Keywords

Computational models, Machine learning, Protein design

Abstract

Various approaches have used neural networks as probabilistic models for the design of protein sequences. These "inverse folding" models employ different objective functions, which come with trade-offs that have not been assessed in detail before. This study introduces probabilistic definitions of protein stability and conformational specificity and demonstrates the relationship between these chemical properties and the p(stucture|seq) Boltzmann probability objective. This links the Boltzmann probability objective function to experimentally verifiable outcomes. We propose a novel sequence decoding algorithm, referred to as “BayesDesign”, that leverages Bayes’ Rule to maximize the p(stucture|seq) objective instead of the p(seq|structure) objective common in inverse folding models. The efficacy of BayesDesign is evaluated in the context of two protein model systems, the NanoLuc enzyme and the WW structural motif. Both BayesDesign and the baseline ProteinMPNN algorithm increase the thermostability of NanoLuc and increase the conformational specificity of WW. The possible sources of error in the model are analyzed.

Original Publication Citation

Stern, J.A., Free, T.J., Stern, K.L. et al. A probabilistic view of protein stability, conformational specificity, and design. Sci Rep 13, 15493 (2023). https://doi.org/10.1038/s41598-023-42032-1

Document Type

Peer-Reviewed Article

Publication Date

2023-09-19

Publisher

Scientific Reports

Language

English

College

Ira A. Fulton College of Engineering

Department

Chemical Engineering

University Standing at Time of Publication

Full Professor

Download

Share

COinS