Skip to main content
QUICK REVIEW

[论文解读] A Point Cloud-Based Deep Learning Strategy for Protein-Ligand Binding Affinity Prediction

Yeji Wang, Shuo Wu|arXiv (Cornell University)|Jul 9, 2021
Computational Drug Discovery Methods参考文献 14被引用 6
一句话总结

本研究提出了一种新颖的深度学习方法,利用来自PDBbind-2016数据的3D点云预测蛋白质-配体结合亲和力。通过将PointNet和PointTransformer架构应用于将蛋白质-配体复合物表示为点云,该方法分别实现了皮尔逊相关系数R = 0.831和R = 0.859,表现出与最先进模型相当的强劲性能。

ABSTRACT

There is great interest to develop artificial intelligence-based protein-ligand affinity models due to their immense applications in drug discovery. In this paper, PointNet and PointTransformer, two pointwise multi-layer perceptrons have been applied for protein-ligand affinity prediction for the first time. Three-dimensional point clouds could be rapidly generated from the data sets in PDBbind-2016, which contain 3 772 and 11 327 individual point clouds derived from the refined or/and general sets, respectively. These point clouds were used to train PointNet or PointTransformer, resulting in protein-ligand affinity prediction models with Pearson correlation coefficients R = 0.831 or 0.859 from the larger point clouds respectively, based on the CASF-2016 benchmark test. The analysis of the parameters suggests that the two deep learning models were capable to learn many interactions between proteins and their ligands, and these key atoms for the interaction could be visualized in point clouds. The protein-ligand interaction features learned by PointTransformer could be further adapted for the XGBoost-based machine learning algorithm, resulting in prediction models with an average Rp of 0.831, which is on par with the state-of-the-art machine learning models based on PDBbind database. These results suggest that point clouds derived from the PDBbind datasets are useful to evaluate the performance of 3D point clouds-centered deep learning algorithms, which could learn critical protein-ligand interactions from natural evolution or medicinal chemistry and have wide applications in studying protein-ligand interactions.

研究动机与目标

  • 开发一种基于分子复合物3D点云表示的蛋白质-配体结合亲和力预测深度学习框架。
  • 评估基于点云的模型在捕捉关键蛋白质-配体相互作用方面的有效性。
  • 比较PointNet和PointTransformer在大规模PDBbind-2016数据集上的性能表现。
  • 探索将深度学习模型学习到的特征与XGBoost等传统机器学习模型结合,以提升预测性能。

提出的方法

  • 使用原子坐标将PDBbind-2016数据库中的蛋白质-配体复合物转换为3D点云。
  • 应用PointNet和PointTransformer两种基于点的多层感知机模型,处理3D点云数据以实现端到端的特征学习。
  • 模型直接从点云中编码的几何和化学特征预测结合亲和力(pKd/pKi)。
  • PointTransformer中的注意力机制使模型能够聚焦于关键的相互作用原子,从而提升特征表示能力。
  • 将PointTransformer学习到的特征进一步用作基于XGBoost的机器学习模型的输入,以增强预测性能。
  • 通过CASF-2016基准进行框架评估,确保与最先进方法的一致性。

实验结果

研究问题

  • RQ13D点云表示能否有效编码蛋白质-配体相互作用特征以实现结合亲和力预测?
  • RQ2PointNet和PointTransformer在从点云数据中学习有意义的空间与化学模式方面表现如何?
  • RQ3PointTransformer中的注意力机制在多大程度上能够突出显示蛋白质-配体复合物中具有生物学意义的相互作用原子?
  • RQ4深度学习模型学习到的特征在多大程度上可有效传递给XGBoost等传统梯度提升模型以提升性能?
  • RQ5在CASF-2016基准上,所提出方法与现有最先进模型相比,在预测准确性方面表现如何?

主要发现

  • 基于PointNet的模型在CASF-2016基准上实现了皮尔逊相关系数R = 0.831,表现出强大的预测能力。
  • 基于PointTransformer的模型优于PointNet,达到R = 0.859,表明其在从3D点云中学习特征方面具有更优性能。
  • PointTransformer中的注意力机制成功突出了参与蛋白质-配体相互作用的关键原子,实现了可解释的特征可视化。
  • 当与XGBoost结合时,PointTransformer的特征实现了平均预测性能Rp = 0.831,与最先进模型相当。
  • 本研究证实,从PDBbind数据中提取的点云对训练能够捕捉进化和药物相关相互作用的3D深度学习模型具有显著有效性。
  • 结果验证了基于点云的深度学习在药物发现中研究蛋白质-配体相互作用方面的实用性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。