EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Thinking Like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens

Nikolai A. Rekut, Alexey A. Orlov, Klea Ziu, Elizaveta Starykh, Martin Takáč, Aleksandr N. Beznosikov

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →