HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery
This addresses the need for generalizable and interpretable scoring functions in drug discovery for researchers, though it appears incremental as it builds on existing 3D convolutional neural networks and benchmarks.
The paper tackled the problem of robust machine-learning-accelerated drug discovery by proposing HydraScreen, a deep-learning approach for structure-based drug design, achieving top-tier results in affinity and pose prediction on the CASF 2016 benchmark with Pearson's r = 0.86, RMSE = 1.15, and Top-1 = 0.95.
We propose HydraScreen, a deep-learning approach that aims to provide a framework for more robust machine-learning-accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network, designed for the effective representation of molecular structures and interactions in protein-ligand binding. We design an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assess our approach using established public benchmarks based on the CASF 2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). Furthermore, we utilize a novel interaction profiling approach to identify potential biases in the model and dataset to boost interpretability and support the unbiased nature of our method. Finally, we showcase HydraScreen's capacity to generalize across unseen proteins and ligands, offering directions for future development of robust machine learning scoring functions. HydraScreen (accessible at https://hydrascreen.ro5.ai) provides a user-friendly GUI and a public API, facilitating easy assessment of individual protein-ligand complexes.