Cafe Variome Central datasets
Fast, Memory-efficient, and Secure Discovery
Café Variome executes queries at a high speed and has very little memory foot-print enabling it to be hosted on small servers.
Apart from discovery, large data files of millions of records can be indexed in a memory-efficient way using the data input pipeline of Café Variome.
Café Variome relies on OIDC providers for authentication. Queries have a bearer token used to authenticate
and authorise data discovery.
Discovery based on semantic similarity
Use of ontology terms in patient data has become more prevalent. Café Variome can work with any health data ontology and can be configured to automatically detect ontology terms in raw data. This enables Café Variome to connect patients to nodes in ontologies. Similarity scores among ontology terms are calculated. Therefore, you can discover similar patients based on phenotypes, diseases, or medicine that they use.