Created
July 12, 2018 17:38
-
-
Save tluquez/549f2b2b3af916db4d3f75917c529f42 to your computer and use it in GitHub Desktop.
Program to download the human reference genome (GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz), the annotation file for that human reference genome (GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gff.gz) and also downloads all .fastq files from ENA supplied by the user in a text file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env bash | |
# MIT License | |
# | |
# Copyright (c) [2018] [Grupo de Bioquimica Experimental y Computacional from the Pontificia Universidad Javeriana and Tain Velasco-Luquez] | |
# | |
# Permission is hereby granted, free of charge, to any person obtaining a copy | |
# of this software and associated documentation files (the "Software"), to deal | |
# in the Software without restriction, including without limitation the rights | |
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |
# copies of the Software, and to permit persons to whom the Software is | |
# furnished to do so, subject to the following conditions: | |
# | |
# The above copyright notice and this permission notice shall be included in all | |
# copies or substantial portions of the Software. | |
# | |
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | |
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | |
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | |
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | |
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | |
# SOFTWARE. | |
# Author: | |
#Tain Velasco-Luquez <tvelasco@javeriana.edu.co> @TainVelasco-Luquez: Design and implementation | |
# Last updated 12/07/2018 | |
##### Usage | |
usage() { | |
printf " | |
$(basename "$0") -- Program to download the human reference genome (GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz), the annotation file for that human reference genome (GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gff.gz) and also downloads all .fastq files from ENA supplied by the user in a text file. | |
Optional: | |
--help -h Show this help text | |
-First_argument Path to save the data | |
-uncompress If \"true\" then apply gunzip to all .gz | |
Mandatory: | |
-Second_argument File with the aspera urls downloaded from ENA | |
-Third_argument The max transfer rate over the network (e.g 300m or 600m) | |
-Fourth_argument Path to the asperaweb_id_dsa.openssh (e.g. ~/Applications/Aspera\Connect.app/Contents/Resources/asperaweb_id_dsa.openssh) | |
Requirements: | |
1. This file assumes aspera CLI is installed and its path properly exported | |
" | |
} | |
##### Check for help option | |
if [ "$1" == "--help" ] || [ "$1" == "-h" ]; then | |
usage | |
exit 0 | |
fi | |
##### Check for arguments | |
if [ $# -eq 0 ] | |
then | |
printf "No arguments supplied." | |
usage | |
exit 1 | |
fi | |
##### Variables | |
my_path=$1 # Path to save the database | |
asp_url=$2 # File with the aspera url downloaded from ENA | |
max_transfer_rate=$3 # Max transfer rate (e.g 300m) | |
aspera_path=$4 # Path to the asperaweb_id_dsa.openssh (e.g. ~/Applications/Aspera\ Connect.app/Contents/Resources/asperaweb_id_dsa.openssh) | |
uncompress=$5 | |
# Lets start by downloading the reference genome according to the instructions in RNA_processing.md | |
printf "Downloading the reference genome GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz \n" | |
rsync -avP rsync://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz "${my_path}" | |
printf "\n DONE \n" | |
# Now lets download the annotation file for the same version and from the same source as the reference genome, avoiding in this way incomaptibilities | |
printf "Downloading the reference annotation GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gff.gz \n" | |
rsync -avP rsync://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids/GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gff.gz "${my_path}" | |
printf "\n DONE \n" | |
# After download the file with the aspera url, lets remove the header (first line) and save the file with vim | |
vim -c ':1d' -c ':wq' "${asp_url}" | |
printf "The number of files to be downloaded from ENA is:" | |
wc -l "${asp_url}" # How many fastq files are in the study? | |
# Lets download the RNAseq data associated to the study accession number SRP103788 | |
if [[ $PATH = *CLI/bin* ]]; | |
then | |
printf "Downloading the files in ${asp_url} \n" | |
while read every_line; do | |
ascp -QT -l "${max_transfer_rate}" -P33001 -i "${aspera_path}" era-fasp@$every_line "${my_path}" | |
printf $every_line " is downloaded" | |
done < "${asp_url}"; | |
printf "All files have been downloaded \n" >&1 | |
exit 0 | |
else | |
printf "Make sure you export the aspera CLI path. \n" >&2 | |
exit 1 | |
fi | |
# Finally, lets unzip the files | |
if [[ ${uncompress} == "true" ]]; then | |
cd ${my_path} | |
printf "About to uncompress the files...\n" >&1 | |
gunzip *.gz | |
printf "All files have been uncompressed\n" >&1 | |
exit 0 | |
else | |
exit 1 | |
fi | |
##### All done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment