Machine learning-assisted directed protein evolution with combinatorial libraries

By Zachary Wu, S. Kan, Russell D. Lewis, Bruce J. Wittmann, Frances H. Arnold. 2019

515 citations recorded by the source corpus.

Significance Proteins often function poorly when used outside their natural contexts; directed evolution can be used to engineer them to be more efficient in new roles. We propose that the expense of experimentally testing a large number of protein variants can be decreased and the outcome can be improved by incorporating machine learning with directed evolution. Simulations on an empirical fitness landscape demonstrate that the expected performance improvement is greater with this approach. Machine learning-assisted directed evolution from a single parent produced enzyme variants that selectively synthesize the enantiomeric products of a new-to-nature chemical transformation. By exploring multiple mutations simultaneously, machine learning efficiently navigates large regions of sequence space to identify improved proteins and also produces diverse solutions to engineering problems. 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 into 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 validated 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 (i.e., 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 (enantiomeric excess). By greatly increasing throughput with in silico modeling, machine learning enhances the quality and diversity of sequence solutions for a protein engineering problem.

Subfields: Biomedical Engineering, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Molecular Biology

Citations in the corpus

ProGen: Language Modeling for Protein Generation (2020, methodology): “In comparison, random mutation, which is the main technique used by state-of-the-art methods such as directed evolution [4] and ML-assisted directed evolution [39], statistically generates samples”
Evolutionary context-integrated deep sequence modeling for protein engineering (2020, methodology): “To reduce the experimental effort, machine learning (ML) methods have been proposed to assist directed evolution and successfully engineered multiple important functional proteins [15–20] .”
Low-N protein engineering with data-efficient deep learning (2020, background): “To meet the enormous data requirement of supervised deep learning — typically greater than 10 6 labeled data points 26,27 — current machine learning-guided protein design approaches must gather high-throughput experimental data 28–31 or abandon deep learning altogether 18,20,21,32–37 .”
FLIP: Benchmark tasks in fitness landscape inference for proteins (2021, methodology): “We use the GB1 landscape [41], which has become a gold standard for investigating epistatic interactions [10].”
Model-based reinforcement learning for biological sequence design (2020, background): “Recently, machine learning approaches have been shown to be effective in optimizing real-world DNA and protein sequences (Wang et al., 2019; Chhibbar & Joshi, 2019; de Jongh et al., 2019; Liu et al., 2019; Sample et al., 2019; Wu et al., 2019).”
An Overview of Catastrophic AI Risks (2023, background): “In the field of biology, AIs have already surpassed human abilities in protein structure prediction [12] and made contributions to synthesizing those proteins [13].”
Machine-learning-guided directed evolution for protein engineering (2018, methodology): “…sequences, machine-learning methods can use this information to expedite evolution and expand the number of properties that can be optimized by intelligently selecting new variants to screen, thereby reaching higher fitness levels than are possible through directed evolution alone 10–14 (Fig.”
Masked Inverse Folding with Sequence Transfer for Protein Representation Learning (2023, background): “Rma NOD: Wu et al. (2019) explore how mutations at seven positions of the Rhodothermus marinus ( Rma ) nitric oxide dioxygenase (NOD) enzyme influences enantioselectivity on the reaction of phenyldimethyl silane with ethyl 2-diazopropanoate.”