LG-Transformer: Learned-Graph Transformer Framework Enabling Diverse Physicochemical Properties Prediction toward Fuel Design

Read full text Summarise with VIRAT
Authors: Jiabo Zhang, Xiang Lv, Hui An, Jing Li, Peng Han, Zhen Yu Huang
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Green fuels are essential for decarbonizing transportation sectors, requiring accurate prediction of different physicochemical properties to optimize engine performance and emissions. Although artificial intelligence-based models demonstrate significant potential to accelerate fuel design, most existing methods cannot utilize the internal and external information within and between fuel molecules with interpretability, limiting their generalizability for diverse properties prediction. To address these challenges, a novel deep learning framework, the learned graph feature fusion Transformer (LG-Transformer), is proposed. Unlike conventional graph neural networks (GNNs) that operate on atom–bond molecular graphs, LG-Transformer employs contrastive learning to construct an inter-molecular relationship graph guided by topological descriptors and property similarity, enabling property-aware feature propagation through Transformer layers for various property prediction. Supporting this effort, a comprehensive fuel property database is developed, containing 1850 diverse molecules across 26 chemical classes, each annotated with 17 key physicochemical properties relevant to engine performance. LG-Transformer achieves state-of-the-art performance with an average $R^2$ of 0.900, significantly outperforming other GNN and deep learning baselines. Additionally, interpretability analyses via integrated gradients reveal underlying molecular structure–property relationships. Overall, this work establishes a powerful, generalizable, and interpretable framework that significantly accelerates virtual screening and rational design of advanced low-carbon fuels, bridging fundamental understanding and practical application to advance the discovery and optimization of next-generation sustainable fuels.

Fields of Study & Subjects

Computational Drug Discovery Methods Machine Learning in Materials Science Advanced Chemical Physics Studies

Publication details

Journal / source
Code Ocean
Publication date
1 January 2026
Language
EN