From 20f7487951ce7c0945786d38db6ade83d949201f Mon Sep 17 00:00:00 2001 From: jkgoodrich <33063077+jkgoodrich@users.noreply.github.com> Date: Tue, 30 Sep 2025 08:30:41 -0600 Subject: [PATCH 1/3] add vep 115 to the vep_context options --- gnomad/resources/grch38/reference_data.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/gnomad/resources/grch38/reference_data.py b/gnomad/resources/grch38/reference_data.py index 25040940f..f2edd0a39 100644 --- a/gnomad/resources/grch38/reference_data.py +++ b/gnomad/resources/grch38/reference_data.py @@ -156,6 +156,9 @@ def _import_ensembl_interval(path) -> hl.Table: "105": GnomadPublicTableResource( path="gs://gnomad-public-requester-pays/resources/context/grch38_context_vep_annotated.v105.ht", ), + "115": GnomadPublicTableResource( + path="gs://gnomad-public-requester-pays/resources/context/grch38_context_vep_annotated.v115.ht", + ), }, ) From e5cacea6a09443235585f4ef8e771687af93b0a8 Mon Sep 17 00:00:00 2001 From: jkgoodrich <33063077+jkgoodrich@users.noreply.github.com> Date: Tue, 30 Sep 2025 14:21:15 -0600 Subject: [PATCH 2/3] Add VEP 115 init --- init_scripts/vep115-init.sh | 101 ++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 init_scripts/vep115-init.sh diff --git a/init_scripts/vep115-init.sh b/init_scripts/vep115-init.sh new file mode 100644 index 000000000..3aeae3d05 --- /dev/null +++ b/init_scripts/vep115-init.sh @@ -0,0 +1,101 @@ +#!/bin/bash + +export PROJECT="$(gcloud config get-value project)" +export VEP_CONFIG_PATH="$(/usr/share/google/get_metadata_value attributes/VEP_CONFIG_PATH)" +export VEP_REPLICATE="$(/usr/share/google/get_metadata_value attributes/VEP_REPLICATE)" +export VEP_BUCKET=hail-${VEP_REPLICATE}-vep +export ASSEMBLY=GRCh38 +export VEP_DOCKER_IMAGE=us-central1-docker.pkg.dev/broad-mpg-gnomad/images/vep115 + +mkdir -p /vep_data/loftee_data +mkdir -p /vep_data/homo_sapiens + +# Install docker +apt-get update +apt-get -y install \ + apt-transport-https \ + ca-certificates \ + curl \ + gnupg2 \ + software-properties-common \ + tabix +curl -fsSL https://download.docker.com/linux/debian/gpg | sudo apt-key add - +sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/debian $(lsb_release -cs) stable" +apt-get update +apt-get install -y --allow-unauthenticated docker-ce + + +gsutil -u ${PROJECT} cat gs://${VEP_BUCKET}/loftee-beta/${ASSEMBLY}.tar | tar -xf - -C /vep_data/ + +docker pull ${VEP_DOCKER_IMAGE} + + +################################################################ +# Added stuff +################################################################ + +# GCS copy of https://ftp.ebi.ac.uk/ensemblorg/pub/release-115/variation/indexed_vep_cache/homo_sapiens_merged_vep_115_GRCh38.tar.gz +gsutil -u $PROJECT cat gs://gcp-public-data--gnomad/resources/vep/v115/homo_sapiens_merged_vep_115_GRCh38.tar.gz | tar -xzf - -C /vep_data + + +# FASTA file from Hail's VEP 95 data +gsutil -u "$PROJECT" cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz /vep_data/ +gsutil -u $PROJECT cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz.fai /vep_data/ +gsutil -u $PROJECT cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz.gzi /vep_data/ + +# Create config file. +cat > /vep_data/vep115-GRCh38.json </vep.c < +#include + +int +main(int argc, char *const argv[]) { + if (setuid(geteuid())) + perror( "setuid" ); + + execv("/vep.sh", argv); + return 0; +} +EOF +gcc -Wall -Werror -O2 /vep.c -o /vep +chmod u+s /vep + +cat >/vep.sh < Date: Thu, 2 Oct 2025 13:46:13 -0600 Subject: [PATCH 3/3] Update vep115 init after testing --- init_scripts/vep115-init.sh | 43 ++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 15 deletions(-) diff --git a/init_scripts/vep115-init.sh b/init_scripts/vep115-init.sh index 3aeae3d05..492ee7f3b 100644 --- a/init_scripts/vep115-init.sh +++ b/init_scripts/vep115-init.sh @@ -7,9 +7,6 @@ export VEP_BUCKET=hail-${VEP_REPLICATE}-vep export ASSEMBLY=GRCh38 export VEP_DOCKER_IMAGE=us-central1-docker.pkg.dev/broad-mpg-gnomad/images/vep115 -mkdir -p /vep_data/loftee_data -mkdir -p /vep_data/homo_sapiens - # Install docker apt-get update apt-get -y install \ @@ -25,11 +22,11 @@ apt-get update apt-get install -y --allow-unauthenticated docker-ce -gsutil -u ${PROJECT} cat gs://${VEP_BUCKET}/loftee-beta/${ASSEMBLY}.tar | tar -xf - -C /vep_data/ +mkdir -p /vep_data/loftee_data +gsutil -u ${PROJECT} cat gs://${VEP_BUCKET}/loftee-beta/${ASSEMBLY}.tar | tar -xf - -C /vep_data/loftee_data & docker pull ${VEP_DOCKER_IMAGE} - ################################################################ # Added stuff ################################################################ @@ -38,7 +35,7 @@ docker pull ${VEP_DOCKER_IMAGE} gsutil -u $PROJECT cat gs://gcp-public-data--gnomad/resources/vep/v115/homo_sapiens_merged_vep_115_GRCh38.tar.gz | tar -xzf - -C /vep_data -# FASTA file from Hail's VEP 95 data +# FASTA file for GRCh38. gsutil -u "$PROJECT" cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz /vep_data/ gsutil -u $PROJECT cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz.fai /vep_data/ gsutil -u $PROJECT cp gs://gcp-public-data--gnomad/resources/vep/Homo_sapiens.GRCh38.dna.toplevel.fa.gz.gzi /vep_data/ @@ -49,23 +46,39 @@ cat > /vep_data/vep115-GRCh38.json <