#!/bin/bash

gdacsite=http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/XXXX/20160128
rnaseqfile=gdac.broadinstitute.org_XXXX.Merge_rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_genes_normalized__data.Level_3.2016012800.0.0.tar.gz
clinicalfile=gdac.broadinstitute.org_XXXX.Merge_Clinical.Level_1.2016012800.0.0.tar.gz


for gdac in ACC BLCA BRCA CESC CHOL COAD COADREAD DLBC ESCA GBM GBMLGG HNSC KICH KIPAN KIRC KIRP LAML LGG LIHC LUAD LUSC MESO OV PAAD PCPG PRAD READ SARC SKCM STAD STES TGCT THCA THYM UCEC UCS UVM
do
    echo "Processing $gdac"
    mkdir -pv $gdac
    cd $gdac 
    gdacurl=${gdacsite//XXXX/$gdac}
    rnasequrl=${rnaseqfile//XXXX/$gdac}
    clinicalurl=${clinicalfile//XXXX/$gdac}
    mkdir -pv RNA-seq
    cd RNA-seq
    wget -nv $gdacurl/$rnasequrl
    tar -zxf $rnasequrl
    rnaseqdir=${rnasequrl//.tar.gz//}
    cp $rnaseqdir/$gdac*RSEM*.txt geneexpression_RSEM.txt -vf
    rm -vf $rnasequrl

    cd ..

    mkdir -pv CLINICAL
    cd CLINICAL
    wget  -nv $gdacurl/$clinicalurl
    tar -zxf $clinicalurl
    cp */*clin.merged.txt clinical_merged.txt
    rm -vf $clinicalurl
    cd ..

    echo "Completed $gdac"
    echo "======================================>"

    cd ../

done