EUVIMEDEUVIMED entdecken
Crossref

FlavorGPN: a graph neural network for multi-label molecular flavor prediction

Jie Liu, Xin Shu, Shougang Ren, Sheng Wan, Xingying Pan

Molecular Diversity · 03.09.2026 · 30 (6) · 10875-10890

DOI: 10.1007/s11030-026-11702-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Diversity, online erschienen am 03.09.2026. Verfasst von Jie Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Nanjing Agricultural University, No.1 Weigang, Nanjing, 210095, Jiangsu, China. lj20020903@gmail.com. Hauptthemen laut MEDLINE: Graph Neural Networks, Flavoring Agents, Cheminformatics. Die Arbeit nennt 49 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting chemosensory attributes from chemical structures is a fundamental task in cheminformatics and molecular modeling. When applied to flavor specifically, this task becomes particularly challenging due to the structural diversity of flavor molecules and the complex, multi-label nature of human sensory perception. Traditional machine learning methods often rely on one-dimensional fingerprints, which inadequately capture high-dimensional topological and geometric features. In this study, we introduce the FlavorGraph Predictive Network (FlavorGPN), a novel graph neural network (GNN) framework for multi-label flavor prediction. FlavorGPN leverages the pretrained 2D graph encoder from GraphMVP, whose parameters are learned through 3D-informed pretraining, to enhance molecular graph representations. Notably, no explicit 3D conformers or atomic coordinates are used during downstream fine-tuning or inference. Therefore, the use of 3D information in this study should be understood as 3D-supervised pretraining rather than direct 2D/3D geometric integration during inference. To mitigate the class imbalance inherent in flavor datasets, we propose ML-ROS-improved, an adaptive oversampling algorithm that integrates dynamic thresholding for minority-label identification, weighted minority-label sampling, and constrained graph augmentation. We also systematically evaluate several graph augmentation strategies. Among them, Molecular Connectivity Index (MCI)-constrained augmentation achieves the highest observed Macro-F1 and Macro AUC-ROC scores. Across the FlavorMiner and FART benchmarks, FlavorGPN achieved the highest observed Macro-F1 and Macro AUC-ROC point estimates among the evaluated baselines under the reported experimental settings. On the FART benchmark, the model achieved a Macro-F1 score of 0.8542 and a Macro AUC-ROC score of 0.9796. Literature-based contextual comparisons further indicate that the unified model performs competitively on key flavor categories, including Sweet, Bitter, and Sour. However, these comparisons do not constitute controlled head-to-head evaluations. Overall, the benchmark results demonstrate the practical value of FlavorGPN for imbalanced multi-label chemosensory prediction under the evaluated settings and suggest its potential to support computational screening and molecular-level analyses of flavor-associated chemical properties.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksFlavoring AgentsCheminformaticsAlgorithmsPrediction AlgorithmsHumansTasteModels, Molecular

Stichwörter der Autor:innen

Chemosensory molecular propertiesFlavorGraph neural networksMolecular graph representationMolecular property predictionQSAR

Substanzen

Flavoring Agents

Autor:innen und Institutionen

  • College of Artificial Intelligence, Nanjing Agricultural University, No.1 Weigang, Nanjing, 210095, Jiangsu, China. lj20020903@gmail.com.
  • College of Artificial Intelligence, Nanjing Agricultural University, No.1 Weigang, Nanjing, 210095, Jiangsu, China.

Zitieren

APA

Liu, J., Shu, X., Ren, S., Wan, S., & Pan, X. (2026). FlavorGPN: a graph neural network for multi-label molecular flavor prediction. Molecular Diversity, 30(6), 10875-10890. https://doi.org/10.1007/s11030-026-11702-3

Vancouver

Liu J, Shu X, Ren S, Wan S, Pan X. FlavorGPN: a graph neural network for multi-label molecular flavor prediction. Molecular Diversity. 2026;30(6):10875-10890. doi:10.1007/s11030-026-11702-3

BibTeX
@article{Liu2026,
  author = {Liu, Jie and Shu, Xin and Ren, Shougang and Wan, Sheng and Pan, Xingying},
  title = {FlavorGPN: a graph neural network for multi-label molecular flavor prediction},
  journal = {Molecular Diversity},
  year = {2026},
  volume = {30},
  number = {6},
  pages = {10875--10890},
  doi = {10.1007/s11030-026-11702-3}
}
Kostenlos starten →