What information do I need to justify my drug discovery software renewal?
Justifying software renewal requires more than highlighting features; you need quantifiable ROI data that resonates with budget holders. Whether it’s…
Abstract
Computational approaches for binding affinity prediction are most frequently demonstrated through cross-validation within a series of molecules or through performance shown on a blinded test set. Here, we show how such a system performs in an iterative, temporal lead optimisation exercise. A series of gyrase inhibitors with known synthetic order formed the set of molecules that could be selected for “synthesis.” Beginning with a small number of molecules, based only on structures and activities, a model was constructed. Compound selection was done computationally, each time making five selections based on confident predictions of high activity and five selections based on a quantitative measure of three-dimensional structural novelty. Compound selection was followed by model refinement using the new data. Iterative computational candidate selection produced rapid improvements in selected compound activity, and incorporation of explicitly novel compounds uncovered much more diverse active inhibitors than strategies lacking active novelty selection.
More publications to browse
What training and support can I expect as a StarDrop customer?
Set up for success with hands-on training sessions We start with dedicated training sessions where you and your team get…
Physical Parameter Estimation vs. Pure Machine-Learning for Drug Design
Nearly all computational methods in the CADD field depend on parameters whose values are derived from various types of experimental…
