Uncertainty quantification for molecular property predictions with graph neural architecture search†

IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Digital discovery Pub Date : 2024-06-25 DOI:10.1039/D4DD00088A
Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash and Victor M. Zavala
{"title":"Uncertainty quantification for molecular property predictions with graph neural architecture search†","authors":"Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash and Victor M. Zavala","doi":"10.1039/D4DD00088A","DOIUrl":null,"url":null,"abstract":"<p >Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1534-1553"},"PeriodicalIF":6.2000,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital discovery","FirstCategoryId":"1085","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00088a","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.

Abstract Image

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用图神经结构搜索进行分子特性预测的不确定性量化
图神经网络(GNN)已成为一类重要的数据驱动型分子特性预测方法。然而,典型 GNN 模型的一个主要局限是无法量化预测中的不确定性。这种能力对于确保在下游任务中可靠地使用和部署模型至关重要。为此,我们推出了用于分子特性预测的自动不确定性量化(UQ)方法 AutoGNNUQ。AutoGNNUQ 利用架构搜索生成高性能 GNN 集合,从而实现预测不确定性的估计。我们的方法采用方差分解法来分离数据不确定性和模型不确定性,为减少不确定性提供了宝贵的见解。在我们的计算实验中,我们证明了在多个基准数据集上,AutoGNNUQ 在预测准确性和 UQ 性能方面都优于现有的 UQ 方法,并能很好地泛化到分布外数据集。此外,我们还利用 t-SNE 可视化技术探索了分子特征与不确定性之间的相关性,为数据集的改进提供了启示。AutoGNNUQ 在药物发现和材料科学等领域具有广泛的适用性,在这些领域,准确的不确定性量化对决策至关重要。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
2.80
自引率
0.00%
发文量
0
期刊最新文献
Back cover ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials. Sorting polyolefins with near-infrared spectroscopy: identification of optimal data analysis pipelines and machine learning classifiers†‡ High accuracy uncertainty-aware interatomic force modeling with equivariant Bayesian neural networks† Correction: A smile is all you need: predicting limiting activity coefficients from SMILES with natural language processing
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1