Machine learning-assisted directed protein evolution with combinatorial libraries

Abstract

To reduce experimental effort associated with directed protein evolution and to explore the sequence space encoded by mutating multiple positions simultaneously, we incorporate machine learning in the directed evolution workflow. Combinatorial sequence space can be quite expensive to sample experimentally, but machine learning models trained on tested variants provide a fast method for testing sequence space computationally. We validate this approach on a large published empirical fitness landscape for human GB1 binding protein, demonstrating that machine learning-guided directed evolution finds variants with higher fitness than those found by other directed evolution approaches. We then provide an example application in evolving an enzyme to produce each of the two possible product enantiomers (stereodivergence) of a new-to-nature carbene Si-H insertion reaction. The approach predicted libraries enriched in functional enzymes and fixed seven mutations in two rounds of evolution to identify variants for selective catalysis with 93% and 79% ee. By greatly increasing throughput with in silico modeling, machine learning enhances the quality and diversity of sequence solutions for a protein engineering problem.

arXiv commentCorrected best S-selective variant sequence in Figure 4. Corrected less R-selective variant sequences from Round II Input library in Table 2 and Supp Table 4. Corrections may also be found on PNAS version https://www.pnas.org/content/early/2019/12/26/1921770117

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Why high-error-rate random mutagenesis libraries are enriched in functional and improved proteins
• Variational auto-encoding of protein sequences
• Design by adaptive sampling

Cited by in corpus (15)

• Machine learning modeling of family wide enzyme-substrate specificity screens
• Population-Based Black-Box Optimization for Biological Sequence Design
• Conformal Prediction Under Feedback Covariate Shift for Biomolecular Design
• SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering
• ProGen: Language Modeling for Protein Generation
• Is novelty predictable?
• A primer on model-guided exploration of fitness landscapes for biological sequence design
• Autofocused oracles for model-based design
• Protein-protein interactions enhance the thermal resilience of SpyRing enzymes: a molecular dynamic simulation study
• Batched Stochastic Bayesian Optimization via Combinatorial Constraints Design
• Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins
• Directed Evolution of Proteins via Bayesian Optimization in Embedding Space
• Rapid Identification of X-ray Diffraction Spectra Based on Very Limited Data by Interpretable Convolutional Neural Networks
• Accurate computational evolution of proteins and its dependence on deep learning
• Designing over uncertain outcomes with stochastic sampling Bayesian optimization