SMILES Token Additivity Model with Interpretability and Generalizability for Fuel Property Predictions
Mengxin Yang, Guanlin Song, Long Cheng, Haisheng Ren · Journal of Chemical Information and Modeling · 2025
Deep learning models for the quantitative structure–property relationship (QSPR) have traditionally encountered challenges related to limited interpretability and generalizability. In this study, we present the simplified molecular input line entry system (SMILES) token additivity (STA) model for accurately predicting fuel properties, which takes SMILES as input and employs stacked multihead self-attention encoders to extract molecular structural information. This model provides insights into the structure–property relationships by quantifying the contributions of individual tokens to target properties. Furthermore, since the STA model operates without handcrafted molecular fingerprints, it is capable of generalizing to a broad spectrum of structure-related properties. To validate the model’s efficacy, seven critical fuel properties of standard enthalpy of formation (Δ f H °), entropy ( S ), isobaric heat capacity ( C p ), cetane number (CN), boiling point (BP), melting point (MP), and flash point (FP) were tested. The 10-fold cross-validation demonstrated outstanding predictive accuracy, with mean absolute errors of 1.86 kcal/mol (Δ f H °), 0.62 kcal/mol/K ( S ), and 1.82 kcal/mol/K ( C p ), alongside root-mean-square errors (RMSE) of 4.90 (CN), 11.27 °C (BP), 14.09 °C (MP), and 9.47 °C (FP). All properties achieved R 2 values exceeding 0.95. The results demonstrate that it achieves predictive accuracy comparable to conventional machine learning models relying on sophisticated feature engineering while also identifying the effect of key tokens on Δ f H ° and CN.