<br>从蛋白质到配体：解码用于结合亲和力预测的深度学习方法,Journal of Chemical Information and Modeling

当前位置： X-MOL 学术 › J. Chem. Inf. Model. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

从蛋白质到配体：解码用于结合亲和力预测的深度学习方法
Journal of Chemical Information and Modeling ( IF 5.6 ) Pub Date : 2023-11-20 , DOI: 10.1021/acs.jcim.3c01208
Rohan Gorantla _{1,

2} , Alžbeta Kubincová ₃ , Andrea Y Weiße _{1,

4} , Antonia S J S Mey ₂

Affiliation

准确的计算机模拟预测蛋白质-配体结合亲和力在药物发现的早期阶段非常重要。基于深度学习的方法是存在的，但尚未取代更传统的方法，例如千兆对接，很大程度上是因为它们缺乏通用性。为了提高普遍性，我们需要了解这些模型从输入蛋白质和配体数据中学到了什么。我们系统地研究了基于序列的深度学习框架，以评估蛋白质和配体编码对预测常用激酶数据集的结合亲和力的影响。使用从序列获得的基于卷积神经网络的编码和富含接触图结构信息的基于图神经网络的编码来研究蛋白质的作用。基于配体的编码是从图神经网络生成的。我们通过随机化节点和边缘属性来测试不同的配体扰动。对于蛋白质，我们使用 3 种不同的蛋白质接触生成方法（AlphaFold2、Pconsc4 和 ESM-1b），并将它们与随机对照进行比较。我们的研究表明，蛋白质编码不会对结合预测产生实质性影响，在研究指标（一致性指数、Pearson R Spearman Rank 和 RMSE）中，KIBA 的结合亲和力没有统计学上的显着差异。具有随机配体和随机配体节点属性的配体编码存在显着差异，这表明学习任务对配体数据的依赖更大。使用不同的方式组合蛋白质和配体编码并没有显示出性能的显着变化。

"点击查看英文标题和摘要"

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Accurate in silico prediction of protein–ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalizability. To improve generalizability, we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins, we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearson’s R Spearman’s Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings did not show a significant change in performance.

更新日期：2023-11-20

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南