Proactive health solutions require that diseases can be identified, diagnosed, and treated efficiently and effectively. In the U.S., diagnosis of a chronic disease can take, on average, 2.5-5 years. Moreover, in the drug development process, more than 86% of candidate therapies fail during phase 1 clinical trials after expensive and lengthy preclinical testing. Computational models that can infer and explain the cascade of cause-and-effect relationships that a therapy or small molecule might have across a whole biological system have the potential to dramatically reduce false discovery rates and accelerate diagnosis and adoption of new therapies. The Platform for CausaL Understanding of InteRcellular and IntRacellular Interactions (PLURRI) aims to integrate state-of-the-art artificial intelligence (AI) models into a holistic causal inferencing engine that can predict cause-and-effect relationships and guide researchers on which early biomarkers and therapies are most likely to succeed with further experimentation.