.png){kind=icon}
返回
Explainable uncertainty quantifications for deep learning-based molecular property prediction
.png){kind=icon}
OA
AI
DOI：10.1186/s13321-023-00682-3.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Quantifying uncertainty in machine learning is important in new research areas with scarce high-quality data. In this work, we develop an explainable uncertainty quantification method for deep learning-based molecular property prediction. This method can capture aleatoric and epistemic uncertainties separately and attribute the uncertainties to atoms present in the molecule. The atom-based uncertainty method provides an extra layer of chemical insight to the estimated uncertainties, i.e., one can analyze individual atomic uncertainty values to diagnose the chemical component that introduces uncertainty to the prediction. Our experiments suggest that atomic uncertainty can detect unseen chemical structures and identify chemical species whose data are potentially associated with significant noise. Furthermore, we propose a post-hoc calibration method to refine the uncertainty quantified by ensemble models for better confidence interval estimates. This work improves uncertainty calibration and provides a framework for assessing whether and why a prediction should be considered unreliable.
Keyword:
Explainable AI
Uncertainty quantifications
Deep learning
Molecular property prediction
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.7
论文数:
1.5K
被引数:
1.1W
机构
引用论文
ChEMBL: towards direct deposition of bioassay dataChEMBL: 走向生物测定数据的直接沉积.png)
NUCLEIC ACIDS RESEARCHOAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏External facial features modify the representation of internal facial features in the fusiform face areaNeuroImage
NeuroImageIF0
PREAI
分享收藏
查看更多内容