|
| 1 | +#!/bin/bash |
| 2 | + |
| 3 | +## This script will create a Data/ directory in the download |
| 4 | +## the data used in this study each in its given sub-directory. |
| 5 | + |
| 6 | +shopt -s extglob |
| 7 | + |
| 8 | +# Set the download directory (same as working directory by default): |
| 9 | + |
| 10 | +workingdir="$( pwd )" |
| 11 | +outputdir=${workingdir} |
| 12 | + |
| 13 | + |
| 14 | +# Setting option for downloading only specific dataset (default: all): |
| 15 | + |
| 16 | +declare -a steps2run |
| 17 | +steps2run=(step1 step2 step3 step4 step5) |
| 18 | +runonlystep="" |
| 19 | + |
| 20 | + |
| 21 | +# Help menu: |
| 22 | + |
| 23 | +function usage() { |
| 24 | + echo " |
| 25 | + Download Data Help Section: |
| 26 | + =========================== |
| 27 | +
|
| 28 | + Usage: $0 |
| 29 | + |
| 30 | + Or for more options: |
| 31 | +
|
| 32 | + Example: $0 -o ~/path/to/my/directory/ |
| 33 | +
|
| 34 | + Optional arguments: |
| 35 | + -o|--outputdir <path> : Directory path for downloaded data |
| 36 | + --runonlystep <string> : Indicate a specific step to run (see below) |
| 37 | + -h|--help : Display this help message |
| 38 | +
|
| 39 | + This script will download all 4 datasets by default. To download only |
| 40 | + a specific dataset, designate a step number when running the script. |
| 41 | + The following step numbers are valid options: |
| 42 | +
|
| 43 | + step1 : downloads the Human Genome Dating atlas dataset from https://human.genome.dating/ |
| 44 | + step2 : downloads recombination maps for GRCh37 from |
| 45 | + https://github.com/joepickrell/1000-genomes-genetic-maps |
| 46 | + step3 : downloads introgression map files from http://dical-admix.sourceforge.net/ |
| 47 | + step4 : downloads population-specific annotation file from |
| 48 | + http://ftp.ensembl.org/pub/grch37/release-103/variation/gvf/homo_sapiens/ |
| 49 | + step5 : download GRCh37 reference genome files from |
| 50 | + https://www.ncbi.nlm.nih.gov/assembly/GCF_000001405.25/ |
| 51 | + " |
| 52 | +} |
| 53 | + |
| 54 | +if [ -z "$*" ]; then usage ; exit 1 ; fi |
| 55 | + |
| 56 | + |
| 57 | +# Parsing command-line arguments: |
| 58 | + |
| 59 | +OPTIONS=`getopt -o o:h --long outputdir:,runonlystep:,help -n 'download error' -- "$@"` |
| 60 | +if [ $? != 0 ]; then echo " " ; echo "Could not parse options (see above) ..." >&2 ; usage ; exit 1 ; fi |
| 61 | + |
| 62 | +eval set -- "$OPTIONS" |
| 63 | + |
| 64 | +while true ; do |
| 65 | + case "$1" in |
| 66 | + -o|--outputdir) |
| 67 | + case "$2" in |
| 68 | + -*) echo "Please designate an output directory when using -o"; usage; exit 1 ;; |
| 69 | + *) outputdir=$2 ; shift 2 ;; |
| 70 | + esac ;; |
| 71 | + |
| 72 | + --runonlystep) |
| 73 | + case "$2" in |
| 74 | + -*) echo "Please designate the code4Rice3K step to execute"; usage; exit 1 ;; |
| 75 | + *) runonlystep=$2 ; shift 2 ;; |
| 76 | + esac ;; |
| 77 | + |
| 78 | + -h|--help) |
| 79 | + usage; exit 1 ;; |
| 80 | + |
| 81 | + --) shift ; break ;; |
| 82 | + |
| 83 | + *) echo "Unknown option or error" ; usage ; exit 1 ;; |
| 84 | + |
| 85 | + esac |
| 86 | +done |
| 87 | + |
| 88 | + |
| 89 | +# Control which step to run: |
| 90 | + |
| 91 | +if [[ $runonlystep != '' ]] ; then |
| 92 | + steps2run=($runonlystep) |
| 93 | +fi |
| 94 | + |
| 95 | +# Step 0 |
| 96 | +# |
| 97 | +echo "" |
| 98 | +echo "==============================================================================" |
| 99 | +echo " Downloading datasets for the Wang etal., 2022 paper ..." |
| 100 | +echo "==============================================================================" |
| 101 | +echo "" |
| 102 | + |
| 103 | +runstep1=0 |
| 104 | +runstep2=0 |
| 105 | +runstep3=0 |
| 106 | +runstep4=0 |
| 107 | +runstep5=0 |
| 108 | +for step in ${steps2run[@]} ; do |
| 109 | + if [[ $step == "step1" ]] ; then runstep1=1 ; fi |
| 110 | + if [[ $step == "step2" ]] ; then runstep2=1 ; fi |
| 111 | + if [[ $step == "step3" ]] ; then runstep3=1 ; fi |
| 112 | + if [[ $step == "step4" ]] ; then runstep4=1 ; fi |
| 113 | + if [[ $step == "step5" ]] ; then runstep5=1 ; fi |
| 114 | +done |
| 115 | + |
| 116 | + |
| 117 | +if [ ! -d "$outputdir" ] ; then |
| 118 | + echo "" |
| 119 | + echo "... new output directory $outputdir will be created in your working directory." |
| 120 | + mkdir $outputdir |
| 121 | +fi |
| 122 | + |
| 123 | +cd $outputdir |
| 124 | +mkdir -p Atlas Recombination Introgression Populations Reference |
| 125 | + |
| 126 | + |
| 127 | +# Step 1 |
| 128 | +if [[ $runstep1 == 1 ]]; then |
| 129 | + echo "" |
| 130 | + echo "==============================================================================" |
| 131 | + echo "Step 1 Downlowding atlas SNP dating files ..." |
| 132 | + echo "==============================================================================" |
| 133 | + echo "" |
| 134 | + |
| 135 | + cd ${workingdir} |
| 136 | + cd ${outputdir}/Atlas |
| 137 | + |
| 138 | + for i in {1..22}; do |
| 139 | + if [[ ! -e atlas.chr${i}.csv ]]; then |
| 140 | + wget https://human.genome.dating/bulk/atlas.chr${i}.csv.gz && gunzip atlas.chr${i}.csv.gz |
| 141 | + fi |
| 142 | + done |
| 143 | + |
| 144 | + echo "Atlas files downloaded" |
| 145 | + echo "" |
| 146 | +fi |
| 147 | + |
| 148 | + |
| 149 | +# Step 2 |
| 150 | +if [[ $runstep2 == 1 ]]; then |
| 151 | + echo "" |
| 152 | + echo "==============================================================================" |
| 153 | + echo "Step 2 Downlowding GRCH37 recombination maps ..." |
| 154 | + echo "==============================================================================" |
| 155 | + echo "" |
| 156 | + |
| 157 | + cd ${workingdir} |
| 158 | + cd ${outputdir}/Recombination |
| 159 | + |
| 160 | + if [[ ! -e HapmapII_GRCh37_RecombinationHotspots.tar.gz ]]; then |
| 161 | + wget ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/technical/working/20110106_recombination_hotspots/HapmapII_GRCh37_RecombinationHotspots.tar.gz && tar -xzvf HapmapII_GRCh37_RecombinationHotspots.tar.gz |
| 162 | + fi |
| 163 | + |
| 164 | + echo "Recombination maps downloaded" |
| 165 | + echo "" |
| 166 | +fi |
| 167 | + |
| 168 | + |
| 169 | +# Step 3 |
| 170 | +if [[ $runstep3 == 1 ]]; then |
| 171 | + echo "" |
| 172 | + echo "==============================================================================" |
| 173 | + echo "Step 3 Downlowding Neanderthal introgression files ..." |
| 174 | + echo "==============================================================================" |
| 175 | + echo "" |
| 176 | + |
| 177 | + cd ${workingdir} |
| 178 | + cd ${outputdir}/Introgression |
| 179 | + |
| 180 | + echo " |
| 181 | + Actually, I couldn't put a script here to download this data directly. |
| 182 | + The Neanderthal introgression files from Steinrucken et al., 2018 |
| 183 | + are hosted on a google drive. You can download it yourself following |
| 184 | + this link here: |
| 185 | +
|
| 186 | + https://drive.google.com/drive/folders/175ae-y9Q9Q6FQN6kQS6iGduzeAdHQZXY |
| 187 | + " |
| 188 | + echo "" |
| 189 | +fi |
| 190 | + |
| 191 | + |
| 192 | +# Step 4 |
| 193 | +if [[ $runstep4 == 1 ]]; then |
| 194 | + echo "" |
| 195 | + echo "==============================================================================" |
| 196 | + echo "Step 4 Downlowding population-specific annotations ..." |
| 197 | + echo "==============================================================================" |
| 198 | + echo "" |
| 199 | + |
| 200 | + cd ${workingdir} |
| 201 | + cd ${outputdir}/Populations |
| 202 | + |
| 203 | + if [[ ! -e 1000GENOMES-phase_3.gvf ]]; then |
| 204 | + wget http://ftp.ensembl.org/pub/grch37/release-103/variation/gvf/homo_sapiens/1000GENOMES-phase_3.gvf.gz && gunzip 1000GENOMES-phase_3.gvf.gz |
| 205 | + fi |
| 206 | + |
| 207 | + echo "Population-specific GVF file downloaded" |
| 208 | + echo "" |
| 209 | +fi |
| 210 | + |
| 211 | + |
| 212 | +# Step 5 |
| 213 | +if [[ $runstep5 == 1 ]]; then |
| 214 | + echo "" |
| 215 | + echo "==============================================================================" |
| 216 | + echo "Step 5 Downlowding GRCh37 reference genome ..." |
| 217 | + echo "==============================================================================" |
| 218 | + echo "" |
| 219 | + |
| 220 | + cd ${workingdir} |
| 221 | + cd ${outputdir}/Reference |
| 222 | + |
| 223 | + if [[ ! -e GCF_000001405.25_GRCh37.p13_genomic.fna ]]; then |
| 224 | + wget https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.25_GRCh37.p13/GCF_000001405.25_GRCh37.p13_genomic.fna.gz && gunzip GCF_000001405.25_GRCh37.p13_genomic.fna.gz |
| 225 | + fi |
| 226 | + |
| 227 | + echo "Referece genome file downloaded" |
| 228 | + echo "" |
| 229 | +fi |
| 230 | + |
| 231 | + |
| 232 | +echo "" |
| 233 | +echo "==============================================================================" |
| 234 | +echo "Files downloaded." |
| 235 | +echo "==============================================================================" |
| 236 | +echo "" |
| 237 | + |
| 238 | +exit |
| 239 | + |
0 commit comments