.png){kind=icon}
返回
Active causal learning for decoding chemical complexities with targeted interventions
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad6feb.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Predicting and enhancing inherent properties based on molecular structures is paramount to design tasks in medicine, materials science, and environmental management. Most of the current machine learning and deep learning approaches have become standard for predictions, but they face challenges when applied across different datasets due to reliance on correlations between molecular representation and target properties. These approaches typically depend on large datasets to capture the diversity within the chemical space, facilitating a more accurate approximation, interpolation, or extrapolation of the chemical behavior of molecules. In our research, we introduce an active learning approach that discerns underlying cause-effect relationships through strategic sampling with the use of a graph loss function. This method identifies the smallest subset of the dataset capable of encoding the most information representative of a much larger chemical space. The identified causal relations are then leveraged to conduct systematic interventions, optimizing the design task within a chemical space that the models have not encountered previously. While our implementation focused on the QM9 quantum-chemical dataset for a specific design task-finding molecules with a large dipole moment-our active causal learning approach, driven by intelligent sampling and interventions, holds potential for broader applications in molecular, materials design and discovery.
Keyword:
molecular design
explainability
causal models
active learning
active causal learning
DAG learning
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach通过高通量虚拟筛选和实验方法设计高效分子有机发光二极管.png)
NATURE MATERIALS
NATURE MATERIALSIF38.5
PREAI
分享收藏PubChem: a public information system for analyzing bioactivities of small moleculesPubChem: 用于分析小分子生物活性的公共信息系统NUCLEIC ACIDS RESEARCH
OAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏
查看更多内容