HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery

TL;DR

HydraScreen introduces a deep learning framework using 3D CNNs for structure-based drug discovery, demonstrating high accuracy and generalization across unseen proteins and ligands, with interpretability features.

Contribution

The paper presents HydraScreen, a novel 3D CNN-based pipeline for robust, interpretable, and generalizable structure-based drug screening and lead optimization.

Findings

Achieves top-tier affinity and pose prediction results.

Effectively generalizes to unseen proteins and ligands.

Provides a user-friendly GUI and API for practical use.

Abstract

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.