Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

可解释性 人工智能 计算机科学 药代动力学 药物与药物的相互作用 药物发现 机器学习 均方预测误差 差异(会计) 模式识别(心理学) 生物信息学 药理学 医学 生物 会计 业务
作者
Raya Stoyanova,Paul Maximilian Katzberger,Leonid Komissarov,Aous Khadhraoui,Lisa Sach-Peltason,Katrin Groebke Zbinden,Torsten Schindler,Nenad Manevski
出处
期刊:Journal of Chemical Information and Modeling [American Chemical Society]
卷期号:63 (2): 442-458 被引量:22
标识
DOI:10.1021/acs.jcim.2c01134
摘要

Although computational predictions of pharmacokinetics (PK) are desirable at the drug design stage, existing approaches are often limited by prediction accuracy and human interpretability. Using a discovery data set of mouse and rat PK studies at Roche (9,685 unique compounds), we performed a proof-of-concept study to predict key PK properties from chemical structure alone, including plasma clearance (CLp), volume of distribution at steady-state (Vss), and oral bioavailability (F). Ten machine learning (ML) models were evaluated, including Single-Task, Multitask, and transfer learning approaches (i.e., pretraining with in vitro data). In addition to prediction accuracy, we emphasized human interpretability of outcomes, especially the quantification of uncertainty, applicability domains, and explanations of predictions in terms of molecular features. Results show that intravenous (IV) PK properties (CLp and Vss) can be predicted with good precision (average absolute fold error, AAFE of 1.96–2.84 depending on data split) and low bias (average fold error, AFE of 0.98–1.36), with AutoGluon, Gaussian Process Regressor (GP), and ChemProp displaying the best performance. Driven by higher complexity of oral PK studies, predictions of F were more challenging, with the best AAFE values of 2.35–2.60 and higher overprediction bias (AFE of 1.45–1.62). Multi-Task approaches and pretraining of ChemProp neural networks with in vitro data showed similar precision to Single-Task models but helped reduce the bias and increase correlations between observations and predictions. A combination of GP-computed prediction variance, molecular clustering, and dimensionality-reduction provided valuable quantitative insights into prediction uncertainty and applicability domains. SHAPley Additive exPlanations (SHAPs) highlighted molecular features contributing to prediction outcomes of Vss, providing explanations that could aid drug design. Combined results show that computational predictions of PK are feasible at the drug design stage, with several ML technologies converging to successfully leverage historical PK data sets. Further studies are needed to unlock the full potential of this approach, especially with respect to data set sizes and quality, transfer learning between in vitro and in vivo data sets, model-independent quantification of uncertainty, and explainability of predictions.
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
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
无私诗云完成签到,获得积分10
刚刚
LL驳回了顾矜应助
刚刚
xiaxia完成签到,获得积分10
刚刚
AKYDXS完成签到,获得积分10
刚刚
hhh完成签到,获得积分10
1秒前
天天快乐应助wzbc采纳,获得10
1秒前
2秒前
徐徐徐完成签到,获得积分10
2秒前
3秒前
美丽凡阳完成签到,获得积分10
3秒前
4秒前
板栗完成签到,获得积分10
4秒前
四月完成签到 ,获得积分10
4秒前
5秒前
wangke完成签到,获得积分10
6秒前
shijie805发布了新的文献求助10
7秒前
香菜完成签到,获得积分10
8秒前
魔幻的妖丽完成签到 ,获得积分10
8秒前
量子星尘发布了新的文献求助10
9秒前
光崽是谁发布了新的文献求助30
9秒前
9秒前
汐总完成签到,获得积分10
10秒前
科目三应助bernie1023采纳,获得10
11秒前
小白想吃面包完成签到,获得积分10
11秒前
qwydeuqgwhed完成签到,获得积分10
11秒前
JevonCheung完成签到 ,获得积分10
12秒前
yym完成签到,获得积分10
12秒前
袁奇点完成签到,获得积分10
13秒前
zzzzz完成签到,获得积分10
14秒前
14秒前
CodeCraft应助琉琉硫采纳,获得10
14秒前
星辰大海应助Kidmuse采纳,获得10
15秒前
何嘻嘻发布了新的文献求助10
15秒前
安静的芝麻完成签到,获得积分10
16秒前
WN完成签到,获得积分10
16秒前
诚心采白完成签到,获得积分10
16秒前
坚定的草丛完成签到,获得积分10
16秒前
刻苦从阳完成签到,获得积分10
17秒前
眨眼眨眨眼完成签到,获得积分10
17秒前
whyme完成签到,获得积分10
18秒前
高分求助中
Production Logging: Theoretical and Interpretive Elements 2700
Neuromuscular and Electrodiagnostic Medicine Board Review 1000
Statistical Methods for the Social Sciences, Global Edition, 6th edition 600
こんなに痛いのにどうして「なんでもない」と医者にいわれてしまうのでしょうか 510
Walter Gilbert: Selected Works 500
An Annotated Checklist of Dinosaur Species by Continent 500
岡本唐貴自伝的回想画集 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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3661230
求助须知:如何正确求助?哪些是违规求助? 3222298
关于积分的说明 9744632
捐赠科研通 2931923
什么是DOI,文献DOI怎么找? 1605300
邀请新用户注册赠送积分活动 757805
科研通“疑难数据库(出版商)”最低求助积分说明 734569