School of Computer Science and Technology, Soochow University, Suzhou 215006, China.
Province Key Lab for Information Processing Technologies, Soochow University, Suzhou 215006, China.
Bioinformatics. 2023 Feb 3;39(2). doi: 10.1093/bioinformatics/btad049.
Accurate and rapid prediction of protein-ligand binding affinity is a great challenge currently encountered in drug discovery. Recent advances have manifested a promising alternative in applying deep learning-based computational approaches for accurately quantifying binding affinity. The structure complementarity between protein-binding pocket and ligand has a great effect on the binding strength between a protein and a ligand, but most of existing deep learning approaches usually extracted the features of pocket and ligand by these two detached modules.
In this work, a new deep learning approach based on the cross-attention mechanism named CAPLA was developed for improved prediction of protein-ligand binding affinity by learning features from sequence-level information of both protein and ligand. Specifically, CAPLA employs the cross-attention mechanism to capture the mutual effect of protein-binding pocket and ligand. We evaluated the performance of our proposed CAPLA on comprehensive benchmarking experiments on binding affinity prediction, demonstrating the superior performance of CAPLA over state-of-the-art baseline approaches. Moreover, we provided the interpretability for CAPLA to uncover critical functional residues that contribute most to the binding affinity through the analysis of the attention scores generated by the cross-attention mechanism. Consequently, these results indicate that CAPLA is an effective approach for binding affinity prediction and may contribute to useful help for further consequent applications.
The source code of the method along with trained models is freely available at https://github.com/lennylv/CAPLA.
Supplementary data are available at Bioinformatics online.
准确快速地预测蛋白质-配体结合亲和力是药物发现中目前面临的一大挑战。最近的进展表明，应用基于深度学习的计算方法来准确量化结合亲和力是一种很有前途的替代方法。蛋白质结合口袋和配体之间的结构互补性对蛋白质和配体之间的结合强度有很大的影响，但大多数现有的深度学习方法通常通过这两个分离的模块提取口袋和配体的特征。
在这项工作中，我们开发了一种基于交叉注意力机制的新的深度学习方法 CAPLA，通过学习蛋白质和配体序列水平信息的特征，来提高蛋白质-配体结合亲和力的预测。具体来说，CAPLA 采用交叉注意力机制来捕捉蛋白质结合口袋和配体之间的相互作用。我们在结合亲和力预测的综合基准实验中评估了我们提出的 CAPLA 的性能，证明了 CAPLA 优于最先进的基线方法的性能。此外，我们通过分析交叉注意力机制生成的注意力得分，为 CAPLA 提供了可解释性，以揭示对结合亲和力贡献最大的关键功能残基。因此，这些结果表明 CAPLA 是一种有效的结合亲和力预测方法，可以为进一步的后续应用提供有用的帮助。
该方法的源代码和训练模型可在 https://github.com/lennylv/CAPLA 上免费获得。
补充数据可在生物信息学在线获得。
