EUVIMEDEUVIMED entdecken
Crossref

An Integrated Computational-Experimental Workflow for Fungal Peroxygenase Discovery and Enzyme–Substrate Prediction

Victor J Y Lim iD, Yee-Song Law, Guangrong Peh, Clarence Tan, Charmaine Chia iD, Jhoann M T Miyajima iD, Nazreen Abdul Muthaliff, Pnelope Ng, Yoganathan Kanagasundaram, Wan Lin Yeo iD, Sebastian Maurer-Stroh, Yee Hwee Lim iD und 2 weitere

Journal of Chemical Information and Modeling · 09.11.2026 · 66 (21) · 14247-14258

DOI: 10.1021/acs.jcim.6c01050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 16.10.2026. Verfasst von Victor J Y Lim und 13 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR) , 30 Biopolis Street, Matrix #07-01, Singapore138671, Singapore. Hauptthemen laut MEDLINE: Mixed Function Oxygenases, Fungi, Computational Biology. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Industry Alignment Fund Pre-positioning (IAF-PP) Pharma Innovation Programme (PIPS) Singapore.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in enzyme informatics have produced increasingly powerful general models for the prediction of protein function prediction. However, their performance remains limited for underexplored enzyme families where experimental data are scarce and heterologous expression remains challenging. Here, we present a computational-experimental workflow for prioritizing, characterizing, and modeling fungal unspecific peroxygenases (UPOs) as a case study in enzyme discovery under data-limited conditions. The workflow integrates large-scale sequence mining, expression-aware candidate prioritization, systematic experimental screening, and machine-learning-based prediction of enzyme–substrate activity. From more than 3000 mined candidate sequences, 59 putative UPOs were shortlisted, expressed in Escherichia coli across two batches, and tested against colorimetric substrates, yielding 27 UPOs with consistent expression and activity. A subset of 15 novel UPOs and 4 well-characterized reference enzyme sequences was then screened against a chemically diverse panel of 27 substrates to generate an enzyme–substrate activity data set. Using this data set, we developed two complementary machine learning protocols based on gradient boosting: (i) a structure-informed model incorporating homology modeling, docking, and interaction-derived features (modeling-docking-ML) and (ii) a latent-representation model utilizing joint protein/chemical language model embeddings (protein/chemical-language-model-ML). In retrospective validation, the models achieved performance with a Matthews correlation coefficient (MCC) of up to 55% and accuracy up to 78%. In selected prospective testing on previously unseen batch 2 enzymes, the models achieved an MCC of up to 48% and accuracy up to 70%. Taken together, these results demonstrate that targeted experimental data generation, combined with complementary structure-informed and embedding-based models, can support prioritization and activity prediction within poorly characterized enzyme families while highlighting the continued challenge of generalizing to broader chemical substrate space.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mixed Function OxygenasesFungiComputational BiologySubstrate SpecificityWorkflowMolecular Docking SimulationMachine LearningPrediction AlgorithmsBoosting Machine Learning AlgorithmsModels, Molecular

Substanzen

Mixed Function Oxygenasesperoxygenase

Autor:innen und Institutionen

  • Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR) , 30 Biopolis Street, Matrix #07-01, Singapore138671, Singapore.
  • DSO National Laboratories, 20 Science Park Drive, Singapore118230, Singapore.
  • Singapore Institute of Food and Biotechnology Innovation (SIFBI), Agency for Science, Technology and Research (A*STAR), 31 Biopolis Way, Nanos #01-02Singapore138669, Singapore.
  • Institute of Sustainability for Chemicals, Energy and Environment (ISCE2), Agency for Science, Technology and Research (A*STAR), 8 Biomedical Grove, Neuros #07-01, Singapore138665, Singapore.
  • Bioprocessing Technology Institute (BTI), Agency for Science, Technology and Research (A*STAR), 20 Biopolis Way, Centros, Singapore138671, Singapore.
  • Department of Biological Sciences, Faculty of Science, National University of Singapore, 16 Science Drive 4, Block S3 #05-01, Singapore117558, Republic of Singapore.

ORCID-Profile: Victor J Y Lim, Charmaine Chia, Jhoann M T Miyajima, Wan Lin Yeo, Yee Hwee Lim, Hao Fan

Förderung

  • Industry Alignment Fund Pre-positioning (IAF-PP) Pharma Innovation Programme (PIPS) Singapore

Zitieren

APA

Lim, V. J. Y., Law, Y. S., Peh, G., Tan, C., Chia, C., Miyajima, J. M. T., Muthaliff, N. A., Ng, P., Kanagasundaram, Y., Yeo, W. L., Maurer-Stroh, S., Lim, Y. H., Ang, E. L., & Fan, H. (2026). An Integrated Computational-Experimental Workflow for Fungal Peroxygenase Discovery and Enzyme–Substrate Prediction. Journal of Chemical Information and Modeling, 66(21), 14247-14258. https://doi.org/10.1021/acs.jcim.6c01050

Vancouver

Lim VJY, Law YS, Peh G, Tan C, Chia C, Miyajima JMT, et al. An Integrated Computational-Experimental Workflow for Fungal Peroxygenase Discovery and Enzyme–Substrate Prediction. Journal of Chemical Information and Modeling. 2026;66(21):14247-14258. doi:10.1021/acs.jcim.6c01050

BibTeX
@article{Lim2026,
  author = {Lim, Victor J Y and Law, Yee-Song and Peh, Guangrong and Tan, Clarence and Chia, Charmaine and Miyajima, Jhoann M T and Muthaliff, Nazreen Abdul and Ng, Pnelope and Kanagasundaram, Yoganathan and Yeo, Wan Lin and Maurer-Stroh, Sebastian and Lim, Yee Hwee and Ang, Ee Lui and Fan, Hao},
  title = {An Integrated Computational-Experimental Workflow for Fungal Peroxygenase Discovery and Enzyme–Substrate Prediction},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {21},
  pages = {14247--14258},
  doi = {10.1021/acs.jcim.6c01050}
}
Kostenlos starten →