Artificial Intelligence (AI) has the potential to speed up the discovery phase and lower discovery costs significantly. Recent advances in molecular science and machine learning, combined with the availability of powerful cloud computing platforms, are turning this potential into reality. We will discuss an approach that applies AI and machine learning to design, test, and optimize lead molecules rapidly in silico and to suggest what molecules to make next in an ‘active learning’ process to help guide the drug discovery process and optimize R&D output. Active learning is a specialization within Machine Learning in which computation (the ‘virtual’) and experiment (the ‘real’) are combined—allowing scientists to find optimal answers in the most efficient way possible. Molecular modeling methods, such as pharmacophore screening, docking, and physics-based computations incorporate 3D and target-based data can enhance the accuracy of predictions for drug potency, efficacy, and selectivity, while also addressing multi-target effects. The Dassault Systèmes’ 3DEXPERIENCE platform offers tight integration between the virtual and real cycles (V+R). This shortens timelines by reducing turnaround time for laboratory synthesis and testing, while also reducing the number of V+R cycles.
The 3DEXPERIENCE platforms allow users to collaborate in a secure and intuitive manner, independent of time and location. The platform captures the entire drug discovery process; including compound structures, molecular models and simulation, synthesis reactions, objectives, and conclusions. Finally, we will present real-world examples of our customers and partners leveraging the benefits of our integrated AI collaborative platform.