arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.12995cs.LGcs.AI
收藏

提升低数据场景下3D结合亲和力模型的泛化能力

Improving generalisability of 3D binding affinity models in low data regimes

Exscientia(Exscientia公司)

Julia Buhmann, Ward Haddadin, Lukáš Pravda, Alan Bilsland, Hagen Triendl

AI总结:

针对低数据场景下3D结合亲和力模型泛化能力不足的问题,提出PDBBind新数据划分,证明3D全局模型优于局部模型,并通过量子力学监督预训练、小分子扩散无监督预训练及显式建模氢原子提升GNN性能。

摘要:

预测蛋白质-配体结合亲和力是计算机辅助药物设计的重要组成部分。然而,具备泛化能力且性能优异的全局结合亲和力模型仍然难以实现,特别是在低数据场景下。尽管模型架构不断演进,但当前的基准测试并不适合探究3D结合亲和力模型的泛化能力。此外,诸如GNN等3D全局架构未能达到性能预期。为了研究这些问题,我们引入了PDBBind数据集的一种新划分方法,最小化训练集和测试集之间的相似性泄漏,并允许在各种模型架构之间进行公平直接的比较。在这种低相似性划分上,我们证明总体而言,在低数据场景下3D全局模型优于蛋白质特定的局部模型。我们还证明GNN的性能得益于三项创新贡献:通过量子力学数据进行监督预训练,通过小分子扩散进行无监督预训练,以及在输入图中显式建模氢原子。我们相信这项工作引入了有前景的新方法,以释放GNN架构在结合亲和力建模方面的潜力。

英文摘要:

Predicting protein-ligand binding affinity is an essential part of computer-aided drug design. However, generalisable and performant global binding affinity models remain elusive, particularly in low data regimes. Despite the evolution of model architectures, current benchmarks are not well-suited to probe the generalisability of 3D binding affinity models. Furthermore, 3D global architectures such as GNNs have not lived up to performance expectations. To investigate these issues, we introduce a novel split of the PDBBind dataset, minimizing similarity leakage between train and test sets and allowing for a fair and direct comparison between various model architectures. On this low similarity split, we demonstrate that, in general, 3D global models are superior to protein-specific local models in low data regimes. We also demonstrate that the performance of GNNs benefits from three novel contributions: supervised pre-training via quantum mechanical data, unsupervised pre-training via small molecule diffusion, and explicitly modeling hydrogen atoms in the input graph. We believe that this work introduces promising new approaches to unlock the potential of GNN architectures for binding affinity modelling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑