Department of Computational & Systems Biology, School of Medicine, University of Pittsburgh, 3501 Fifth Avenue, Suite 3064, Biomedical Science Tower 3 (BST3), Pittsburgh, PA, 15260, USA.
J Comput Aided Mol Des. 2019 Jan;33(1):19-34. doi: 10.1007/s10822-018-0133-y. Epub 2018 Jul 10.
We assess the ability of our convolutional neural network (CNN)-based scoring functions to perform several common tasks in the domain of drug discovery. These include correctly identifying ligand poses near and far from the true binding mode when given a set of reference receptors and classifying ligands as active or inactive using structural information. We use the CNN to re-score or refine poses generated using a conventional scoring function, Autodock Vina, and compare the performance of each of these methods to using the conventional scoring function alone. Furthermore, we assess several ways of choosing appropriate reference receptors in the context of the D3R 2017 community benchmarking challenge. We find that our CNN scoring function outperforms Vina on most tasks without requiring manual inspection by a knowledgeable operator, but that the pose prediction target chosen for the challenge, Cathepsin S, was particularly challenging for de novo docking. However, the CNN provided best-in-class performance on several virtual screening tasks, underscoring the relevance of deep learning to the field of drug discovery.
我们评估了基于卷积神经网络 (CNN) 的评分函数在药物发现领域执行几个常见任务的能力。这些任务包括在给定一组参考受体时正确识别靠近和远离真实结合模式的配体构象，以及使用结构信息将配体分类为活性或非活性。我们使用 CNN 重新评分或改进使用传统评分函数（Autodock Vina）生成的构象，并将每种方法的性能与仅使用传统评分函数进行比较。此外，我们评估了在 D3R 2017 社区基准测试挑战的背景下选择合适参考受体的几种方法。我们发现，我们的 CNN 评分函数在大多数任务上都优于 Vina，而无需由有知识的操作员进行手动检查，但为挑战选择的 Cathepsin S 构象预测目标对从头开始对接特别具有挑战性。然而，CNN 在几个虚拟筛选任务中提供了同类最佳的性能，突显了深度学习在药物发现领域的相关性。
