Thinking Like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens
IEEE Access · 2026 · 14 · 53145-53163
DOI: 10.1109/access.2026.3678512 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Nikolai A. Rekut und 5 weiteren Autor:innen. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Health of the Russian Federation.
Abstract (Originalsprache)
Representing molecular structures effectively in chemistry remains a challenging task. Language models and graph-based models are extensively utilized within this domain, consistently achieving state-of-the-art results across an array of tasks. However, the prevailing practice of representing chemical compounds in the SMILES format – used by most data sets and many language models – presents notable limitations as a training data format. In this study, we present a novel approach that decomposes molecules into substructures and computes descriptor-based representations for these fragments, providing more detailed and chemically relevant input for model training. We use this substructure and descriptor data as input for language model and also propose a bimodal architecture that integrates this language model with graph-based models. As LM we use RoBERTa, Graph Isomorphism Networks (GIN), Graph Convolutional Networks (GCN) and Graphormer as graph ones. Our framework shows notable improvements over traditional methods in various tasks such as Quantitative Structure-Activity Relationship (QSAR) prediction.
Förderung
- Ministry of Health of the Russian Federation
Zitieren
APA
Rekut, N. A., Orlov, A. A., Ziu, K., Starykh, E., Takáč, M., & Beznosikov, A. N. (2026). Thinking Like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens. IEEE Access, 14, 53145-53163. https://doi.org/10.1109/access.2026.3678512
Vancouver
Rekut NA, Orlov AA, Ziu K, Starykh E, Takáč M, Beznosikov AN. Thinking Like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens. IEEE Access. 2026;14:53145-53163. doi:10.1109/access.2026.3678512
BibTeX
@article{Rekut2026,
author = {Rekut, Nikolai A. and Orlov, Alexey A. and Ziu, Klea and Starykh, Elizaveta and Takáč, Martin and Beznosikov, Aleksandr N.},
title = {Thinking Like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {53145--53163},
doi = {10.1109/access.2026.3678512}
}
EUVIMED