BRCAChallenge · melissacline · Oct 18, 2025 · Oct 18, 2025 · Dec 29, 2025 · Dec 30, 2025
diff --git a/pipeline/Makefile b/pipeline/Makefile
@@ -20,9 +20,9 @@ LUIGI_WORKERS = 8
 SEQ_REPO_DIR_DOCKER := /files/resources/seq_repo
 
 ifndef GENE_CONFIG_FILENAME
-GENE_CONFIG_FILE = /opt/brca-exchange/pipeline/workflow/gene_config_brca_only.txt
+GENE_CONFIG_FILE = /opt/brca-exchange-kb/pipeline/workflow/gene_config_brca_only.txt
 else
-GENE_CONFIG_FILE = /opt/brca-exchange/pipeline/workflow/$(GENE_CONFIG_FILENAME)
+GENE_CONFIG_FILE = /opt/brca-exchange-kb/pipeline/workflow/$(GENE_CONFIG_FILENAME)
 endif
 
 init: ## setup config file
@@ -52,7 +52,7 @@ start-local-uta: ## starting local uta docker container
 
 start-seqrepo-rest-service:
 	[ `docker ps -f name="seqrepo-rest-service" | wc -l` -gt 1 ] || \
-	utilities/lauch_seqrepo.sh
+	utilities/launch_seqrepo.sh
 
 .ONESHELL:
 setup-files: ## setup various directories to run pipeline
@@ -67,7 +67,8 @@ setup-files: ## setup various directories to run pipeline
 setup-lovd: ## setting up LOVD data via pipeline machine, if not running on pipeline machine, as the access is IP restricted. Requires access to main pipeline machine
 	if [ `hostname -s` != "brcaexchange-dev" ]; then
 		mkdir -p $(OUT_DIR)/LOVD
-		ssh brca@brcaexchange-dev.gi.ucsc.edu curl https://databases.lovd.nl/shared/export/BRCA > $(OUT_DIR)/LOVD/BRCA.txt
+		ssh brca@brcaexchange-dev.gi.ucsc.edu curl https://databases.lovd.nl/shared/export/BRCA > $(OUT_DIR)/LOVD/BRCA.txt || \
+		wget https://brcaexchange.org/backend/downloads/BRCA_from_LOVD.2025_11_11.txt -O $(OUT_DIR)/LOVD/BRCA.txt
 	fi
 
 
@@ -81,15 +82,15 @@ COMMON_DOCKER_ARGS = --rm -u `id -u ${USER}`:$(DOCKER_GRP) \
 	-e "DATA_DATE=$(DATA_DATE)" \
 	-e "UTA_DB_URL=$(UTA_DB_URL)" \
 	-e "HGVS_SEQREPO_DIR=$(SEQ_REPO_DIR_DOCKER)/latest" \
-	-e "PYTHONPATH=/opt/brca-exchange/pipeline" \
+	-e "PYTHONPATH=/opt/brca-exchange-kb/pipeline" \
 	--network host \
 	-v $(RESOURCES_DIR):/files/resources \
 	-v $(SEQ_REPO_DIR):$(SEQ_REPO_DIR_DOCKER) \
 	-v $(OUT_DIR):/files/data \
 	-v $(CREDENTIALS_PATH):/opt/luigi_pipeline_credentials.cfg \
 	-v $(PREVIOUS_RELEASE_PATH):/files/previous_release.tar.gz \
 	-v $(RELEASE_NOTES_PATH):/files/release_notes.txt \
-	-v $(CODE_BASE):/opt/brca-exchange \
+	-v $(CODE_BASE):/opt/brca-exchange-kb \
 	-v /var/run/docker.sock:/var/run/docker.sock
 
 download-seqrepo: ## Download seq repo data (fyi, seqrepo pull will skip downloading the latest release if we already have it)
@@ -99,14 +100,14 @@ download-seqrepo: ## Download seq repo data (fyi, seqrepo pull will skip downloa
 	  grep 'most recent seqrepo instance is' | rev | cut -d ' ' -f 1 | rev > $(OUT_DIR)/seqrepo_instance.txt
 
 download-victor-data: ## download data dependency for victor (bayesdel computations). Keeping a separate data version per release. In order to save disk space, e.g. jdupes could be used to create hardlinks
-	docker run $(COMMON_DOCKER_ARGS) -v $(VICTOR_DATA_DIR):/mnt $(PIPELINE_IMAGE) bash -c '/opt/brca-exchange/pipeline/data_merging/bayesdel/download_bayesdel_data_dependencies.sh /mnt/$(DATA_DATE)'
+	docker run $(COMMON_DOCKER_ARGS) -v $(VICTOR_DATA_DIR):/mnt $(PIPELINE_IMAGE) bash -c '/opt/brca-exchange-kb/pipeline/data_merging/bayesdel/download_bayesdel_data_dependencies.sh /mnt/$(DATA_DATE)'
 
 run-pipeline: ## running entire pipeline
 	TS=`date +%Y%m%d_%H%M%S`
 	LOG_FILE=$(LOG_DIR)/pipeline_run_$${TS}.log
 	echo "Log files are in $${LOG_FILE}"
 
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) /opt/brca-exchange/pipeline/docker/run_luigi.sh $(PRIORS_REFERENCES) $(OUT_DIR) $(PRIORS_IMAGE) $(VR_IMAGE) $(LUIGI_ROOT_TASK) $(LUIGI_WORKERS) $(GENE_CONFIG_FILE) ${VICTOR_IMAGE} ${VICTOR_DATA_DIR}/STATIC_DATA $(SEQ_REPO_DIR) > $${LOG_FILE} 2>&1
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) /opt/brca-exchange-kb/pipeline/docker/run_luigi.sh $(PRIORS_REFERENCES) $(OUT_DIR) $(PRIORS_IMAGE) $(VR_IMAGE) $(LUIGI_ROOT_TASK) $(LUIGI_WORKERS) $(GENE_CONFIG_FILE) ${VICTOR_IMAGE} ${VICTOR_DATA_DIR}/STATIC_DATA $(SEQ_REPO_DIR) > $${LOG_FILE} 2>&1
 
 
 run-interactive: ## starting docker container in interactive mode
@@ -121,7 +122,7 @@ ifeq ($(firstword),$(filter $(firstword), run-task, force-run-task, clean-files-
   $(eval $(RUN_ARGS):;@:)
 endif
 
-RUN_TASK_CMD := docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) /opt/brca-exchange/pipeline/docker/run_luigi.sh $(PRIORS_REFERENCES) $(OUT_DIR) $(PRIORS_IMAGE) $(VR_IMAGE)
+RUN_TASK_CMD := docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) /opt/brca-exchange-kb/pipeline/docker/run_luigi.sh $(PRIORS_REFERENCES) $(OUT_DIR) $(PRIORS_IMAGE) $(VR_IMAGE)
 
 run-task: ## Running a specific task
 	$(RUN_TASK_CMD) $(RUN_ARGS) $(LUIGI_WORKERS) $(GENE_CONFIG_FILE) ${VICTOR_IMAGE} ${VICTOR_DATA_DIR}/STATIC_DATA $(SEQ_REPO_DIR)
@@ -130,26 +131,26 @@ PIPELINE_ARGS := --PipelineParams-output-dir /files/data/output --PipelineParams
 
 force-run-task: ## Running a specific task (deleting its dependencies first)
 	## TODO: should this command use RUN_ARGS command twice?
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange/pipeline/workflow && python prune_output_files.py CompileVCFFiles $(RUN_ARGS) $(RUN_ARGS) $(PIPELINE_ARGS)'
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange-kb/pipeline/workflow && python prune_output_files.py CompileVCFFiles $(RUN_ARGS) $(RUN_ARGS) $(PIPELINE_ARGS)'
 	$(RUN_TASK_CMD) $(RUN_ARGS) $(LUIGI_WORKERS) $(GENE_CONFIG_FILE) ${VICTOR_IMAGE} ${VICTOR_DATA_DIR}/STATIC_DATA $(SEQ_REPO_DIR)
 
 clean-files-from: ## Delete files generated by tasks on the task path between the given task and $(LUIGI_ROOT_TASK)
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange/pipeline/workflow && python prune_output_files.py CompileVCFFiles $(LUIGI_ROOT_TASK) $(RUN_ARGS) $(PIPELINE_ARGS)'
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange-kb/pipeline/workflow && python prune_output_files.py CompileVCFFiles $(LUIGI_ROOT_TASK) $(RUN_ARGS) $(PIPELINE_ARGS)'
 
 show-luigi-graph: ## print some representation of the luigi compute graph on the console
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange/pipeline/workflow && PYTHONPATH="/opt/brca-exchange/pipeline:/opt/brca-exchange/pipeline/workflow" luigi-deps-tree --module CompileVCFFiles $(PIPELINE_ARGS) $(LUIGI_ROOT_TASK) | sed -E "s/([^{])\{.*\}([^}])/\1/g" '
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange-kb/pipeline/workflow && PYTHONPATH="/opt/brca-exchange-kb/pipeline:/opt/brca-exchange-kb/pipeline/workflow" luigi-deps-tree --module CompileVCFFiles $(PIPELINE_ARGS) $(LUIGI_ROOT_TASK) | sed -E "s/([^{])\{.*\}([^}])/\1/g" '
 
 test: ## Running pipeline unit tests
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange/pipeline/data && bash getdata && cd /opt/brca-exchange/pipeline && pytest --ignore=splicing/'
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange-kb/pipeline/data && bash getdata && cd /opt/brca-exchange-kb/pipeline && pytest --ignore=splicing/'
 
 test-coverage: ## Running pipeline unit tests with coverage information
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange/pipeline/data && bash getdata && cd /opt/brca-exchange/pipeline && pytest --cov --ignore=splicing/ && coverage html --include="/opt/brca-exchange/pipeline/*" --omit="*/test_*"'
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) bash -c 'cd /opt/brca-exchange-kb/pipeline/data && bash getdata && cd /opt/brca-exchange-kb/pipeline && pytest --cov --ignore=splicing/ && coverage html --include="/opt/brca-exchange-kb/pipeline/*" --omit="*/test_*"'
 
 
 build-release: checkout build-docker setup-files setup-lovd download-resources download-seqrepo start-local-uta start-seqrepo-rest-service run-pipeline variants-by-source ## create new data release
 
 variants-by-source: ## postprocessing: compute statistics for changes with respect to the last release
-	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) python /opt/brca-exchange/pipeline/utilities/variantsBySource.py  -i /files/data/output/release/built_with_change_types.tsv -c true
+	docker run $(COMMON_DOCKER_ARGS) $(PIPELINE_IMAGE) python /opt/brca-exchange-kb/pipeline/utilities/variantsBySource.py  -i /files/data/output/release/built_with_change_types.tsv -c true
 
 prune-release-notes-output: ## postprocessing: removes some files, s.t. luigi tasks can be triggered to include updated release notes into release archive
 	make clean-files-from GenerateReleaseNotes

diff --git a/pipeline/docker/Dockerfile b/pipeline/docker/Dockerfile
@@ -1,5 +1,4 @@
-FROM python:3.9-bullseye
-
+FROM python:3.12-bookworm
 RUN chmod 1777 /tmp
 
 RUN apt-get update && apt-get install -y \
@@ -11,15 +10,12 @@ RUN apt-get update && apt-get install -y \
     libbz2-dev \
     liblzma-dev \
     pkg-config \
-    python3 \
-    python3-pip \
     python3-gdbm \
-    python-lzo \
     rsync \
     vim \
     wget \
     zlib1g-dev \
-    netcat
+    netcat-openbsd
 
 # Get the Docker binary
 RUN curl -fsSL get.docker.com -o get-docker.sh \
@@ -31,12 +27,16 @@ COPY pipeline/requirements.txt .
 COPY test-requirements.txt .
 
 # pip 20.3+ uses strict dependency resolver that causes biocommons/bioutils and hgvs/ipython errors
-RUN pip install pip==24.0
+# Using pip 24.3.1 for Python 3.12 compatibility
+RUN pip install --upgrade pip==24.3.1
+
+# install six first as it's a fundamental dependency for many packages
+RUN pip install $(grep "^six" requirements.txt)
 
 # install numpy first to avoid issues with bio python and bx-python (see also https://github.com/LUMC/vep2lovd/issues/1)
-RUN pip install $(grep numpy requirements.txt)
+RUN pip install $(grep "^numpy" requirements.txt)
 
-RUN pip install $(grep -i cython requirements.txt)
+RUN pip install $(grep "^cython" requirements.txt)
 RUN pip install -r requirements.txt -r test-requirements.txt
 
 # install vcf tools
@@ -64,13 +64,13 @@ RUN mkdir -p $res /files/data && chmod -R o+rwx /files
 RUN rm -r  /root/.cache
 
 ARG FORCE_REBUILD=0
-COPY . /opt/brca-exchange
+COPY . /opt/brca-exchange-kb
 
 ENV LUIGI_CONFIG_PATH="/opt/luigi_pipeline_credentials.cfg"
 
 ARG IS_GIT_DIRTY="False"
 ARG GIT_COMMIT=""
 LABEL GitCommit=$GIT_COMMIT IsGitDirty=$IS_GIT_DIRTY
 
-CMD ["/opt/brca-exchange/pipeline/docker/run_luigi.sh"]
+CMD ["/opt/brca-exchange-kb/pipeline/docker/run_luigi.sh"]
 
diff --git a/pipeline/docker/reproducibility/README.md b/pipeline/docker/reproducibility/README.md
@@ -7,6 +7,6 @@ The pipeline consists of 2 stages where the first one is to normalize the data f
 ## Reproducing Merging Stage
 
 1. Make sure you have docker installed on your system 
-2. Copy and run [this script](https://github.com/BRCAChallenge/brca-exchange/blob/master/pipeline/docker/reproducibility/reproduce_merging.sh): 
+2. Copy and run [this script](https://github.com/BRCAChallenge/brca-exchange-kb/blob/master/pipeline/docker/reproducibility/reproduce_merging.sh): 
    It will download necessary release archives, some auxiliary data and run the docker image of the merging part.
 3. If everything went well, the script will output a path were the newly generated release archive can be found.
diff --git a/pipeline/docker/run_luigi.sh b/pipeline/docker/run_luigi.sh
@@ -30,15 +30,15 @@ PREVIOUS_RELEASE_TAR=/files/previous_release.tar.gz
 
 RELEASE_NOTES=/files/release_notes.txt
 
-CODE_MNT=$(mount | grep /opt/brca-exchange)
+CODE_MNT=$(mount | grep /opt/brca-exchange-kb)
 [ -z "${CODE_MNT}" ] || echo "WARNING: BRCA Code base mounted from host file system"
 
-cd /opt/brca-exchange
+cd /opt/brca-exchange-kb
 
 echo "Running brca exchange pipeline:"
 echo "Git hash: $(git log | head -n 1)"
 
-cd /opt/brca-exchange/pipeline/workflow
+cd /opt/brca-exchange-kb/pipeline/workflow
 
 echo "Attempting to run task ${LUIGI_TASK}"
 python -m luigi --logging-conf-file luigi_log_configuration.conf --module CompileVCFFiles ${LUIGI_TASK} \

diff --git a/pipeline/pipeline_running/brca_pipeline_cfg.mk.j2 b/pipeline/pipeline_running/brca_pipeline_cfg.mk.j2
@@ -19,12 +19,6 @@ PREVIOUS_RELEASE_DIR := {{ PREVIOUS_RELEASE_DIR }}
 SEQ_REPO_DIR := {{ SEQ_REPO_DIR }}
 HGVS_SEQREPO_DIR := {{ SEQ_REPO_DIR }}
 
-{% set VICTOR_DATA_DIR = VICTOR_DATA_DIR|default("/data/victor") %}
-VICTOR_DATA_DIR := {{ VICTOR_DATA_DIR }}
-
-{% set VICTOR_IMAGE_DEFAULT_TAG = "0.1" %}
-VICTOR_IMAGE := {{ VICTOR_IMAGE | default("brcachallenge/victor:" + VICTOR_IMAGE_DEFAULT_TAG) }}
-
 # path to release notes
 RELEASE_NOTES_PATH := {{ RELEASE_NOTES_PATH | default(WORK_DIR + "/release_notes_" + RELEASE_TAG + ".txt") }}
 
@@ -33,7 +27,7 @@ OUT_DIR := {{ OUT_DIR | default(WORK_DIR + "/data_out") }}
 
 CODE_BASE := {{ CODE_BASE|default("../../..") }}
 GIT_COMMIT := {{ GIT_COMMIT|default("master") }}
-BRCA_GIT_REPO := {{ BRCA_GIT_REPO|default("https://github.com/BRCAChallenge/brca-exchange.git") }}
+BRCA_GIT_REPO := {{ BRCA_GIT_REPO|default("https://github.com/BRCAChallenge/brca-exchange-kb.git") }}
 
 PIPELINE_IMAGE := {{ PIPELINE_IMAGE | default("brcachallenge/brca-exchange-pipeline:" + RELEASE_TAG) }}
 RESOURCES_DIR := {{ RESOURCES_DIR|default(WORK_DIR + "/resources") }}
@@ -51,16 +45,16 @@ VR_IMAGE := {{ VR_IMAGE | default("brcachallenge/append-vr-ids:" + VR_IMAGE_DEFA
 
 ## UTA configurations
 
-{% set UTA_RELEASE_DATE = UTA_RELEASE_DATE|default("20210129b") %}
+{% set UTA_RELEASE_DATE = UTA_RELEASE_DATE|default("20241220") %}
 UTA_RELEASE_DATE := {{ UTA_RELEASE_DATE }}
 UTA_DOCKER_IMAGE := {{ UTA_DOCKER_IMAGE | default("biocommons/uta:uta_" + UTA_RELEASE_DATE) }}
 UTA_CONTAINER := {{ UTA_CONTAINER | default("uta_" + UTA_RELEASE_DATE) }}
-{% set UTA_PG_PW = brca_2024 %}
+{% set UTA_PG_PW = UTA_PG_PW | default("POSTGRES_PASSWORD=uta_password") %}
 UTA_PG_PW := {{ UTA_PG_PW }}
 {% set UTA_PORT =  UTA_PORT | default("50828")  %}
 UTA_PORT := {{ UTA_PORT }}
 UTA_DB_URL := {{ "postgresql://anonymous@localhost:" + UTA_PORT + "/uta/uta_" + UTA_RELEASE_DATE }}
-{% set UTA_VOLUME = UTA_VOLUME | default("uta-" + UTA_RELEASE_DATE) %}
+{% set UTA_VOLUME = UTA_VOLUME | default("uta_vol") %}
 UTA_VOLUME := {{ UTA_VOLUME }}