Data-Efficient Distal Engineering of Fluorinase Using Zero-Shot Models
- 1The Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Søltofts Plads 220, 2200 Kongens Lyngby, Denmark
- 2Loschmidt Laboratories, Department of Experimental Biology and RECETOX, Faculty of Science, Masaryk University, Kamenice 5, 625 00 Brno, Czech Republic
- 3International Clinical Research Center, St. Anne’s University Hospital, Pekařská 664/53, 602 00 Brno, Czech Republic
Abstract
Fluorinases have high potential for industrial biofluorination, but any applications have been precluded by low catalytic efficiency and resistance to active site engineering. In this work, we employed PRIZM, a computational workflow utilizing an existing low-N data set and zero-shot models for in silico prediction of activity-enhancing mutations at distal sites. The combination of these predictions with expert opinion led to the identification of 21 fluorinase mutants with enhanced relative activities, while 3 variants showed increased melting temperatures. A mutation in the hexameric interface, K237R, resulted in the largest stability gain, a more than 3.2-fold improvement in catalytic efficiency at 57 °C, and an 8-fold increase in relative activity at 62 °C. These results highlight the potential of distal fluorinase engineering for improving properties required to realize its industrial applications.
Related
- Zero-shot design of drug-binding proteins via neural iterative selection−expansion
- Splicing-guaranteed artificial introns enable efficient homology-directed repair at internal exons and streamlined cell engineering
- Efficient Escherichia coli platform for L-proline biosynthesis via systematic metabolic engineering.
- Rapid receptor internalization potentiates CD7-targeted lipid nanoparticles for efficient mRNA delivery to T cells and in vivo CAR T-cell engineering
- Mechanisms of transcription control by distal enhancers from single-gene nanoscopy
BibTeX
@article{hardinglarsen2026dataefficient,
title = {{Data-Efficient Distal Engineering of Fluorinase Using Zero-Shot Models}},
author = {David Harding-Larsen and Brianna M. Lax and Christopher Kurt Weingarten and Aboubakar Sako and Stanislav Mazurenko and Ditte Hededam Welner},
journal = {Chem \& Bio Engineering},
year = {2026},
month = aug,
doi = {10.1021/cbe.6c00028},
url = {https://doi.org/10.1021/cbe.6c00028},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Data-Efficient Distal Engineering of Fluorinase Using Zero-Shot Models
AU - David Harding-Larsen
AU - Brianna M. Lax
AU - Christopher Kurt Weingarten
AU - Aboubakar Sako
AU - Stanislav Mazurenko
AU - Ditte Hededam Welner
PY - 2026
DA - 2026/08/05
JO - Chem & Bio Engineering
DO - 10.1021/cbe.6c00028
UR - https://doi.org/10.1021/cbe.6c00028
AB - Fluorinases have high potential for industrial biofluorination, but any applications have been precluded by low catalytic efficiency and resistance to active site engineering. In this work, we employed PRIZM, a computational workflow utilizing an existing low-N data set and zero-shot models for in silico prediction of activity-enhancing mutations at distal sites. The combination of these predictions with expert opinion led to the identification of 21 fluorinase mutants with enhanced relative activities, while 3 variants showed increased melting temperatures. A mutation in the hexameric interface, K237R, resulted in the largest stability gain, a more than 3.2-fold improvement in catalytic efficiency at 57 °C, and an 8-fold increase in relative activity at 62 °C. These results highlight the potential of distal fluorinase engineering for improving properties required to realize its industrial applications.
SN - 2836-967X
ER -