Enabling Accurate and Interpretable Property Prediction with TDiMS in Large Molecules

Lisa Hamada, Akihiro Kishimoto, Junta Fuchiwaki, Kohei Miyaguchi, Hirose Masataka, Indra Priyadarsini, Seiji Takeda, Sina Klampt, Takao Moriyama

Keywords: Molecular descriptor, Topological distance, Property prediction, Interpretable machine learning

TL;DR: TDiMS captures substructure distances to improve property prediction for large molecules, outperforming existing descriptors while retaining interpretability.

Abstract: In materials discovery, descriptors that are both accurate and interpretable are essential for predicting molecular properties. However, existing descriptors, including neural network-based approaches, often struggle to capture long-range interactions between substructures. We analyze the previously proposed descriptor TDiMS, which models nonlocal structural relationships via average topological distances between substructure-pairs. While TDiMS has shown strong performance, its size dependence had not been systematically assessed. Our analysis reveals that TDiMS is particularly effective for larger molecules, where long-range interactions are critical and conventional descriptors underperform. SHAP-based analysis highlights that its predictive power derives from distant substructure-pair features. In addition to improved accuracy, TDiMS offers interpretable features that provide chemical insight, potentially accelerating molecular design and discovery.

Submission Track: Paper Track (Short Paper)

Submission Category: AI-Guided Design

Institution Location: Tokyo, Japan

AI4Mat RLSF: Yes

Submission Number: 29