SysFungiNet: A Multi-Omics Data Fusion Framework with Explainable AI for Bioactive Prioritization
DOI:
https://doi.org/10.62411/faith.3048-3719-304Keywords:
Bioactive Discovery, Cheminformatics, Explainable Artificial Intelligence, FAIR Data Principles, Macrofungi Metabolomics, Multi-Omics Integration, Systems Bioinformatics, XGBoost–Graph Neural NetworksAbstract
Macrofungi signify an extensive reservoir of bioactive metabolites. Still, their chemical description is stalled by fragmented analytical pipelines and low reproducibility. This study introduces SysFungiNet, a unified, FAIR-compliant systems-bioinformatics framework designed to accelerate bioactives discovery in non-model fungi. Unlike existing pipelines, SysFungiNet integrates LC-MS/MS metabolomics, transcriptomics, and genomic data with explainable artificial intelligence and molecular docking validation. By reconstructing biosynthetic pathways for Ganoderma lucidum and Craterellus cornucopioides, the framework achieved a Pathway Completeness Index of 0.86. An ensemble machine-learning model predicted bioactivity with an F1-score of 0.91, identifying 312 annotated metabolites. Crucially, decision-making was transparent, with SHAP analysis identifying specific chemical substructures driving predicted immunomodulation. The framework prioritized five high-confidence candidates, including a putative novel terpenoid, Cornucopiolide, which showed high binding affinity (−9.4 kcal/mol) to human immune receptors in silico. Benchmarking against MetaFungi and PhytoOmics demonstrated superior annotation accuracy and reproducibility. SysFungiNet offers a scalable, open-source ecosystem for transforming fungal bioprospecting into an evidence-driven process.
Downloads
References
Samra Qaraghuli, Rasha Eldalawy, Noor Mohsen Nasser, and Zahraa Abdulelah Al Naqqash, “Macrofungi as a Promising Source of Nutraceuticals,” Al Mustansiriyah J. Pharm. Sci., vol. 25, no. 2, pp. 224–233, May 2025, doi: 10.32947/ajps.v25i2.1159.
M. Sharif et al., “Pharmaceutical and Nutraceutical Importance of Bioactive Metabolites from Macrofungi,” About This J. Focus Scope Author Guidel. Artic. Process. Charg. About This J. J. Biol. Regul. Homeost. Agents, vol. 38, no. 5, May 2024, doi: 10.23812/j.biol.regul.homeost.agents.20243805.287.
V. Alves, D. Zamith-Miranda, S. Frases, and J. D. Nosanchuk, “Fungal Metabolomics: A Comprehensive Approach to Understanding Pathogenesis in Humans and Identifying Potential Therapeutics,” J. Fungi, vol. 11, no. 2, p. 93, Jan. 2025, doi: 10.3390/jof11020093.
Y. Li, Y. Qiao, Y. Ma, P. Xue, and C. Ding, “AI in fungal drug development: opportunities, challenges, and future outlook,” Front. Cell. Infect. Microbiol., vol. 15, May 2025, doi: 10.3389/fcimb.2025.1610743.
Wellcome Connecting Science, “WCSCourses/Fungal_Pathogen_Genomics: Hands-on training in web-based data-mining resources for fungal genomes,” GitHub, 2024. https://github.com/WCSCourses/Fungal_Pathogen_Genomics
G. Li, T. Jian, X. Liu, Q. Lv, G. Zhang, and J. Ling, “Application of Metabolomics in Fungal Research,” Molecules, vol. 27, no. 21, p. 7365, Oct. 2022, doi: 10.3390/molecules27217365.
K. K. Kopeć et al., “Unlocking the secrets of metabolomics with Artificial Intelligence: a comprehensive literature review,” J. Pediatr. Neonatal Individ. Med., vol. 13, no. 1, p. e130105, 2024, doi: 10.7363/130105.
Z. Liu and T. Park, “DMOIT: denoised multi-omics integration approach based on transformer multi-head self-attention mechanism,” Front. Genet., vol. 15, Dec. 2024, doi: 10.3389/fgene.2024.1488683.
T. Yang and Z. Chen, “MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification,” arXiv. Aug. 10, 2025. doi: 10.48550/arXiv.2508.07465.
N. A. Valous, F. Popp, I. Zörnig, D. Jäger, and P. Charoentong, “Graph machine learning for integrated multi-omics analysis,” Br. J. Cancer, vol. 131, no. 2, pp. 205–211, Jul. 2024, doi: 10.1038/s41416-024-02706-7.
M. Wang, S. Zhang, R. Li, and Q. Zhao, “Unraveling the specialized metabolic pathways in medicinal plant genomes: a review,” Front. Plant Sci., vol. 15, Dec. 2024, doi: 10.3389/fpls.2024.1459533.
A. G. Niego et al., “Macrofungi as a Nutraceutical Source: Promising Bioactive Compounds and Market Value,” J. Fungi, vol. 7, no. 5, p. 397, May 2021, doi: 10.3390/jof7050397.
S. Y. Son et al., “Integrated Metabolomics and Transcriptomics Unravel the Metabolic Pathway Variations for Different Sized Beech Mushrooms,” Int. J. Mol. Sci., vol. 20, no. 23, p. 6007, Nov. 2019, doi: 10.3390/ijms20236007.
M. Kotera and S. Goto, “Metabolic pathway reconstruction strategies for central metabolism and natural product biosynthesis,” Biophys. Physicobiology, vol. 13, pp. 195–205, 2016, doi: 10.2142/biophysico.13.0_195.
L. Chen, Z. Zhang, Q. Zeng, W. Wang, H. Zhou, and Y. Wu, “Subtractive genomics and comparative metabolic pathways profiling revealed novel drug targets in Ureaplasma urealyticum,” Front. Microbiol., vol. 15, Oct. 2024, doi: 10.3389/fmicb.2024.1484423.
T. H. Cherubino Ribeiro et al., “Metabolic Pathway Reconstruction Indicates the Presence of Important Medicinal Compounds in Coffea Such as L-DOPA,” Int. J. Mol. Sci., vol. 24, no. 15, p. 12466, Aug. 2023, doi: 10.3390/ijms241512466.
A. A. Ginatt et al., “A metabolic modeling-based framework for predicting trophic dependencies in native rhizobiomes of crop plants,” Elife, vol. 13, Oct. 2024, doi: 10.7554/eLife.94558.
A. Bhatia et al., “Metabolic profiling of Commiphora wightii (guggul) reveals a potential source for pharmaceuticals and nutraceuticals,” Phytochemistry, vol. 110, pp. 29–36, Feb. 2015, doi: 10.1016/j.phytochem.2014.12.016.
J. Xiao et al., “Metabolomic Profiling and Biological Investigation of the Marine Sponge-Derived Fungus Aspergillus sp. SYPUF29 in Response to NO Condition,” J. Fungi, vol. 10, no. 9, p. 636, Sep. 2024, doi: 10.3390/jof10090636.
Z. Hu, M. Zuo, S. Ding, Y. Zhong, M. Xue, and H. Zheng, “Integrating Metabolomics and Genomics to Uncover the Impact of Fermented Total Mixed Ration on Heifer Growth Performance Through Host-Dependent Metabolic Pathways,” Animals, vol. 15, no. 2, p. 173, Jan. 2025, doi: 10.3390/ani15020173.
M. D. Wilkinson et al., “The FAIR Guiding Principles for scientific data management and stewardship,” Sci. Data, vol. 3, no. 1, p. 160018, Mar. 2016, doi: 10.1038/sdata.2016.18.
Agri-Sense International, “Agri-Sense International Projects,” Agri-Sense International, 2022. https://www.agrisenseinternational.com/copy-of-2022
D. M. Goodstein et al., “Phytozome: a comparative platform for green plant genomics,” Nucleic Acids Res., vol. 40, no. D1, pp. D1178–D1186, Jan. 2012, doi: 10.1093/nar/gkr944.
Join Genome Institute, “Phytozome version 14,” Join Genome Institute, 2024. https://phytozome-next.jgi.doe.gov/
D. Vasisht et al., “Farmbeats: An IoT platform for data-driven agriculture,” Proc. 14th USENIX Symp. Networked Syst. Des. Implementation, NSDI 2017, pp. 515–529, 2017.
Plant and Food Research, “Phytophthora,” NCBI, 2020. https://www.ncbi.nlm.nih.gov/bioproject/641215
Benoit_Paix1, “MassIVE MSV000084512 - GNPS Taonia atomaria EMPREINTES project,” MassIVE Dataset Summary.
T. M. Okyay, I. Yilmaz, and M. Koldas, “Machine learning-based bioactivity prediction of porphyrin derivatives: molecular descriptors, clustering, and model evaluation,” Photochem. Photobiol. Sci., vol. 24, no. 6, pp. 923–937, Jun. 2025, doi: 10.1007/s43630-025-00733-8.
L. Deng et al., “Integrating transcriptome and metabolome to reveal the characteristics of gene expression profiles and metabolite changes of sorghum in response to cadmium treatment,” Front. Plant Sci., vol. 16, Sep. 2025, doi: 10.3389/fpls.2025.1678876.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Johnson Bisi Oluwagbemi, Olusegun Victor Oyetayo, Emmanuel Onwako Ibam
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
