Calibrated geometric deep learning improves kinase–drug binding predictions

基诺美 可药性 化学空间 人工智能 结合亲和力 计算机科学 计算生物学 药物发现 机器学习 深度学习 亲缘关系 激酶 生物 生物信息学 生物化学 基因 受体
作者
Yunan Luo,Yang Liu,Jian Peng
出处
期刊:Nature Machine Intelligence [Nature Portfolio]
卷期号:5 (12): 1390-1401 被引量:25
标识
DOI:10.1038/s42256-023-00751-0
摘要

Protein kinases regulate various cellular functions and hold significant pharmacological promise in cancer and other diseases. Although kinase inhibitors are one of the largest groups of approved drugs, much of the human kinome remains unexplored but potentially druggable. Computational approaches, such as machine learning, offer efficient solutions for exploring kinase–compound interactions and uncovering novel binding activities. Despite the increasing availability of three-dimensional (3D) protein and compound structures, existing methods predominantly focus on exploiting local features from one-dimensional protein sequences and two-dimensional molecular graphs to predict binding affinities, overlooking the 3D nature of the binding process. Here we present KDBNet, a deep learning algorithm that incorporates 3D protein and molecule structure data to predict binding affinities. KDBNet uses graph neural networks to learn structure representations of protein binding pockets and drug molecules, capturing the geometric and spatial characteristics of binding activity. In addition, we introduce an algorithm to quantify and calibrate the uncertainties of KDBNet's predictions, enhancing its utility in model-guided discovery in chemical or protein space. Experiments demonstrated that KDBNet outperforms existing deep learning models in predicting kinase–drug binding affinities. The uncertainties estimated by KDBNet are informative and well-calibrated with respect to prediction errors. When integrated with a Bayesian optimization framework, KDBNet enables data-efficient active learning and accelerates the exploration and exploitation of diverse high-binding kinase–drug pairs. Geometric deep learning has become a powerful tool in virtual drug design, but it is not always obvious when a model makes incorrect predictions. Luo and colleagues improve the accuracy of their deep learning model using uncertainty calibration and Bayesian optimization in an active learning cycle.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
严西完成签到,获得积分10
刚刚
Mr.Ren完成签到,获得积分10
刚刚
Feng发布了新的文献求助10
1秒前
1秒前
skepticalsnails完成签到,获得积分0
2秒前
喜悦的向日葵完成签到,获得积分10
5秒前
纸柒完成签到 ,获得积分10
6秒前
7秒前
肖战战完成签到 ,获得积分10
8秒前
一一一应助songvv采纳,获得10
10秒前
量子星尘发布了新的文献求助10
10秒前
陶一二完成签到,获得积分10
11秒前
MM完成签到,获得积分10
12秒前
Who1990完成签到,获得积分10
13秒前
李友健完成签到 ,获得积分10
14秒前
hhhhh完成签到 ,获得积分10
16秒前
可耐的乘风完成签到,获得积分10
18秒前
wangnn发布了新的文献求助20
18秒前
大橙子发布了新的文献求助10
19秒前
19秒前
19秒前
余慵慵完成签到 ,获得积分10
20秒前
奋斗的小土豆完成签到,获得积分10
21秒前
ZJJ静完成签到,获得积分10
21秒前
邢大宝完成签到,获得积分10
22秒前
尔玉完成签到 ,获得积分10
24秒前
memo完成签到,获得积分10
24秒前
24秒前
一路芬芳完成签到,获得积分20
24秒前
26秒前
一一一应助songvv采纳,获得10
26秒前
26秒前
SciKid524完成签到 ,获得积分10
28秒前
科研通AI2S应助hhh采纳,获得10
28秒前
QWE完成签到,获得积分10
28秒前
赛赛完成签到 ,获得积分10
30秒前
tinydog完成签到,获得积分10
32秒前
长情琦完成签到,获得积分10
32秒前
Mercury完成签到 ,获得积分10
34秒前
zx完成签到 ,获得积分10
35秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038201
求助须知:如何正确求助?哪些是违规求助? 3575940
关于积分的说明 11373987
捐赠科研通 3305747
什么是DOI,文献DOI怎么找? 1819274
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022