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.

薄层色谱（TLC）是分子极性分析中关键的技术，但对 TLC 的预测模型的解释性，尤其是由人工智能驱动的模型，仍然存在挑战。为了弥合这一差距，我们引入了无监督的分层符号回归（UHiSR），结合了分层神经网络和符号回归。UHiSR 自动提取了具有化学直观性的极性指数，并发现了将分子结构与色谱行为相关联的可以解释的方程。