Abstract
BackgroundDirected evolution (DE) is a technique for protein engineering that involves iterative rounds of mutagenesis and screening to search for sequences that optimize a given property, such as binding affinity to a specified target. Unfortunately, the underlying optimization problem is under-determined, and so mutations introduced to improve the specified property may come at the expense of unmeasured, but nevertheless important properties (ex. solubility, thermostability, etc). We address this issue by formulating DE as a regularized Bayesian optimization problem where the regularization term reflects evolutionary or structure-based constraints.ResultsWe applied our approach to DE to three representative proteins, GB1, BRCA1, and SARS-CoV-2 Spike, and evaluated both evolutionary and structure-based regularization terms. The results of these experiments demonstrate that: (i) structure-based regularization usually leads to better designs (and never hurts), compared to the unregularized setting; (ii) evolutionary-based regularization tends to be least effective; and (iii) regularization leads to better designs because it effectively focuses the search in certain areas of sequence space, making better use of the experimental budget. Additionally, like previous work in Machine learning assisted DE, we find that our approach significantly reduces the experimental burden of DE, relative to model-free methods.ConclusionIntroducing regularization into a Bayesian ML-assisted DE framework alters the exploratory patterns of the underlying optimization routine, and can shift variant selections towards those with a range of targeted and desirable properties. In particular, we find that structure-based regularization often improves variant selection compared to unregularized approaches, and never hurts.
Highlights
The field of protein engineering seeks to design molecules with novel or improved properties [1]
Results we report the results of five approaches to performing Directed evolution (DE): (i) single mutation walk; (ii) recombination; (iii) Bayesian optimization using standard acquisition functions (Eqs. 7–9), denoted by ‘Gaussian process (GP) + expected improvement (EI)’, ‘GP + probability of improvement (PI)’, or ‘GP + upper (or lower) confidence bounds (UCB)’; (iv) Bayesian optimization using evolution-based regularized acquisition functions with transformer protein language model (TPLM)-derived log-odds, denoted by ‘GP + EI + TPLM’, ‘GP + PI + TPLM’, or ‘GP + UCB + TPLM’; and (v) Bayesian optimization using structure-based regularized acquisition functions with FoldX-derived G values, denoted by ‘GP + EI + FoldX’, ‘GP + PI + FoldX’, or ‘GP + UCB + FoldX’
In Additional file 1: Fig. S1, we show that evolution-based regularization via gremlin and profile Hidden Markov Model (HMM) are able to improve upon traditional DE techniques on the same Streptococcal protein G B1 domain (GB1) variant selection task
Summary
The field of protein engineering seeks to design molecules with novel or improved properties [1]. The primary techniques used in protein engineering fall into two broad categories: rational design [2] and directed evolution (DE) [3]. In contrast, involves iterative rounds of saturation mutagenesis at select residue positions, followed by in vitro or in vivo screening for desirable traits. Directed evolution (DE) is a technique for protein engineering that involves iterative rounds of mutagenesis and screening to search for sequences that optimize a given property, such as binding affinity to a specified target. The primary steps in directed evolution are: (i) random mutagenesis, to create a library of variants; (ii) screening, to identify variants with the desired traits; and (iii) amplification of the best variants, to seed the round. The exploratory aspect of DE is effectively a strategy for getting out of local optima on the underlying fitness landscape
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
