Created
February 24, 2020 23:12
-
-
Save danielecook/2fdfead2562ab6cff28ba79c40960181 to your computer and use it in GitHub Desktop.
setup wormbase genome
This file contains hidden or 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
| # This script will download, index, and prep reference genomes. | |
| # Prep N2 reference genome | |
| RELEASE=WS274 | |
| PROJECT=PRJNA13758 | |
| mkdir -p "${PROJECT}.${RELEASE}" && cd "${PROJECT}.${RELEASE}" | |
| # Annotation file | |
| wget ftp://ftp.ensembl.org/pub/current_gff3/caenorhabditis_elegans/Caenorhabditis_elegans.WBcel235.99.gff3.gz | |
| # Download and prepare FASTA Genome | |
| wget "ftp://ftp.wormbase.org/pub/wormbase/species/c_elegans/${PROJECT}/sequence/genomic/c_elegans.${PROJECT}.${RELEASE}.genomic.fa.gz" | |
| bwa index c_elegans.${PROJECT}.${RELEASE}.genomic.fa.gz | |
| gunzip -kfc c_elegans.${PROJECT}.${RELEASE}.genomic.fa.gz > c_elegans.${PROJECT}.${RELEASE}.genomic.fa | |
| # # Download Annotations | |
| # wget "ftp://ftp.wormbase.org/pub/wormbase/species/c_elegans/${PROJECT}/gff/c_elegans.${PROJECT}.${RELEASE}.annotations.gff3.gz" | |
| # # Filter for wormbase annotations only; Others are not required. | |
| # gunzip -kfc c_elegans.${PROJECT}.${RELEASE}.annotations.gff3.gz | \ | |
| # awk '$0 ~ /^#/ || $2 == "WormBase"' > out.gff3 | |
| # bedtools sort -i out.gff3 > c_elegans.${PROJECT}.${RELEASE}.annotations.wormbase.gff3 | |
| # bgzip c_elegans.${PROJECT}.${RELEASE}.annotations.wormbase.gff3 | |
| # tabix -p gff c_elegans.${PROJECT}.${RELEASE}.annotations.wormbase.gff3.gz | |
| # Prep N2 PD1074 genome | |
| RELEASE=WS274 | |
| PROJECT=PRJEB28388 # PD1074 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment