to your $PATH environment variable

#
# samtools
#
wget https://github.com/samtools/samtools/archive/master.zip
unzip master.zip
rm master.zip
cd samtools-master
make
./samtools
cd ..

#
# bwa
# 
wget https://github.com/lh3/bwa/archive/master.zip
unzip master.zip
rm master.zip
cd bwa-master
make
./bwa
cd ..
   
#
# picard
#
wget http://downloads.sourceforge.net/project/picard/picard-tools/1.92/picard-tools-1.92.zip
unzip picard-tools-1.92.zip
rm picard-tools-1.92.zip
cd picard-tools-1.92
java -jar SortSam.jar
cd ..

#
# hydra 
# 
wget https://hydra-sv.googlecode.com/files/Hydra.v0.5.3.tar.gz
tar -xzf Hydra.v0.5.3.tar.gz
rm Hydra.v0.5.3.tar.gz
cd Hydra-Version-0.5.3
make clean
make
bin/hydra
cd ..

#
# Download the human reference genome. 
# We will download the version used by the 1000 Genomes Project.
# It is build 37 of the reference and contains extra sequences to help
# avoid false positive variant calls by misalignments to the reference
#
# The `bwa index` command will build an index file so you can run bwa against the reference
# It will take a few hours to run so I do not recommend running it on your cloud instance
# during the workshop

mkdir genome
cd genome
wget ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/technical/reference/human_g1k_v37.fasta.gz
gunzip human_g1k_v37.fasta.gz
#../bwa-master/bwa index human_g1k_v37.fasta
cd ..