DeCOIL: Optimization of Degenerate Codon Libraries for Machine Learning-Assisted Protein Engineering

Yang, Jason; Ducharme, Julie; Johnston, Kadina E.; Li, Francesca-Zhoufan; Yue, Yisong; Arnold, Frances H.

doi:10.1021/acssynbio.3c00301

DeCOIL: Optimization of Degenerate Codon Libraries for Machine Learning-Assisted Protein Engineering

Journal Article · Mon Jul 31 00:00:00 EDT 2023 · ACS Synthetic Biology

DOI:https://doi.org/10.1021/acssynbio.3c00301· OSTI ID:1992599

^[1]; Ducharme, Julie ^[2]; ^[2]; ^[2]; Yue, Yisong ^[2]; ^[2]

California Institute of Technology (CalTech), Pasadena, CA (United States); California Institute of Technology (Caltech)
California Institute of Technology (CalTech), Pasadena, CA (United States)

With advances in machine learning (ML)-assisted protein engineering, models based on data, biophysics, and natural evolution are being used to propose informed libraries of protein variants to explore. Synthesizing these libraries for experimental screens is a major bottleneck, as the cost of obtaining large numbers of exact gene sequences is often prohibitive. Degenerate codon (DC) libraries are a cost-effective alternative for generating combinatorial mutagenesis libraries where mutations are targeted to a handful of amino acid sites. However, existing computational methods to optimize DC libraries to include desired protein variants are not well suited to design libraries for ML-assisted protein engineering. To address these drawbacks, we present DEgenerate Codon Optimization for Informed Libraries (DeCOIL), a generalized method which directly optimizes DC libraries to be useful for protein engineering: to sample protein variants that are likely to have both high fitness and high diversity in the sequence search space. Using computational simulations and wet-lab experiments, we demonstrate that DeCOIL is effective across two specific case studies, with potential to be applied to many other use cases. DeCOIL offers several advantages over existing methods, as it is direct, easy-to-use, generalizable, and scalable. With accompanying software, DeCOIL can be readily implemented to generate desired informed libraries.

View Accepted Manuscript (DOE)

Research Organization:: California Institute of Technology (CalTech), Pasadena, CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: SC0022218

OSTI ID:: 1992599

Journal Information:: ACS Synthetic Biology, Journal Name: ACS Synthetic Biology Journal Issue: 8 Vol. 12; ISSN 2161-5063

Publisher:: American Chemical Society (ACS)Copyright Statement

Country of Publication:: United States

Language:: English

References (63)

Directed Evolution: Bringing New Chemistry to Life Arnold, Frances H. Angewandte Chemie International Edition, Vol. 57, Issue 16 https://doi.org/10.1002/anie.201708408	journal	November 2017
Tryptophan Synthase: Biocatalyst Extraordinaire Watkins‐Dulaney, Ella; Straathof, Sabine; Arnold, Frances ChemBioChem, Vol. 22, Issue 1 https://doi.org/10.1002/cbic.202000379	journal	September 2020
Machine Learning-driven Protein Library Design: A Path Toward Smarter Libraries Mardikoraem, Mehrsa; Woldring, Daniel Yeast Surface Display https://doi.org/10.1007/978-1-0716-2285-8_5	book	April 2022
An analysis of approximations for maximizing submodular set functions—I Nemhauser, G. L.; Wolsey, L. A.; Fisher, M. L. Mathematical Programming, Vol. 14, Issue 1 https://doi.org/10.1007/BF01588971	journal	December 1978
The budgeted maximum coverage problem Khuller, Samir; Moss, Anna; Naor, Joseph (Seffi) Information Processing Letters, Vol. 70, Issue 1 https://doi.org/10.1016/S0020-0190(99)00031-9	journal	April 1999
Informed training set design enables efficient machine learning-assisted directed protein evolution Wittmann, Bruce J.; Yue, Yisong; Arnold, Frances H. Cell Systems https://doi.org/10.1016/j.cels.2021.07.008	journal	August 2021
Evolutionary velocity with protein language models predicts evolutionary dynamics of diverse proteins Hie, Brian L.; Yang, Kevin K.; Kim, Peter S. Cell Systems, Vol. 13, Issue 4 https://doi.org/10.1016/j.cels.2022.01.003	journal	April 2022
Machine learning to navigate fitness landscapes for protein engineering Freschlin, Chase R.; Fahlberg, Sarah A.; Romero, Philip A. Current Opinion in Biotechnology, Vol. 75 https://doi.org/10.1016/j.copbio.2022.102713	journal	June 2022
Advances in machine learning for directed evolution Wittmann, Bruce J.; Johnston, Kadina E.; Wu, Zachary Current Opinion in Structural Biology, Vol. 69 https://doi.org/10.1016/j.sbi.2021.01.008	journal	August 2021
Adaptive machine learning for protein engineering Hie, Brian L.; Yang, Kevin K. Current Opinion in Structural Biology, Vol. 72 https://doi.org/10.1016/j.sbi.2021.11.002	journal	February 2022
Deep Dive into Machine Learning Models for Protein Engineering Xu, Yuting; Verma, Deeptak; Sheridan, Robert P. Journal of Chemical Information and Modeling, Vol. 60, Issue 6 https://doi.org/10.1021/acs.jcim.0c00073	journal	April 2020
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design Alford, Rebecca F.; Leaver-Fay, Andrew; Jeliazkov, Jeliazko R. Journal of Chemical Theory and Computation, Vol. 13, Issue 6 https://doi.org/10.1021/acs.jctc.7b00125	journal	May 2017
Machine Learning in Enzyme Engineering Mazurenko, Stanislav; Prokop, Zbynek; Damborsky, Jiri ACS Catalysis, Vol. 10, Issue 2 https://doi.org/10.1021/acscatal.9b04321	journal	December 2019
100th Anniversary of Macromolecular Science Viewpoint: Data-Driven Protein Design Ferguson, Andrew L.; Ranganathan, Rama ACS Macro Letters, Vol. 10, Issue 3 https://doi.org/10.1021/acsmacrolett.0c00885	journal	February 2021
evSeq: Cost-Effective Amplicon Sequencing of Every Variant in a Protein Library Wittmann, Bruce J.; Johnston, Kadina E.; Almhjell, Patrick J. ACS Synthetic Biology, Vol. 11, Issue 3 https://doi.org/10.1021/acssynbio.1c00592	journal	February 2022
A Web Interface for Codon Compression Halweg-Edwards, Andrea L.; Pines, Gur; Winkler, James D. ACS Synthetic Biology, Vol. 5, Issue 9 https://doi.org/10.1021/acssynbio.6b00026	journal	May 2016
Reducing Codon Redundancy and Screening Effort of Combinatorial Protein Libraries Created by Saturation Mutagenesis Kille, Sabrina; Acevedo-Rocha, Carlos G.; Parra, Loreto P. ACS Synthetic Biology, Vol. 2, Issue 2 https://doi.org/10.1021/sb300037w	journal	June 2012
Natural Selection and the Concept of a Protein Space Maynard Smith, John Nature, Vol. 225, Issue 5232 https://doi.org/10.1038/225563a0	journal	February 1970
Mutation effects predicted from sequence co-variation Hopf, Thomas A.; Ingraham, John B.; Poelwijk, Frank J. Nature Biotechnology, Vol. 35, Issue 2 https://doi.org/10.1038/nbt.3769	journal	January 2017
Molecular evolution by staggered extension process (StEP) in vitro recombination Zhao, Huimin; Giver, Lori; Shao, Zhixin Nature Biotechnology, Vol. 16, Issue 3 https://doi.org/10.1038/nbt0398-258	journal	March 1998
Enzymatic assembly of DNA molecules up to several hundred kilobases Gibson, Daniel G.; Young, Lei; Chuang, Ray-Yuan Nature Methods, Vol. 6, Issue 5, p. 343-345 https://doi.org/10.1038/nmeth.1318	journal	April 2009
Methods for the directed evolution of proteins Packer, Michael S.; Liu, David R. Nature Reviews Genetics, Vol. 16, Issue 7 https://doi.org/10.1038/nrg3927	journal	June 2015
Exploring protein fitness landscapes by directed evolution Romero, Philip A.; Arnold, Frances H. Nature Reviews Molecular Cell Biology, Vol. 10, Issue 12 https://doi.org/10.1038/nrm2805	journal	December 2009
Protein building blocks preserved by recombination Voigt, Christopher A.; Martinez, Carlos; Wang, Zhen-Gang Nature Structural Biology https://doi.org/10.1038/nsb805	journal	June 2002
Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions Aghazadeh, Amirali; Nisonoff, Hunter; Ocal, Orhan Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25371-3	journal	September 2021
Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production Greenhalgh, Jonathan C.; Fahlberg, Sarah A.; Pfleger, Brian F. Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25831-w	journal	October 2021
Deep diversification of an AAV capsid protein by machine learning Bryant, Drew H.; Bashir, Ali; Sinai, Sam Nature Biotechnology, Vol. 39, Issue 6 https://doi.org/10.1038/s41587-020-00793-4	journal	February 2021
Learning protein fitness models from evolutionary and assay-labeled data Hsu, Chloe; Nisonoff, Hunter; Fannjiang, Clara Nature Biotechnology https://doi.org/10.1038/s41587-021-01146-5	journal	January 2022
Deep generative models of genetic variation capture the effects of mutations Riesselman, Adam J.; Ingraham, John B.; Marks, Debora S. Nature Methods, Vol. 15, Issue 10 https://doi.org/10.1038/s41592-018-0138-4	journal	September 2018
Machine-learning-guided directed evolution for protein engineering Yang, Kevin K.; Wu, Zachary; Arnold, Frances H. Nature Methods, Vol. 16, Issue 8 https://doi.org/10.1038/s41592-019-0496-6	journal	July 2019
Machine learning-guided channelrhodopsin engineering enables minimally invasive optogenetics Bedbrook, Claire N.; Yang, Kevin K.; Robinson, J. Elliott Nature Methods, Vol. 16, Issue 11 https://doi.org/10.1038/s41592-019-0583-8	journal	October 2019
Unified rational protein engineering with sequence-based deep representation learning Alley, Ethan C.; Khimulya, Grigory; Biswas, Surojit Nature Methods, Vol. 16, Issue 12 https://doi.org/10.1038/s41592-019-0598-1	journal	October 2019
LM-GVP: an extensible sequence and structure informed deep learning framework for protein property prediction Wang, Zichen; Combs, Steven A.; Brand, Ryan Scientific Reports, Vol. 12, Issue 1 https://doi.org/10.1038/s41598-022-10775-y	journal	April 2022
Machine learning-enabled retrobiosynthesis of molecules Yu, Tianhao; Boob, Aashutosh Girish; Volk, Michael J. Nature Catalysis, Vol. 6, Issue 2 https://doi.org/10.1038/s41929-022-00909-w	journal	February 2023
Cluster learning-assisted directed evolution Qiu, Yuchi; Hu, Jian; Wei, Guo-Wei Nature Computational Science, Vol. 1, Issue 12 https://doi.org/10.1038/s43588-021-00168-y	journal	December 2021
Combining chemistry and protein engineering for new-to-nature biocatalysis Miller, David C.; Athavale, Soumitra V.; Arnold, Frances H. Nature Synthesis, Vol. 1, Issue 1 https://doi.org/10.1038/s44160-021-00008-x	journal	January 2022
Protein stability promotes evolvability Bloom, J. D.; Labthavikul, S. T.; Otey, C. R. Proceedings of the National Academy of Sciences, Vol. 103, Issue 15, p. 5869-5874 https://doi.org/10.1073/pnas.0510098103	journal	March 2006
Computational method to reduce the search space for directed protein evolution Voigt, C. A.; Mayo, S. L.; Arnold, F. H. Proceedings of the National Academy of Sciences, Vol. 98, Issue 7 https://doi.org/10.1073/pnas.051614498	journal	March 2001
Navigating the protein fitness landscape with Gaussian processes Romero, P. A.; Krause, A.; Arnold, F. H. Proceedings of the National Academy of Sciences, Vol. 110, Issue 3 https://doi.org/10.1073/pnas.1215251110	journal	December 2012
Directed evolution of the tryptophan synthase β-subunit for stand-alone function recapitulates allosteric activation Buller, Andrew R.; Brinkmann-Chen, Sabine; Romney, David K. Proceedings of the National Academy of Sciences, Vol. 112, Issue 47 https://doi.org/10.1073/pnas.1516401112	journal	November 2015
Machine learning-assisted directed protein evolution with combinatorial libraries Wu, Zachary; Kan, S. B. Jennifer; Lewis, Russell D. Proceedings of the National Academy of Sciences, Vol. 116, Issue 18 https://doi.org/10.1073/pnas.1901979116	journal	April 2019
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences Rives, Alexander; Meier, Joshua; Sercu, Tom Proceedings of the National Academy of Sciences, Vol. 118, Issue 15 https://doi.org/10.1073/pnas.2016239118	journal	April 2021
Optimization of Combinatorial Mutagenesis Parker, Andrew S.; Griswold, Karl E.; Bailey-Kellogg, Chris Journal of Computational Biology, Vol. 18, Issue 11 https://doi.org/10.1089/cmb.2011.0152	journal	November 2011
DeCoDe: degenerate codon design for complete protein-coding DNA libraries Shimko, Tyler C.; Fordyce, Polly M.; Orenstein, Yaron Bioinformatics, Vol. 36, Issue 11 https://doi.org/10.1093/bioinformatics/btaa162	journal	March 2020
CoLiDe: Combinatorial Library Design tool for probing protein sequence space Tretyachenko, Vyacheslav; Voráček, Václav; Souček, Radko Bioinformatics, Vol. 37, Issue 4 https://doi.org/10.1093/bioinformatics/btaa804	journal	September 2020
SwiftLib: rapid degenerate-codon-library optimization through dynamic programming Jacobs, Timothy M.; Yumerefendi, Hayretin; Kuhlman, Brian Nucleic Acids Research, Vol. 43, Issue 5 https://doi.org/10.1093/nar/gku1323	journal	December 2014
Automated design of degenerate codon libraries Mena, Marco A.; Daugherty, Patrick S. Protein Engineering, Design and Selection, Vol. 18, Issue 12 https://doi.org/10.1093/protein/gzi061	journal	October 2005
MSA Transformer Rao, Roshan; Liu, Jason; Verkuil, Robert bioRxiv https://doi.org/10.1101/2021.02.12.430858	preprint	August 2021
Language models enable zero-shot prediction of the effects of mutations on protein function Meier, Joshua; Rao, Roshan; Verkuil, Robert https://doi.org/10.1101/2021.07.09.450648	preprint	November 2021
Optimal Design of Stochastic DNA Synthesis Protocols based on Generative Sequence Models Weinstein, Eli N.; Amin, Alan N.; Grathwohl, Will https://doi.org/10.1101/2021.10.28.466307	posted_content	October 2021
Optimal trade-off control in machine learning-based library design, with application to adeno-associated virus (AAV) for gene therapy Zhu, Danqing; Brookes, David H.; Busia, Akosua https://doi.org/10.1101/2021.11.02.467003	posted_content	September 2022
Convolutions are competitive with transformers for protein sequence pretraining Yang, Kevin K.; Fusi, Nicolo K.; Lu, Alex X. BioRxiv https://doi.org/10.1101/2022.05.19.492714	preprint	February 2024
Masked inverse folding with sequence transfer for protein representation learning Yang, Kevin K.; Yeh, Hugh; Zanichelli, Niccolò bioRxiv https://doi.org/10.1101/2022.05.25.493516	preprint	March 2023
Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design Thomas, Neil; Agarwala, Atish; Belanger, David bioRxiv https://doi.org/10.1101/2022.10.28.514293	journal	October 2022
ProT-VAE: Protein Transformer Variational AutoEncoder for Functional Protein Design Sevgen, Emre; Moller, Joshua; Lange, Adrian bioRxiv https://doi.org/10.1101/2023.01.23.525232	preprint	January 2023
Protein Fitness Prediction is Impacted by the Interplay of Language Models, Ensemble Learning, and Sampling Methods Mardikoraem, Mehrsa; Woldring, Daniel https://doi.org/10.1101/2023.02.09.527362	posted_content	February 2023
ProtWave-VAE: Integrating autoregressive sampling with latent-based inference for data-driven protein design Praljak, Niksa; Lian, Xinran; Ranganathan, Rama https://doi.org/10.1101/2023.04.23.537971	posted_content	April 2023
Evaluating Protein Transfer Learning with TAPE Rao, Roshan; Bhattacharya, Nicholas; Thomas, Neil bioRxiv https://doi.org/10.1101/676825	preprint	June 2019
Pareto Optimization of Combinatorial Mutagenesis Libraries Verma, Deeptak; Grigoryan, Gevorg; Bailey-Kellogg, Chris IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 16, Issue 4 https://doi.org/10.1109/TCBB.2018.2858794	journal	July 2019
Enzyme function prediction using contrastive learning Yu, Tianhao; Cui, Haiyang; Li, Jianan Canal Science, Vol. 379, Issue 6639 https://doi.org/10.1126/science.adf2465	journal	March 2023
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
Machine learning to design integral membrane channelrhodopsins for efficient eukaryotic expression and plasma membrane localization Bedbrook, Claire N.; Yang, Kevin K.; Rice, Austin J. PLOS Computational Biology, Vol. 13, Issue 10 https://doi.org/10.1371/journal.pcbi.1005786	journal	October 2017
Adaptation in protein fitness landscapes is facilitated by indirect paths Wu, Nicholas C.; Dai, Lei; Olson, C. Anders eLife, Vol. 5 https://doi.org/10.7554/eLife.16965	journal	July 2016

Similar Records

evSeq: Cost-Effective Amplicon Sequencing of Every Variant in a Protein Library

Journal Article · Wed Feb 16 23:00:00 EST 2022 · ACS Synthetic Biology · OSTI ID:1853986

A Robust and Versatile Method of Combinatorial Chemical Synthesis of Gene Libraries via Hierarchical Assembly of Partially Randomized Modules

Journal Article · Thu Sep 10 00:00:00 EDT 2015 · PLoS ONE · OSTI ID:1627763

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
degenerate codon
directed evolution
genetics
machine learning
monomers
mutagenesis
optimization
peptides and proteins
protein engineering

DeCOIL: Optimization of Degenerate Codon Libraries for Machine Learning-Assisted Protein Engineering

Citation Formats

References (63)

Similar Records

Related Subjects