Scoreformer: A Surrogate Model For Large-Scale Prediction of Docking Scores
This work addresses the need for efficient high-throughput virtual screening in drug discovery, representing an incremental improvement over recent graph neural network models.
The study tackled the problem of predicting molecular docking scores for drug discovery by developing ScoreFormer, a graph transformer model that achieved competitive performance and a 1.65-fold reduction in inference time compared to existing models.
In this study, we present ScoreFormer, a novel graph transformer model designed to accurately predict molecular docking scores, thereby optimizing high-throughput virtual screening (HTVS) in drug discovery. The architecture integrates Principal Neighborhood Aggregation (PNA) and Learnable Random Walk Positional Encodings (LRWPE), enhancing the model's ability to understand complex molecular structures and their relationship with their respective docking scores. This approach significantly surpasses traditional HTVS methods and recent Graph Neural Network (GNN) models in both recovery and efficiency due to a wider coverage of the chemical space and enhanced performance. Our results demonstrate that ScoreFormer achieves competitive performance in docking score prediction and offers a substantial 1.65-fold reduction in inference time compared to existing models. We evaluated ScoreFormer across multiple datasets under various conditions, confirming its robustness and reliability in identifying potential drug candidates rapidly.