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
2秒前
Owen应助不是当地采纳,获得10
2秒前
3秒前
团结友爱完成签到,获得积分10
3秒前
5秒前
领导范儿应助nichen采纳,获得10
6秒前
我是站长才怪应助迟迟采纳,获得10
6秒前
7秒前
柯一一应助lang采纳,获得10
8秒前
DeepLearning发布了新的文献求助10
9秒前
sonic完成签到,获得积分10
9秒前
神说要有光完成签到 ,获得积分10
9秒前
小李博士发布了新的文献求助10
13秒前
18秒前
19秒前
pp发布了新的文献求助10
20秒前
顾矜应助小李博士采纳,获得10
20秒前
23秒前
nichen发布了新的文献求助10
23秒前
dustomb发布了新的文献求助10
25秒前
醉熏的天与应助pp采纳,获得10
27秒前
CodeCraft应助ecnuZhao采纳,获得10
27秒前
28秒前
冰激凌UP发布了新的文献求助10
28秒前
逸兴遄飞完成签到,获得积分20
29秒前
29秒前
cyn完成签到,获得积分10
32秒前
jackwang完成签到,获得积分10
34秒前
竹筏过海应助雪山飞龙采纳,获得30
34秒前
34秒前
georgia_qiao完成签到,获得积分10
35秒前
kuoping完成签到,获得积分0
35秒前
逸兴遄飞发布了新的文献求助30
35秒前
36秒前
36秒前
37秒前
40秒前
小李博士发布了新的文献求助10
41秒前
41秒前
41秒前
高分求助中
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 500
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 3962850
求助须知:如何正确求助?哪些是违规求助? 3508775
关于积分的说明 11142938
捐赠科研通 3241643
什么是DOI,文献DOI怎么找? 1791625
邀请新用户注册赠送积分活动 872998
科研通“疑难数据库(出版商)”最低求助积分说明 803571