Data Lakehouse to support the development of AI models for predicting patient response to anti-tumor therapies

In the context of the European project KATY on precision medicine, we prototyped a Data Lakehouse by integrating research studies that generated molecular profiling data from cohorts of kidney tumor tissues taken from patients included in drug clinical trials. Indeed, there is currently a lack of a database dedicated to support the development of AI models to help doctors in chosing the best drug for each patient.
The Data Lakehouse architecture, which we have implemented with open source Delta Lake technology, brings together the best features of Data Lake and Data Warehouse.
The Data Lakehouse will allow three types of access for the KATY consortium members:
- the implementation of data analytics approaches to query and visualize molecular and clinical data
- the targeted extraction of data for the training and testing of AI models
- feeding a Knowledge Graph to support the explainability of the predictive models using a priori biological and clinical knowledge.