edge machine learning techniques from three complementary informatics technologies: Supervised Learning, Transfer Learning and Active Learning, to efficiently solve multi-parameter optimization problems in a series of discrete discovery cycles.

CoRE’s unique capability to effect simultaneous co-optimization of the entire efficacy, safety and off-target effects property profile is vastly more efficient than the standard approach and greatly accelerates discovery.

Based on over 20 industry collaborations, it is very realistic to expect, at a minimum, CoRE™ can reduce preclinical attrition 5%, preclinical costs 20% and lead optimization costs 40%. When these three parameters were adjusted in a recent assessment of pharmaceutical R&D productivity (Paul et al. 2010 ) to capture the effects of using CoRE™, this translated to capitalized costs savings of $238 million and out-of-pocket cost reductions of $88 million. Additionally, CoRE™ can quickly yield significant reductions in time which may be instrumental in gaining first mover IP advantage, particularly with novel targets.

The Revolutionary CoRE™ Platform Changes How Predictive In Silico Models Are Generated and Deployed, and How Highly Accurate Predictive Models Enable and Accelerate Efficient Drug Discovery. The net result is a game changing competitive advantage.