{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T03:09:36Z","timestamp":1791774576390,"version":"4.3.4"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA0910800"],"award-info":[{"award-number":["2021YFA0910800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFA0908500"],"award-info":[{"award-number":["2020YFA0908500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32071428"],"award-info":[{"award-number":["32071428"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Directed protein evolution applies repeated rounds of genetic mutagenesis and phenotypic screening and is often limited by experimental throughput. Through in silico prioritization of mutant sequences, machine learning has been applied to reduce wet lab burden to a level practical for human researchers. On the other hand, robotics permits large batches and rapid iterations for protein engineering cycles, but such capacities have not been well exploited in existing machine learning-assisted directed evolution approaches. Here, we report a scalable and batched method, Bayesian Optimization-guided EVOlutionary (BO-EVO) algorithm, to guide multiple rounds of robotic experiments to explore protein fitness landscapes of combinatorial mutagenesis libraries. We first examined various design specifications based on an empirical landscape of protein G domain B1. Then, BO-EVO was successfully generalized to another empirical landscape of an Escherichia coli kinase PhoQ, as well as simulated NK landscapes with up to moderate epistasis. This approach was then applied to guide robotic library creation and screening to engineer enzyme specificity of RhlA, a key biosynthetic enzyme for rhamnolipid biosurfactants. A 4.8-fold improvement in producing a target rhamnolipid congener was achieved after examining less than 1% of all possible mutants after four iterations. Overall, BO-EVO proves to be an efficient and general approach to guide combinatorial protein engineering without prior knowledge.<\/jats:p>","DOI":"10.1093\/bib\/bbac570","type":"journal-article","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T09:05:12Z","timestamp":1669194312000},"source":"Crossref","is-referenced-by-count":68,"title":["Protein engineering via Bayesian optimization-guided evolutionary algorithm and robotic experiments"],"prefix":"10.1093","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9837-290X","authenticated-orcid":false,"given":"Ruyun","family":"Hu","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihao","family":"Fu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"},{"name":"CAS Key Laboratory for Quantitative Engineering Biology, Shenzhen Institute of Synthetic Biology , Shenzhen 518055, China"},{"name":"University of Chinese Academy of Sciences , Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongcan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"},{"name":"CAS Key Laboratory for Quantitative Engineering Biology, Shenzhen Institute of Synthetic Biology , Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2985-9014","authenticated-orcid":false,"given":"Tong","family":"Si","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"},{"name":"CAS Key Laboratory for Quantitative Engineering Biology, Shenzhen Institute of Synthetic Biology , Shenzhen 518055, China"},{"name":"University of Chinese Academy of Sciences , Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,12,23]]},"reference":[{"key":"2023011917105487400_ref1","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1038\/nrm2805","article-title":"Exploring protein fitness landscapes by directed evolution","volume":"10","author":"Romero","year":"2009","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2023011917105487400_ref2","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1038\/35070613","article-title":"Functional proteins from a random-sequence library","volume":"410","author":"Keefe","year":"2001","journal-title":"Nature"},{"key":"2023011917105487400_ref3","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.jtbi.2005.05.001","article-title":"The distribution of fitness effects among beneficial mutations in Fisher\u2019s geometric model of adaptation","volume":"238","author":"Orr","year":"2006","journal-title":"J Theor Biol"},{"key":"2023011917105487400_ref4","doi-asserted-by":"crossref","first-page":"5562","DOI":"10.1038\/s41467-021-25826-7","article-title":"Epistasis shapes the fitness landscape of an allosteric specificity switch","volume":"12","author":"Nishikawa","year":"2021","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref5","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1038\/nature06879","article-title":"Kemp elimination catalysts by computational enzyme design","volume":"453","author":"R\u00f6thlisberger","year":"2008","journal-title":"Nature"},{"key":"2023011917105487400_ref6","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-021-04184-w","article-title":"De novo protein design by deep network hallucination","volume":"600","author":"Anishchenko","year":"2021","journal-title":"Nature"},{"key":"2023011917105487400_ref7","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.1073\/pnas.0808220106","article-title":"Rational stabilization of enzymes by computational redesign of surface charge-charge interactions","volume":"106","author":"Gribenko","year":"2009","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2023011917105487400_ref8","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.1002\/prot.25599","article-title":"TKSA-MC: a web server for rational mutation through the optimization of protein charge interactions","volume":"86","author":"Contessoto","year":"2018","journal-title":"Proteins Struct Funct Bioinforma"},{"key":"2023011917105487400_ref9","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1093\/bioinformatics\/btx697","article-title":"PStab: prediction of stable mutants, unfolding curves, stability maps and protein electrostatic frustration","volume":"34","author":"Gopi","year":"2018","journal-title":"Bioinformatics"},{"key":"2023011917105487400_ref10","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1021\/ar960017f","article-title":"Design by directed evolution","volume":"31","author":"Arnold","year":"1998","journal-title":"Acc Chem Res"},{"key":"2023011917105487400_ref11","article-title":"A primer on model-guided exploration of fitness landscapes for biological sequence design","volume-title":"arXiv preprint arXiv:2010.10614","author":"Sinai"},{"key":"2023011917105487400_ref12","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1093\/bib\/bbz071","article-title":"A critical review of five machine learning-based algorithms for predicting protein stability changes upon mutation","volume":"21","author":"Fang","year":"2020","journal-title":"Brief Bioinform"},{"key":"2023011917105487400_ref13","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaa074","article-title":"Predicting the stability of mutant proteins by computational approaches: an overview","volume":"22","author":"Marabotti","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023011917105487400_ref14","doi-asserted-by":"crossref","first-page":"2104878118","DOI":"10.1073\/pnas.2104878118","article-title":"Neural networks to learn protein sequence-function relationships from deep mutational scanning data","volume":"118","author":"Gelman","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023011917105487400_ref15","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.cels.2020.09.007","article-title":"Leveraging uncertainty in machine learning accelerates biological discovery and design","volume":"11","author":"Hie","year":"2020","journal-title":"Cell Syst"},{"key":"2023011917105487400_ref16","doi-asserted-by":"crossref","first-page":"8852","DOI":"10.1073\/pnas.1901979116","article-title":"Machine learning-assisted directed protein evolution with combinatorial libraries","volume":"116","author":"Wu","year":"2019","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023011917105487400_ref17","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkaa1100","article-title":"UniProt: The universal protein knowledgebase in 2021","volume":"49","author":"Bateman","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023011917105487400_ref18","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat Methods"},{"key":"2023011917105487400_ref19","doi-asserted-by":"crossref","DOI":"10.1101\/676825","article-title":"Evaluating protein transfer learning with TAPE","volume-title":"Advances in neural information processing systems","author":"Rao"},{"key":"2023011917105487400_ref20","doi-asserted-by":"crossref","article-title":"Language models enable zero-shot prediction of the effects of mutations on protein function","author":"Meier","DOI":"10.1101\/2021.07.09.450648"},{"key":"2023011917105487400_ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: towards cracking the language of lifes code through self-supervised deep learning and high performance computing","volume":"14","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023011917105487400_ref22","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1016\/j.cels.2021.07.008","article-title":"Informed training set design enables efficient machine learning-assisted directed protein evolution","volume":"12","author":"Wittmann","year":"2021","journal-title":"Cell Syst"},{"key":"2023011917105487400_ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-25976-8","article-title":"ECNet is an evolutionary context-integrated deep learning framework for protein engineering","volume":"12","author":"Luo","year":"2021","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref24","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1038\/s41592-021-01100-y","article-title":"Low-N protein engineering with data-efficient deep learning","volume":"18","author":"Biswas","year":"2021","journal-title":"Nat Methods"},{"key":"2023011917105487400_ref25","first-page":"1038","article-title":"Building a global alliance of biofoundries","volume":"10","author":"Hillson","year":"2019","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref26","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.ymben.2017.06.003","article-title":"Engineering biological systems using automated biofoundries","volume":"42","author":"Chao","year":"2017","journal-title":"Metab Eng"},{"key":"2023011917105487400_ref27","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.copbio.2021.01.010","article-title":"Accelerating strain engineering in biofuel research via build and test automation of synthetic biology","volume":"67","author":"Zhang","year":"2021","journal-title":"Curr Opin Biotechnol"},{"key":"2023011917105487400_ref28","doi-asserted-by":"crossref","first-page":"7581","DOI":"10.1039\/D2SC01637K","article-title":"Directed evolution of a cyclodipeptide synthase with new activities via label-free mass spectrometric screening","volume":"13","author":"Zhang","year":"2022","journal-title":"Chem Sci"},{"key":"2023011917105487400_ref29","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1002\/bit.25925","article-title":"Fully automatized high-throughput enzyme library screening using a robotic platform","volume":"113","author":"D\u00f6rr","year":"2016","journal-title":"Biotechnol Bioeng"},{"key":"2023011917105487400_ref30","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: a review of Bayesian optimization","volume":"104","author":"Shahriari","year":"2016","journal-title":"Proc IEEE"},{"key":"2023011917105487400_ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-25831-w","article-title":"Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production","volume":"12","author":"Greenhalgh","year":"2021","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-13189-z","article-title":"Towards a fully automated algorithm driven platform for biosystems design","volume":"10","author":"HamediRad","year":"2019","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref33","doi-asserted-by":"crossref","first-page":"4879","DOI":"10.1038\/s41467-020-18008-4","article-title":"A machine learning automated recommendation tool for synthetic biology","volume":"11","author":"Radivojevi\u0107","year":"2020","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref34","doi-asserted-by":"crossref","first-page":"4880","DOI":"10.1038\/s41467-020-17910-1","article-title":"Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism","volume":"11","author":"Zhang","year":"2020","journal-title":"Nat Commun"},{"key":"2023011917105487400_ref35","doi-asserted-by":"crossref","first-page":"e16965","DOI":"10.7554\/eLife.16965","article-title":"Adaptation in protein fitness landscapes is facilitated by indirect paths","volume":"5","author":"Wu","year":"2016","journal-title":"Elife"},{"key":"2023011917105487400_ref36","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1126\/science.1257360","article-title":"Pervasive degeneracy and epistasis in a protein-protein interface","volume":"347","author":"Podgornaia","year":"2015","journal-title":"Science"},{"key":"2023011917105487400_ref37","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0022-5193(89)80019-0","article-title":"The NK model of rugged fitness landscapes and its application to maturation of the immune response","volume":"141","author":"Kauffman","year":"1989","journal-title":"J Theor Biol"},{"key":"2023011917105487400_ref38","first-page":"32","article-title":"Gaussian processes for machine learning","volume":"7","author":"Rasmussen","year":"2006","journal-title":"Adapt Comput Mach Learn"},{"key":"2023011917105487400_ref39","first-page":"7576","article-title":"GPyTorch: blackbox matrix-matrix Gaussian process inference with GPU acceleration","volume":"31","author":"Gardner","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023011917105487400_ref40","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","article-title":"Asymptotically efficient adaptive allocation rules","volume":"6","author":"Lai","year":"1985","journal-title":"Adv Appl Math"},{"key":"2023011917105487400_ref41","doi-asserted-by":"crossref","first-page":"3250","DOI":"10.1109\/TIT.2011.2182033","article-title":"Information-theoretic regret bounds for Gaussian process optimization in the bandit setting","volume":"58","author":"Srinivas","year":"2012","journal-title":"IEEE Trans Inf Theory"},{"key":"2023011917105487400_ref42","first-page":"1","article-title":"Biological Sequence Design using Batched Bayesian Optimization","author":"Belanger","year":"2019"},{"key":"2023011917105487400_ref43","article-title":"AdaLead: a simple and robust adaptive greedy search algorithm for sequence design","volume-title":"arXiv preprint arXiv:2010.02141","author":"Sinai"},{"key":"2023011917105487400_ref44","doi-asserted-by":"crossref","first-page":"P01005","DOI":"10.1088\/1742-5468\/2013\/01\/P01005","article-title":"Quantitative analyses of empirical fitness landscapes","volume":"2013","author":"Szendro","year":"2013","journal-title":"J Stat Mech Theory Exp"},{"key":"2023011917105487400_ref45","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1093\/protein\/14.9.633","article-title":"A cross-section of the fitness landscape of dihydrofolate reductase","volume":"14","author":"Aita","year":"2001","journal-title":"Protein Eng"},{"key":"2023011917105487400_ref46","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1111\/jam.12515","article-title":"Engineering the biosynthesis of novel rhamnolipids in Escherichia coli for enhanced oil recovery","volume":"117","author":"Han","year":"2014","journal-title":"J Appl Microbiol"},{"key":"2023011917105487400_ref47","doi-asserted-by":"crossref","first-page":"4036","DOI":"10.1111\/febs.14954","article-title":"Semi-rational evolution of the 3-(3-hydroxyalkanoyloxy)alkanoate (HAA) synthase RhlA to improve rhamnolipid production in Pseudomonas aeruginosa and Burkholderia glumae","volume":"286","author":"Dulcey","year":"2019","journal-title":"FEBS J"},{"key":"2023011917105487400_ref48","doi-asserted-by":"crossref","first-page":"12466","DOI":"10.1021\/jacs.7b04641","article-title":"Profiling of microbial colonies for high-throughput engineering of multistep enzymatic reactions via optically guided matrix-assisted laser desorption\/ionization mass spectrometry","volume":"139","author":"Si","year":"2017","journal-title":"J Am Chem Soc"},{"key":"2023011917105487400_ref49","doi-asserted-by":"crossref","first-page":"102725","DOI":"10.1016\/j.copbio.2022.102725","article-title":"Towards one sample per second for mass spectrometric screening of engineered microbial strains","volume":"76","author":"Fu","year":"2022","journal-title":"Curr Opin Biotechnol"},{"key":"2023011917105487400_ref50","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1038\/s43588-021-00168-y","article-title":"Cluster learning-assisted directed evolution","volume":"1","author":"Qiu","year":"2021","journal-title":"Nat Comput Sci"},{"key":"2023011917105487400_ref51","first-page":"1","article-title":"ODBO: Bayesian optimization with search space prescreening for directed protein evolution","volume-title":"arXiv preprint arXiv:2205.09548","author":"Cheng","year":"2022"},{"key":"2023011917105487400_ref52","first-page":"1","article-title":"A survey on Bayesian deep learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM Comput Surv"},{"key":"2023011917105487400_ref53","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1021\/acscentsci.1c00546","article-title":"Evidential deep learning for guided molecular property prediction and discovery","volume":"7","author":"Soleimany","year":"2021","journal-title":"ACS Cent Sci"},{"key":"2023011917105487400_ref54","doi-asserted-by":"crossref","first-page":"107926","DOI":"10.1016\/j.biotechadv.2022.107926","article-title":"Hot spots-making directed evolution easier","volume":"56","author":"Yu","year":"2022","journal-title":"Biotechnol Adv"},{"key":"2023011917105487400_ref55","doi-asserted-by":"crossref","first-page":"2927","DOI":"10.1021\/acssynbio.0c00345","article-title":"Discovery of novel gain-of-function mutations guided by structure-based deep learning","volume":"9","author":"Shroff","year":"2020","journal-title":"ACS Synth Biol"},{"key":"2023011917105487400_ref56","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1038\/s41586-022-04599-z","article-title":"Machine learning-aided engineering of hydrolases for PET depolymerization","volume":"604","author":"Lu","year":"2022","journal-title":"Nature"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac570\/48782188\/bbac570.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac570\/48782188\/bbac570.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T12:30:42Z","timestamp":1674131442000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac570\/6958505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,19]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac570","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.08.11.503535","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1]]},"published":{"date-parts":[[2022,12,23]]},"article-number":"bbac570"}}