Running locally

NodeNormalizer can be started locally using Docker Compose:

docker compose -f docker-compose.yml up --build

Then navigate to http://localhost:8080/docs to see available endpoints.

Loading Data

Loading the test data is quick & easy using Docker Exec for both compendia & conflation files:

docker container exec -it node-norm python node_normalizer/load_compendium.py -c tests/resources/Cell.txt -c tests/resources/Disease.txt -c tests/resources/Gene.txt -c tests/resources/Protein.txt -r redis_config.yaml
docker container exec -it node-norm python node_normalizer/load_conflation.py -c tests/resources/GeneProtein.txt -s gene_protein -r redis_config.yaml

Note that the dataset for Node normalization is quite large and 256Gb of memory and disk space should be made available to the Redis instance to ensure proper loading of the all compendia files.