Integrating machine learning tools in protein design: a case of MHETase engineering for PET biodeconstruction
Protein Engineering, Design and Selection · 09.01.2026 · 39
DOI: 10.1093/protein/gzag009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Protein Engineering, Design and Selection, online erschienen am 15.04.2026. Verfasst von Rommel Santiago Granja-Travez und 2 weiteren Autor:innen. Beteiligte Einrichtung: Bioscience Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, United States. Hauptthemen laut MEDLINE: Protein Engineering, Machine Learning, Polyethylene Terephthalates, Burkholderiales. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Bio-Optimized Technologies to keep Thermoplastics out of Landfills and the Environment (BOTTLE) Consortium, DOE-CMEI's Alternate Fuels and Feedstocks Office and Advanced Materials and Manufacturing Office, Los Alamos Unlimited Release.
Abstract (Originalsprache)
The integration of machine learning tools into protein engineering offers substantial promise, yet linking computational predictions to experimental performance remains challenging. Here, we applied accessible computational platforms to engineer Ideonella sakaiensis MHETase, a key enzyme in the biodeconstruction of polyethylene terephthalate (PET). Homologue identification with EnzymeMiner, followed by solubility-focused redesign using AggreProt and ProteinMPNN, enabled the finding of MHETase-like enzymes and the generation of is-MHETase variants with increase in soluble expression, as supported by predictive scoring and experimental validation. However, retaining catalytic activity proved considerably more difficult. Structural modeling and kinetic analyses revealed that ProteinMPNN introduced substitutions incompatible with MHETase function, reflecting biases toward sequence patterns common in broader esterase families rather than constraints specific to this narrow enzyme subgroup. These findings highlight both the utility and the current limitations of accessible ML tools for enzyme engineering, underscoring the continued necessity of experimental validation to guide and refine computational predictions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Bioscience Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, United States.
- BOTTLE Consortium, Golden, CO, 80401, United States.
ORCID-Profile: Rommel Santiago Granja-Travez, Taraka Dale, Ramesh K Jha
Förderung
- Bio-Optimized Technologies to keep Thermoplastics out of Landfills and the Environment (BOTTLE) Consortium
- DOE-CMEI's Alternate Fuels and Feedstocks Office and Advanced Materials and Manufacturing Office
- Los Alamos Unlimited Release
- DOE-CMEI’s Alternate Fuels and Feedstocks Office and Advanced Materials and Manufacturing Office
Zitieren
APA
Granja-Travez, R. S., Dale, T., & Jha, R. K. (2026). Integrating machine learning tools in protein design: a case of MHETase engineering for PET biodeconstruction. Protein Engineering, Design and Selection, 39. https://doi.org/10.1093/protein/gzag009
Vancouver
Granja-Travez RS, Dale T, Jha RK. Integrating machine learning tools in protein design: a case of MHETase engineering for PET biodeconstruction. Protein Engineering, Design and Selection. 2026;39. doi:10.1093/protein/gzag009
BibTeX
@article{GranjaTravez2026,
author = {Granja-Travez, Rommel Santiago and Dale, Taraka and Jha, Ramesh K},
title = {Integrating machine learning tools in protein design: a case of MHETase engineering for PET biodeconstruction},
journal = {Protein Engineering, Design and Selection},
year = {2026},
volume = {39},
doi = {10.1093/protein/gzag009}
}
EUVIMED