EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PHA synthase variant design using a conditional variational autoencoder

Tuula Tenkanen iD, Anna Ylinen, Paula Jouhten iD, Merja Penttilä, Sandra Castillo

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1014087 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Tuula Tenkanen und 4 weiteren Autor:innen. Beteiligte Einrichtung: VTT Technical Research Centre of Finland Ltd., Espoo, Finland. Hauptthemen laut MEDLINE: Acyltransferases, Protein Engineering. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jane ja Aatos Erkon Säätiö, Virtual Laboratory for Biodesign, Jenny ja Antti Wihurin Rahasto.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Polyhydroxyalkanoate (PHA) synthases are a group of complex, dimeric enzymes which catalyze polymerization of R-hydroxyacids into PHAs. PHA properties depend on their monomer composition but enzymes found in nature have limited specificities to certain R-hydroxyacids only. In this study, a conditional variational autoencoder was used for the first time to design novel PHA synthases. The model was trained with native protein sequences obtained from Uniprot and was used for the creation of approximately 10 000 new PHA synthase enzymes. Out of these, 16 sequences were selected for in vivo validation. The selection criteria included the presence of conserved residues such as catalytic amino acids and amino acids in the dimer interface and structural features like the number of α -helices in the N-terminal part of the enzyme. Two of the 16 novel PHA synthases that had substantial numbers of amino acid substitutions (87 and 98) with respect to the most similar native enzymes were confirmed active and produced poly(hydroxybutyrate) (PHB) when expressed in yeast S. cerevisiae . The results show the power of AI based methods to create active variants of highly complex dimer enzymes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AcyltransferasesProtein EngineeringAutoencoderAmino Acid SequenceModels, MolecularComputational BiologySaccharomyces cerevisiae

Substanzen

Acyltransferasespoly(3-hydroxyalkanoic acid) synthase

Autor:innen und Institutionen

  • VTT Technical Research Centre of Finland Ltd., Espoo, Finland.
  • Department of Bioproducts and Biosystems, Aalto University, Espoo, Finland.

ORCID-Profile: Tuula Tenkanen, Paula Jouhten

Förderung

  • Jane ja Aatos Erkon Säätiö
  • Virtual Laboratory for Biodesign
  • Jenny ja Antti Wihurin Rahasto

Zitieren

APA

Tenkanen, T., Ylinen, A., Jouhten, P., Penttilä, M., & Castillo, S. (2026). PHA synthase variant design using a conditional variational autoencoder. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014087

Vancouver

Tenkanen T, Ylinen A, Jouhten P, Penttilä M, Castillo S. PHA synthase variant design using a conditional variational autoencoder. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1014087

BibTeX
@article{Tenkanen2026,
  author = {Tenkanen, Tuula and Ylinen, Anna and Jouhten, Paula and Penttilä, Merja and Castillo, Sandra},
  title = {PHA synthase variant design using a conditional variational autoencoder},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1014087}
}
Kostenlos starten →