Can I read Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression on EtoBox?

Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression by Lou, Siyu; Liu, Chengchun; Chen, Yuntian; Mo, Fanyang is a scholarly article available to read on EtoBox.

What is Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression about?

Thin-layer chromatography (TLC) is a crucial technique in molecular polarity analysis. Despite its importance, the interpretability of predictive models for TLC, especially those driven by artificial intelligence, remains a challenge. Current approaches, utilizing either high-dimensional molecular fingerprints or domain-knowledge-driven feature engineering, often face a dilemma between expressiveness and interpretability. To bridge this gap, we introduce Unsupervised Hierarchical Symbolic Regression (UHiSR), combining hierarchical neural networks and symbolic regression. UHiSR automatically distills chemical-intuitive polarity indices, and discovers interpretable equations that link molecular structure to chromatographic behavior.

Author

Lou, Siyu; Liu, Chengchun; Chen, Yuntian; Mo, Fanyang

Published

2024

Language

EN