Biophysics-based protein language models for protein engineering DOI Creative Commons
Sam Gelman,

Bryce Johnson,

Chase R. Freschlin

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 17, 2024

Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure, and function. However, these overlook decades of research into biophysical factors governing We propose Mutational Effect Transfer Learning (METL), a model framework that unites advanced machine learning modeling. Using the METL framework, we pretrain transformer-based neural networks simulation to capture fundamental relationships between energetics. finetune experimental sequence-function harness signals apply them when predicting properties like thermostability, catalytic activity, fluorescence. excels in challenging engineering tasks generalizing from small training sets position extrapolation, although existing methods train remain many types assays. demonstrate METL's ability design functional green fluorescent variants only 64 examples, showcasing potential biophysics-based engineering.

Language: Английский

Active learning-assisted directed evolution DOI Creative Commons
Jason Yang, Ravi Lal,

James C. Bowden

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: Jan. 16, 2025

Abstract Directed evolution (DE) is a powerful tool to optimize protein fitness for specific application. However, DE can be inefficient when mutations exhibit non-additive, or epistatic, behavior. Here, we present Active Learning-assisted Evolution (ALDE), an iterative machine learning-assisted workflow that leverages uncertainty quantification explore the search space of proteins more efficiently than current methods. We apply ALDE engineering landscape challenging DE: optimization five epistatic residues in active site enzyme. In three rounds wet-lab experimentation, improve yield desired product non-native cyclopropanation reaction from 12% 93%. also perform computational simulations on existing sequence-fitness datasets support our argument effective DE. Overall, practical and broadly applicable strategy unlock improved outcomes.

Language: Английский

Citations

4
Biophysics-based protein language models for protein engineering DOI Creative Commons
Sam Gelman,

Bryce Johnson,

Chase R. Freschlin

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 17, 2024

Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure, and function. However, these overlook decades of research into biophysical factors governing We propose Mutational Effect Transfer Learning (METL), a model framework that unites advanced machine learning modeling. Using the METL framework, we pretrain transformer-based neural networks simulation to capture fundamental relationships between energetics. finetune experimental sequence-function harness signals apply them when predicting properties like thermostability, catalytic activity, fluorescence. excels in challenging engineering tasks generalizing from small training sets position extrapolation, although existing methods train remain many types assays. demonstrate METL's ability design functional green fluorescent variants only 64 examples, showcasing potential biophysics-based engineering.

Language: Английский

Citations

11