Raising the Bar on ADMET Prediction with Open Science
- The majority of medicinal chemistry resources are consumed by the complex task of balancing pharmacokinetics with the mitigation of off-target interactions
- At OpenADMET, we seek to model off-target interactions through a systematic, integrated approach that synthesizes three critical pillars: targeted data generation, high-resolution structural insights from X-ray crystallography and cryo-EM, and predictive machine learning
- OpenADMET both encourages and relies upon community collaboration in the form of model and data releases, blog posts, and blind challenges that provide a statistically rigorous comparison of approaches to push the needle forward on ADMET prediction