{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:50:26Z","timestamp":1782989426180,"version":"3.54.5"},"reference-count":47,"publisher":"National Academy of Sciences","issue":"18","license":[{"start":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T00:00:00Z","timestamp":1570838400000},"content-version":"vor","delay-in-days":183,"URL":"https:\/\/www.pnas.org\/site\/aboutpnas\/licenses.xhtml"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["GRF2017227007"],"award-info":[{"award-number":["GRF2017227007"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Rothenberg Innovation Initiative","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"Jacobs Institute for Molecular Engineering for Medicine","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2019,4,30]]},"abstract":"<jats:p>\n                    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\u2013H 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%\n                    <jats:italic>ee<\/jats:italic>\n                    (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.\n                  <\/jats:p>","DOI":"10.1073\/pnas.1901979116","type":"journal-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T15:16:21Z","timestamp":1555427781000},"page":"8852-8858","update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":567,"title":["Machine learning-assisted directed protein evolution with combinatorial libraries"],"prefix":"10.1073","volume":"116","author":[{"given":"Zachary","family":"Wu","sequence":"first","affiliation":[{"name":"Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA 91125;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. B. Jennifer","family":"Kan","sequence":"additional","affiliation":[{"name":"Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA 91125;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5776-7347","authenticated-orcid":false,"given":"Russell D.","family":"Lewis","sequence":"additional","affiliation":[{"name":"Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA 91125"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruce J.","family":"Wittmann","sequence":"additional","affiliation":[{"name":"Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA 91125"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frances H.","family":"Arnold","sequence":"additional","affiliation":[{"name":"Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA 91125;"},{"name":"Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA 91125"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2019,4,12]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.sbi.2018.08.004","article-title":"Molecular modeling of conformational dynamics and its role in enzyme evolution","volume":"52","author":"Petrovi\u0107 D","year":"2018","unstructured":"D Petrovi\u0107, SCL Kamerlin, Molecular modeling of conformational dynamics and its role in enzyme evolution. Curr Opin Struct Biol 52, 50\u201357 (2018).","journal-title":"Curr Opin Struct Biol"},{"key":"e_1_3_4_2_2","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1038\/nrm2805","article-title":"Exploring protein fitness landscapes by directed evolution","volume":"10","author":"Romero PA","year":"2009","unstructured":"PA Romero, FH Arnold, Exploring protein fitness landscapes by directed evolution. Nat Rev Mol Cell Biol 10, 866\u2013876 (2009).","journal-title":"Nat Rev Mol Cell Biol"},{"key":"e_1_3_4_3_2","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.sbi.2017.09.002","article-title":"Enzyme engineering: Reaching the maximal catalytic efficiency peak","volume":"47","author":"Goldsmith M","year":"2017","unstructured":"M Goldsmith, DS Tawfik, Enzyme engineering: Reaching the maximal catalytic efficiency peak. Curr Opin Struct Biol 47, 140\u2013150 (2017).","journal-title":"Curr Opin Struct Biol"},{"key":"e_1_3_4_4_2","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1146\/annurev-biochem-062917-012034","article-title":"Directed evolution of protein catalysts","volume":"87","author":"Zeymer C","year":"2018","unstructured":"C Zeymer, D Hilvert, Directed evolution of protein catalysts. Annu Rev Biochem 87, 131\u2013157 (2018).","journal-title":"Annu Rev Biochem"},{"key":"e_1_3_4_5_2","first-page":"87","volume-title":"Computational Tools for Chemical Biology","author":"Garcia-Borr\u00e1s M","year":"2018","unstructured":"M Garcia-Borr\u00e1s, KN Houk, G Jim\u00e9nez-Oses, Computational design of protein function. Computational Tools for Chemical Biology, ed S Mart\u00edn-Santamar\u00eda (Royal Society of Chemistry, London), pp. 87\u2013107 (2018)."},{"key":"e_1_3_4_6_2","doi-asserted-by":"crossref","first-page":"7308","DOI":"10.1073\/pnas.1807027115","article-title":"Catalytic iron-carbene intermediate revealed in a cytochrome c carbene transferase","volume":"115","author":"Lewis RD","year":"2018","unstructured":"RD Lewis, , Catalytic iron-carbene intermediate revealed in a cytochrome c carbene transferase. Proc Natl Acad Sci USA 115, 7308\u20137313 (2018).","journal-title":"Proc Natl Acad Sci USA"},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1126\/science.278.5335.82","article-title":"De novo protein design: Fully automated sequence selection","volume":"278","author":"Dahiyat BI","year":"1997","unstructured":"BI Dahiyat, SL Mayo, De novo protein design: Fully automated sequence selection. Science 278, 82\u201387 (1997).","journal-title":"Science"},{"key":"e_1_3_4_8_2","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.molcel.2018.08.033","article-title":"Automated design of efficient and functionally diverse enzyme repertoires","volume":"72","author":"Khersonsky O","year":"2018","unstructured":"O Khersonsky, , Automated design of efficient and functionally diverse enzyme repertoires. Mol Cell 72, 178\u2013186.e5 (2018).","journal-title":"Mol Cell"},{"key":"e_1_3_4_9_2","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1107\/S2052252516018017","article-title":"CADEE: Computer-aided directed evolution of enzymes","volume":"4","author":"Amrein BA","year":"2017","unstructured":"BA Amrein, , CADEE: Computer-aided directed evolution of enzymes. IUCrJ 4, 50\u201364 (2017).","journal-title":"IUCrJ"},{"key":"e_1_3_4_10_2","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy KP","year":"2012","unstructured":"KP Murphy Machine Learning: A Probabilistic Perspective (MIT Press, Cambridge, MA, 2012)."},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: Trends, perspectives, and prospects","volume":"349","author":"Jordan MI","year":"2015","unstructured":"MI Jordan, TM Mitchell, Machine learning: Trends, perspectives, and prospects. Science 349, 255\u2013260 (2015).","journal-title":"Science"},{"key":"e_1_3_4_12_2","unstructured":"D Silver Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv:1712.01815v1. (2017)."},{"key":"e_1_3_4_13_2","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1038\/nbt1286","article-title":"Improving catalytic function by ProSAR-driven enzyme evolution","volume":"25","author":"Fox RJ","year":"2007","unstructured":"RJ Fox, , Improving catalytic function by ProSAR-driven enzyme evolution. Nat Biotechnol 25, 338\u2013344 (2007).","journal-title":"Nat Biotechnol"},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","first-page":"E193","DOI":"10.1073\/pnas.1215251110","article-title":"Navigating the protein fitness landscape with Gaussian processes","volume":"110","author":"Romero PA","year":"2013","unstructured":"PA Romero, A Krause, FH Arnold, Navigating the protein fitness landscape with Gaussian processes. Proc Natl Acad Sci USA 110, E193\u2013E201 (2013).","journal-title":"Proc Natl Acad Sci USA"},{"key":"e_1_3_4_15_2","unstructured":"KK Yang Z Wu FH Arnold Machine learning in protein engineering. arXiv:1811.10775v1. (2018)."},{"key":"e_1_3_4_16_2","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 NC","year":"2016","unstructured":"NC Wu, L Dai, CA Olson, JO Lloyd-Smith, R Sun, Adaptation in protein fitness landscapes is facilitated by indirect paths. eLife 5, e16965 (2016).","journal-title":"eLife"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","first-page":"e34","DOI":"10.1093\/nar\/gku1323","article-title":"SwiftLib: Rapid degenerate-codon-library optimization through dynamic programming","volume":"43","author":"Jacobs TM","year":"2015","unstructured":"TM Jacobs, H Yumerefendi, B Kuhlman, A Leaver-Fay, SwiftLib: Rapid degenerate-codon-library optimization through dynamic programming. Nucleic Acids Res 43, e34 (2015).","journal-title":"Nucleic Acids Res"},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1002\/cbic.200800298","article-title":"Addressing the numbers problem in directed evolution","volume":"9","author":"Reetz MT","year":"2008","unstructured":"MT Reetz, D Kahakeaw, R Lohmer, Addressing the numbers problem in directed evolution. ChemBioChem 9, 1797\u20131804 (2008).","journal-title":"ChemBioChem"},{"key":"e_1_3_4_19_2","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.bioeng.2004.11.002","article-title":"Mathematical expressions useful in the construction, description and evaluation of protein libraries","volume":"22","author":"Bosley AD","year":"2005","unstructured":"AD Bosley, M Ostermeier, Mathematical expressions useful in the construction, description and evaluation of protein libraries. Biomol Eng 22, 57\u201361 (2005).","journal-title":"Biomol Eng"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.1126\/science.aah6219","article-title":"Directed evolution of cytochrome c for carbon\u2013silicon bond formation: Bringing silicon to life","volume":"354","author":"Kan SBJ","year":"2016","unstructured":"SBJ Kan, RD Lewis, K Chen, FH Arnold, Directed evolution of cytochrome c for carbon\u2013silicon bond formation: Bringing silicon to life. Science 354, 1048\u20131051 (2016).","journal-title":"Science"},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/S1359-6446(03)02726-0","article-title":"Chemistry challenges in lead optimization: Silicon isosteres in drug discovery","volume":"8","author":"Showell GA","year":"2003","unstructured":"GA Showell, JS Mills, Chemistry challenges in lead optimization: Silicon isosteres in drug discovery. Drug Discov Today 8, 551\u2013556 (2003).","journal-title":"Drug Discov Today"},{"key":"e_1_3_4_22_2","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1021\/jm3010114","article-title":"Organosilicon molecules with medicinal applications","volume":"56","author":"Franz AK","year":"2013","unstructured":"AK Franz, SO Wilson, Organosilicon molecules with medicinal applications. J Med Chem 56, 388\u2013405 (2013).","journal-title":"J Med Chem"},{"key":"e_1_3_4_23_2","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1038\/nature17191","article-title":"Copper-catalysed enantioselective stereodivergent synthesis of amino alcohols","volume":"532","author":"Shi SL","year":"2016","unstructured":"SL Shi, ZL Wong, SL Buchwald, Copper-catalysed enantioselective stereodivergent synthesis of amino alcohols. Nature 532, 353\u2013356 (2016).","journal-title":"Nature"},{"key":"e_1_3_4_24_2","doi-asserted-by":"crossref","first-page":"4802","DOI":"10.1002\/anie.201107204","article-title":"Enantiomeric natural products: Occurrence and biogenesis","volume":"51","author":"Finefield JM","year":"2012","unstructured":"JM Finefield, DH Sherman, M Kreitman, RM Williams, Enantiomeric natural products: Occurrence and biogenesis. Angew Chem Int Ed Engl 51, 4802\u20134836 (2012).","journal-title":"Angew Chem Int Ed Engl"},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","first-page":"5716","DOI":"10.1073\/pnas.0306866101","article-title":"Controlling the enantioselectivity of enzymes by directed evolution: Practical and theoretical ramifications","volume":"101","author":"Reetz MT","year":"2004","unstructured":"MT Reetz, Controlling the enantioselectivity of enzymes by directed evolution: Practical and theoretical ramifications. Proc Natl Acad Sci USA 101, 5716\u20135722 (2004).","journal-title":"Proc Natl Acad Sci USA"},{"key":"e_1_3_4_26_2","doi-asserted-by":"crossref","first-page":"D158","DOI":"10.1093\/nar\/gkw1099","article-title":"UniProt: The universal protein knowledgebase","volume":"45","author":"The UniProt Consortium","year":"2017","unstructured":"; The UniProt Consortium, UniProt: The universal protein knowledgebase. Nucleic Acids Res 45, D158\u2013D169 (2017).","journal-title":"Nucleic Acids Res"},{"key":"e_1_3_4_27_2","doi-asserted-by":"crossref","first-page":"5869","DOI":"10.1073\/pnas.0510098103","article-title":"Protein stability promotes evolvability","volume":"103","author":"Bloom JD","year":"2006","unstructured":"JD Bloom, ST Labthavikul, CR Otey, FH Arnold, Protein stability promotes evolvability. Proc Natl Acad Sci USA 103, 5869\u20135874 (2006).","journal-title":"Proc Natl Acad Sci USA"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1093\/protein\/gzg077","article-title":"Optimizing the search algorithm for protein engineering by directed evolution","volume":"16","author":"Fox R","year":"2003","unstructured":"R Fox, , Optimizing the search algorithm for protein engineering by directed evolution. Protein Eng 16, 589\u2013597 (2003).","journal-title":"Protein Eng"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1021\/sb300037w","article-title":"Reducing codon redundancy and screening effort of combinatorial protein libraries created by saturation mutagenesis","volume":"2","author":"Kille S","year":"2013","unstructured":"S Kille, , Reducing codon redundancy and screening effort of combinatorial protein libraries created by saturation mutagenesis. ACS Synth Biol 2, 83\u201392 (2013).","journal-title":"ACS Synth Biol"},{"key":"e_1_3_4_30_2","first-page":"1069","article-title":"Patentability of chemical and biotechnology inventions: A discrepancy in standards","volume":"81","author":"Lissy NA","year":"2003","unstructured":"NA Lissy, Patentability of chemical and biotechnology inventions: A discrepancy in standards. Washingt Univ Law Q 81, 1069\u20131095 (2003).","journal-title":"Washingt Univ Law Q"},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","first-page":"e1500921","DOI":"10.1126\/sciadv.1500921","article-title":"Environmental changes bridge evolutionary valleys","volume":"2","author":"Steinberg B","year":"2016","unstructured":"B Steinberg, M Ostermeier, Environmental changes bridge evolutionary valleys. Sci Adv 2, e1500921 (2016).","journal-title":"Sci Adv"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.jmb.2005.05.023","article-title":"Why high-error-rate random mutagenesis libraries are enriched in functional and improved proteins","volume":"350","author":"Drummond DA","year":"2005","unstructured":"DA Drummond, BL Iverson, G Georgiou, FH Arnold, Why high-error-rate random mutagenesis libraries are enriched in functional and improved proteins. J Mol Biol 350, 806\u2013816 (2005).","journal-title":"J Mol Biol"},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1038\/nature05385","article-title":"Robustness-epistasis link shapes the fitness landscape of a randomly drifting protein","volume":"444","author":"Bershtein S","year":"2006","unstructured":"S Bershtein, M Segal, R Bekerman, N Tokuriki, DS Tawfik, Robustness-epistasis link shapes the fitness landscape of a randomly drifting protein. Nature 444, 929\u2013932 (2006).","journal-title":"Nature"},{"key":"e_1_3_4_34_2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41586-018-0808-5","article-title":"Enzymatic assembly of carbon\u2013carbon bonds via iron-catalysed sp3 C\u2013H functionalization","volume":"565","author":"Zhang RK","year":"2019","unstructured":"RK Zhang, , Enzymatic assembly of carbon\u2013carbon bonds via iron-catalysed sp3 C\u2013H functionalization. Nature 565, 67\u201372 (2019).","journal-title":"Nature"},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1002\/prot.24374","article-title":"One contact for every twelve residues allows robust and accurate topology-level protein structure modeling","volume":"82","author":"Kim DE","year":"2014","unstructured":"DE Kim, , One contact for every twelve residues allows robust and accurate topology-level protein structure modeling. Proteins 82, 208\u2013218 (2014).","journal-title":"Proteins"},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1038\/nmeth.3027","article-title":"Deep mutational scanning: A new style of protein science","volume":"11","author":"Fowler DM","year":"2014","unstructured":"DM Fowler, S Fields, Deep mutational scanning: A new style of protein science. Nat Methods 11, 801\u2013807 (2014).","journal-title":"Nat Methods"},{"key":"e_1_3_4_37_2","unstructured":"S Sinai E Kelsic GM Church MA Nowak Variational auto-encoding of protein sequences. arXiv:1712.03346v3. (2017)."},{"key":"e_1_3_4_38_2","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1038\/s41592-018-0138-4","article-title":"Deep generative models of genetic variation capture the effects of mutations","volume":"15","author":"Riesselman AJ","year":"2018","unstructured":"AJ Riesselman, JB Ingraham, DS Marks, Deep generative models of genetic variation capture the effects of mutations. Nat Methods 15, 816\u2013822 (2018).","journal-title":"Nat Methods"},{"key":"e_1_3_4_39_2","unstructured":"DH Brookes J Listgarten Design by adaptive sampling. arXiv:1810.03714v3. (2018)."},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","first-page":"2014","DOI":"10.1021\/acssynbio.8b00155","article-title":"Machine-learning-guided mutagenesis for directed evolution of fluorescent proteins","volume":"7","author":"Saito Y","year":"2018","unstructured":"Y Saito, , Machine-learning-guided mutagenesis for directed evolution of fluorescent proteins. ACS Synth Biol 7, 2014\u20132022 (2018).","journal-title":"ACS Synth Biol"},{"key":"e_1_3_4_41_2","doi-asserted-by":"crossref","first-page":"16757","DOI":"10.1038\/s41598-018-35033-y","article-title":"A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes","volume":"8","author":"Cadet F","year":"2018","unstructured":"F Cadet, , A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes. Sci Rep 8, 16757 (2018).","journal-title":"Sci Rep"},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","first-page":"e0147596","DOI":"10.1371\/journal.pone.0147596","article-title":"Kinetic characterization of 100 glycoside hydrolase mutants enables the discovery of structural features correlated with kinetic constants","volume":"11","author":"Carlin DA","year":"2016","unstructured":"DA Carlin, , Kinetic characterization of 100 glycoside hydrolase mutants enables the discovery of structural features correlated with kinetic constants. PLoS One 11, e0147596 (2016).","journal-title":"PLoS One"},{"key":"e_1_3_4_43_2","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1021\/acs.jcim.7b00488","article-title":"Improved descriptors for the quantitative structure-activity relationship modeling of peptides and proteins","volume":"58","author":"Barley MH","year":"2018","unstructured":"MH Barley, NJ Turner, R Goodacre, Improved descriptors for the quantitative structure-activity relationship modeling of peptides and proteins. J Chem Inf Model 58, 234\u2013243 (2018).","journal-title":"J Chem Inf Model"},{"key":"e_1_3_4_44_2","doi-asserted-by":"crossref","first-page":"4138","DOI":"10.1093\/bioinformatics\/bty455","article-title":"Learned protein embeddings for machine learning","volume":"34","author":"Yang KK","year":"2018","unstructured":"KK Yang, Z Wu, CN Bedbrook, FH Arnold, Learned protein embeddings for machine learning. Bioinformatics 34, 4138 (2018).","journal-title":"Bioinformatics"},{"key":"e_1_3_4_45_2","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1002\/pro.3406","article-title":"ProtaBank\u202f: A repository for protein design and engineering data","volume":"27","author":"Wang CY","year":"2018","unstructured":"CY Wang, , ProtaBank\u202f: A repository for protein design and engineering data. Protein Sci 27, 1113\u20131124 (2018).","journal-title":"Protein Sci"},{"key":"e_1_3_4_46_2","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa F","year":"2011","unstructured":"F Pedregosa, , Scikit-learn: Machine learning in Python. J Mach Learn Res 12, 2825\u20132830 (2011).","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_47_2","doi-asserted-by":"crossref","first-page":"W296","DOI":"10.1093\/nar\/gky427","article-title":"SWISS-MODEL: Homology modelling of protein structures and complexes","volume":"46","author":"Waterhouse A","year":"2018","unstructured":"A Waterhouse, , SWISS-MODEL: Homology modelling of protein structures and complexes. Nucleic Acids Res 46, W296\u2013W303 (2018).","journal-title":"Nucleic Acids Res"}],"updated-by":[{"DOI":"10.1073\/pnas.1921770117","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2019,12,30]],"date-time":"2019-12-30T00:00:00Z","timestamp":1577664000000}}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.pnas.org\/syndication\/doi\/10.1073\/pnas.1901979116","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.1901979116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T15:13:15Z","timestamp":1654614795000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/full\/10.1073\/pnas.1901979116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,12]]},"references-count":47,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2019,4,30]]}},"alternative-id":["10.1073\/pnas.1901979116"],"URL":"https:\/\/doi.org\/10.1073\/pnas.1901979116","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,12]]},"assertion":[{"value":"2019-04-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}