A survey of models composed of graph neural networks and large language models for molecular science
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag387 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Bioinformatics, 2026. Verfasst von Natàlia Segura-Alabart und 1 weiteren Autor:innen. Beteiligte Einrichtung: Departament d'Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili, Tarragona, Catalonia 43007, Spain. Hauptthemen laut MEDLINE: Graph Neural Networks, Large Language Models, Models, Molecular. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AGAUR research, ASCLEPIUS: Smart Technology for Smart Healthcare, Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación.
Abstract (Originalsprache)
Motivation Graphs have been demonstrated to have an impressive ability to keep the structural and semantic properties of chemical compounds and are therefore widely used in molecular modeling. Moreover, Graph Neural Networks (GNNs) and Large Language Models (LLMs) have achieved outstanding results in predicting molecular properties and generating textual descriptions given graphs or texts, respectively. Recently, some mathematical models have been presented for molecular science applications, which combine the GNNs ability to capture the structural and semantic information and the generative ability of LLMs. However, these models are dispersed across the literature and vary in architecture, input–output design, and application scope, making it difficult to systematically compare them or to identify suitable approaches for specific research objectives. Results This paper classifies recent GNN–LLM models and summarizes them with the aim of providing guidance for research involving their use or the development of new models. We present tables that depict the properties and parameters of the models, as well as their associated chemical computational applications. In addition, a new model classification is presented to help researchers define the models they use or future ones. Finally, we quantitatively compare these models based on their reported experimental results.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Departament d'Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili, Tarragona, Catalonia 43007, Spain.
ORCID-Profile: Natàlia Segura-Alabart, Francesc Serratosa
Förderung
- AGAUR research
- ASCLEPIUS: Smart Technology for Smart Healthcare
- Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación
Zitieren
APA
Segura-Alabart, N., & Serratosa, F. (2026). A survey of models composed of graph neural networks and large language models for molecular science. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag387
Vancouver
Segura-Alabart N, Serratosa F. A survey of models composed of graph neural networks and large language models for molecular science. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag387
BibTeX
@article{SeguraAlabart2026,
author = {Segura-Alabart, Natàlia and Serratosa, Francesc},
title = {A survey of models composed of graph neural networks and large language models for molecular science},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag387}
}
EUVIMED