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.

本研究提出了一种新颖的图形变换器模型 ScoreFormer，用于准确预测分子对接得分，从而优化药物发现中的高通量虚拟筛选。该模型通过集成 Principal Neighborhood Aggregation（PNA）和 Learnable Random Walk Positional Encodings（LRWPE）来增强对复杂分子结构及其与对应对接得分的关系的理解能力。这种方法在化学空间的覆盖范围和性能提升方面显著超过传统的高通量虚拟筛选方法和最新的图神经网络模型，具有竞争力的对接得分预测性能，并相较于现有模型，推理时间减少了 1.65 倍，我们通过在多个数据集下进行评估，在各种条件下验证了 ScoreFormer 的鲁棒性和可靠性，能够快速识别潜在的药物候选物。

Scoreformer：一种大规模对接得分预测的代理模型

Scoreformer: A Surrogate Model For Large-Scale Prediction of Docking  Scores

Chemical space is so large that brute force searches for new interesting
molecules are infeasible. High-throughput virtual screening via computer
cluster simulations can speed up the discovery process by collecting very large
amounts of data in parallel, e.g., up to hundreds or thousands of parallel
measurements. Bayesian optimization (BO) can produce additional acceleration by
sequentially identifying the most useful simulations or experiments to be
performed next. However, current BO methods cannot scale to the large numbers
of parallel measurements and the massive libraries of molecules currently used
in high-throughput screening. Here, we propose a scalable solution based on a
parallel and distributed implementation of Thompson sampling (PDTS). We show
that, in small scale problems, PDTS performs similarly as parallel expected
improvement (EI), a batch version of the most widely used BO heuristic.
Additionally, in settings where parallel EI does not scale, PDTS outperforms
other scalable baselines such as a greedy search, $\epsilon$-greedy approaches
and a random search method. These results show that PDTS is a successful
solution for large-scale parallel BO.

为了解决高吞吐量筛选中大规模问题的局限性，该研究提出了一种基于并行和分布式的 Thompson 采样的可伸缩解决方案，实现了大规模并行贝叶斯优化。结果表明，该方法在大规模问题中表现良好，是大规模并行贝叶斯优化的有效解决方案。