Drug Candidate Optimization
Optimization of lead candidate properties is the most time consuming and costly preclinical drug discovery process largely due to the lack of, or low accuracy of, in silico predictive models for efficacy, ADME and toxicity properties. The primary drivers of time and cost are the high numbers of compounds needing to be synthesized and tested in a very inefficient process. According to a recent estimate, the average optimization campaign costs $10 million and takes 2 years to complete; and, 15 optimization campaigns are necessary for one FDA-approved drug.
CoRE™ can maximize the efficiency of optimizing compounds by concurrently evaluating desired efficacy, ADME and safety profiles while minimizing adverse effects. Projects to date have shown CoRE™ can reduce the time from lead identification to preclinical as much as 60% and can capture associated cost savings approaching 90% by synthesizing substantially fewer compounds while still meeting optimization criteria and dramatically reducing experimentation.
- Concurrently optimizes multiple candidate properties
- Rapidly returns selections for compound and assay testing
- Efficiently explores potential data hypotheses & tests for spurious correlation
- Notifies when stopping criteria are met
- Results in enriched training data
- Enables informed decision making at every discovery cycle