{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:10:17Z","timestamp":1772136617579,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000057","name":"U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["GM129004"],"award-info":[{"award-number":["GM129004"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000057","name":"U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["GM126189"],"award-info":[{"award-number":["GM126189"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000121","name":"NSF | Directorate for Mathematical & Physical Sciences | Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-2052983"],"award-info":[{"award-number":["DMS-2052983"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000121","name":"NSF | Directorate for Mathematical & Physical Sciences | Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-1761320"],"award-info":[{"award-number":["DMS-1761320"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF | Directorate for Mathematical & Physical Sciences | Division of Mathematical Sciences"},{"DOI":"10.13039\/100000145","name":"NSF | Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-1900473"],"award-info":[{"award-number":["IIS-1900473"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences"},{"name":"MSU Foundation; Pfizer; Bristol-Myers Squibb 65109"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-021-00168-y","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T12:02:55Z","timestamp":1639051375000},"page":"809-818","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":70,"title":["Cluster learning-assisted directed evolution"],"prefix":"10.1038","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7058-6428","authenticated-orcid":false,"given":"Yuchi","family":"Qiu","sequence":"first","affiliation":[]},{"given":"Jian","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5781-2937","authenticated-orcid":false,"given":"Guo-Wei","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,9]]},"reference":[{"key":"168_CR1","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1146\/annurev-biochem-030409-143718","volume":"79","author":"OK Tawfik","year":"2010","unstructured":"Tawfik, O. K. & S, D. Enzyme promiscuity: a mechanistic and evolutionary perspective. Annu. Rev. Biochem. 79, 471\u2013505 (2010).","journal-title":"Annu. Rev. Biochem."},{"key":"168_CR2","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1016\/j.cels.2021.07.008","volume":"12","author":"BJ Wittmann","year":"2021","unstructured":"Wittmann, B. J., Yue, Y. & Arnold, F. H. Informed training set design enables efficient machine learning-assisted directed protein evolution. Cell Syst. 12, 1026\u20131045.e7 (2021).","journal-title":"Cell Syst."},{"key":"168_CR3","doi-asserted-by":"publisher","first-page":"8852","DOI":"10.1073\/pnas.1901979116","volume":"116","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Kan, S. J., Lewis, R. D., Wittmann, B. J. & Arnold, F. H. Machine learning-assisted directed protein evolution with combinatorial libraries. Proc. Natl Acad. Sci. USA 116, 8852\u20138858 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"168_CR4","doi-asserted-by":"publisher","first-page":"e16965","DOI":"10.7554\/eLife.16965","volume":"5","author":"NC Wu","year":"2016","unstructured":"Wu, N. C., Dai, L., Olson, C. A., Lloyd-Smith, J. O. & Sun, R. Adaptation in protein fitness landscapes is facilitated by indirect paths. eLife 5, e16965 (2016).","journal-title":"eLife"},{"key":"168_CR5","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1038\/s41592-019-0496-6","volume":"16","author":"KK Yang","year":"2019","unstructured":"Yang, K. K., Wu, Z. & Arnold, F. H. Machine-learning-guided directed evolution for protein engineering. Nat. Methods 16, 687\u2013694 (2019).","journal-title":"Nat. Methods"},{"key":"168_CR6","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/bs.mie.2020.05.005","volume":"643","author":"NE Siedhoff","year":"2020","unstructured":"Siedhoff, N. E., Schwaneberg, U. & Davari, M. D. Machine learning-assisted enzyme engineering. Methods Enzymol. 643, 281\u2013315 (2020).","journal-title":"Methods Enzymol."},{"key":"168_CR7","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.tips.2020.12.004","volume":"42","author":"H Narayanan","year":"2021","unstructured":"Narayanan, H. et al. Machine learning for biologics: opportunities for protein engineering, developability and formulation. Trends Pharmacol. Sci. 42, 151\u2013165 (2021).","journal-title":"Trends Pharmacol. Sci."},{"key":"168_CR8","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1021\/acscatal.9b04321","volume":"10","author":"S Mazurenko","year":"2019","unstructured":"Mazurenko, S., Prokop, Z. & Damborsky, J. Machine learning in enzyme engineering. ACS Catal. 10, 1210\u20131223 (2019).","journal-title":"ACS Catal."},{"key":"168_CR9","doi-asserted-by":"publisher","first-page":"1903093","DOI":"10.1002\/smll.201903093","volume":"16","author":"D Bojar","year":"2020","unstructured":"Bojar, D. & Fussenegger, M. The role of protein engineering in biomedical applications of mammalian synthetic biology. Small 16, 1903093 (2020).","journal-title":"Small"},{"key":"168_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.copbio.2019.08.010","volume":"64","author":"GB Kim","year":"2020","unstructured":"Kim, G. B., Kim, W. J., Kim, H. U. & Lee, S. Y. Machine learning applications in systems metabolic engineering. Curr. Opin. Biotechnol. 64, 1\u20139 (2020).","journal-title":"Curr. Opin. Biotechnol."},{"key":"168_CR11","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1186\/1471-2105-11-370","volume":"11","author":"J Tian","year":"2010","unstructured":"Tian, J., Wu, N., Chu, X. & Fan, Y. Predicting changes in protein thermostability brought about by single- or multi-site mutations. BMC Bioinformatics 11, 370 (2010).","journal-title":"BMC Bioinformatics"},{"key":"168_CR12","first-page":"3549","volume":"33","author":"Z Cang","year":"2017","unstructured":"Cang, Z. & Wei, G.-W. Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology. Bioinformatics 33, 3549\u20133557 (2017).","journal-title":"Bioinformatics"},{"key":"168_CR13","doi-asserted-by":"publisher","first-page":"2936","DOI":"10.1093\/bioinformatics\/btw361","volume":"32","author":"L Quan","year":"2016","unstructured":"Quan, L., Lv, Q. & Zhang, Y. STRUM: structure-based prediction of protein stability changes upon single-point mutation. Bioinformatics 32, 2936\u20132946 (2016).","journal-title":"Bioinformatics"},{"key":"168_CR14","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.1093\/bioinformatics\/bty166","volume":"34","author":"S Khurana","year":"2018","unstructured":"Khurana, S. et al. DeepSol: a deep learning framework for sequence-based protein solubility prediction. Bioinformatics 34, 2605\u20132613 (2018).","journal-title":"Bioinformatics"},{"key":"168_CR15","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.cels.2020.09.007","volume":"11","author":"B Hie","year":"2020","unstructured":"Hie, B., Bryson, B. D. & Berger, B. Leveraging uncertainty in machine learning accelerates biological discovery and design. Cell Syst. 11, 461\u2013477 (2020).","journal-title":"Cell Syst."},{"key":"168_CR16","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s42256-020-0149-6","volume":"2","author":"M Wang","year":"2020","unstructured":"Wang, M., Cang, Z. & Wei, G.-W. A topology-based network tree for the prediction of protein\u2013protein binding affinity changes following mutation. Nat. Mach. Intell. 2, 116\u2013123 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"168_CR17","first-page":"9689","volume":"32","author":"R Rao","year":"2019","unstructured":"Rao, R. et al. Evaluating protein transfer learning with tape. Adv. Neural Inf. Process. Syst. 32, 9689\u20139701 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"168_CR18","doi-asserted-by":"publisher","first-page":"2642","DOI":"10.1093\/bioinformatics\/bty178","volume":"34","author":"KK Yang","year":"2018","unstructured":"Yang, K. K., Wu, Z., Bedbrook, C. N. & Arnold, F. H. Learned protein embeddings for machine learning. Bioinformatics 34, 2642\u20132648 (2018).","journal-title":"Bioinformatics"},{"key":"168_CR19","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1038\/s41592-018-0138-4","volume":"15","author":"AJ Riesselman","year":"2018","unstructured":"Riesselman, A. J., Ingraham, J. B. & Marks, D. S. Deep generative models of genetic variation capture the effects of mutations. Nat. Methods 15, 816\u2013822 (2018).","journal-title":"Nat. Methods"},{"key":"168_CR20","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","volume":"16","author":"EC Alley","year":"2019","unstructured":"Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M. & Church, G. M. Unified rational protein engineering with sequence-based deep representation learning. Nat. Methods 16, 1315\u20131322 (2019).","journal-title":"Nat. Methods"},{"key":"168_CR21","unstructured":"Bepler, T. & Berger, B. Learning protein sequence embeddings using information from structure. In Proc. International Conference on Learning Representations (2018)."},{"key":"168_CR22","unstructured":"Rao, R. et al. MSA transformer. In Proc. 38th International Conference on Machine Learning Vol. 139, 8844\u20138856 (PMLR, 2021)."},{"key":"168_CR23","first-page":"281","volume":"16","author":"G Hamerly","year":"2004","unstructured":"Hamerly, G. & Elkan, C. Learning the k in k-means. Adv. Neural Inf. Process. Syst. 16, 281\u2013288 (2004).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"168_CR24","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey, B. J. & Dueck, D. Clustering by passing messages between data points. Science 315, 972\u2013976 (2007).","journal-title":"Science"},{"key":"168_CR25","doi-asserted-by":"publisher","first-page":"P10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","volume":"2008","author":"VD Blondel","year":"2008","unstructured":"Blondel, V. D., Guillaume, J.-L., Lambiotte, R. & Lefebvre, E. Fast unfolding of communities in large networks. J. Stat. Mech. 2008, P10008 (2008).","journal-title":"J. Stat. Mech."},{"key":"168_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3068335","volume":"42","author":"E Schubert","year":"2017","unstructured":"Schubert, E., Sander, J., Ester, M., Kriegel, H. P. & Xu, X. DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans. Database Syst. 42, 1\u201321 (2017).","journal-title":"ACM Trans. Database Syst."},{"key":"168_CR27","doi-asserted-by":"publisher","first-page":"9505","DOI":"10.1093\/nar\/gkaa725","volume":"48","author":"Y Sha","year":"2020","unstructured":"Sha, Y., Wang, S., Zhou, P. & Nie, Q. Inference and multiscale model of epithelial-to-mesenchymal transition via single-cell transcriptomic data. Nucleic Acids Res. 48, 9505\u20139520 (2020).","journal-title":"Nucleic Acids Res."},{"key":"168_CR28","doi-asserted-by":"crossref","unstructured":"Kuang, D., Ding, C. & Park, H. Symmetric nonnegative matrix factorization for graph clustering. In Proc. 2012 SIAM International Conference on Data Mining 106\u2013117 (SIAM, 2012).","DOI":"10.1137\/1.9781611972825.10"},{"key":"168_CR29","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.coisb.2021.02.002","volume":"25","author":"S Oller-Moreno","year":"2021","unstructured":"Oller-Moreno, S., Kloiber, K., Machart, P. & Bonn, S. Algorithmic advances in machine learning for single cell expression analysis. Curr. Opin. Syst. Biol. 25, 27\u201333 (2021).","journal-title":"Curr. Opin. Syst. Biol."},{"key":"168_CR30","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1016\/j.neucom.2017.06.053","volume":"267","author":"A Saxena","year":"2017","unstructured":"Saxena, A. et al. A review of clustering techniques and developments. Neurocomputing 267, 664\u2013681 (2017).","journal-title":"Neurocomputing"},{"key":"168_CR31","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.asoc.2017.11.045","volume":"64","author":"Y Zhong","year":"2018","unstructured":"Zhong, Y., Ma, A., Soon Ong, Y., Zhu, Z. & Zhang, L. Computational intelligence in optical remote sensing image processing. Appl. Soft Comput. 64, 75\u201393 (2018).","journal-title":"Appl. Soft Comput."},{"key":"168_CR32","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1002\/adsc.201900149","volume":"361","author":"G Li","year":"2019","unstructured":"Li, G., Dong, Y. & Reetz, M. T. Can machine learning revolutionize directed evolution of selective enzymes? Adv. Synth. Catal. 361, 2377\u20132386 (2019).","journal-title":"Adv. Synth. Catal."},{"key":"168_CR33","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.1021\/acssynbio.8b00155","volume":"7","author":"Y Saito","year":"2018","unstructured":"Saito, Y. et al. Machine-learning-guided mutagenesis for directed evolution of fluorescent proteins. ACS Synth. Biol. 7, 2014\u20132022 (2018).","journal-title":"ACS Synth. Biol."},{"key":"168_CR34","doi-asserted-by":"publisher","first-page":"e1005786","DOI":"10.1371\/journal.pcbi.1005786","volume":"13","author":"CN Bedbrook","year":"2017","unstructured":"Bedbrook, C. N., Yang, K. K., Rice, A. J., Gradinaru, V. & Arnold, F. H. Machine learning to design integral membrane channelrhodopsins for efficient eukaryotic expression and plasma membrane localization. PLoS Comput. Biol. 13, e1005786 (2017).","journal-title":"PLoS Comput. Biol."},{"key":"168_CR35","doi-asserted-by":"publisher","first-page":"E193","DOI":"10.1073\/pnas.1215251110","volume":"110","author":"PA Romero","year":"2013","unstructured":"Romero, P. A., Krause, A. & Arnold, F. H. 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":"168_CR36","doi-asserted-by":"publisher","unstructured":"Mason, D. M. et al. Deep learning enables therapeutic antibody optimization in mammalian cells by deciphering high-dimensional protein sequence space. bioRxiv https:\/\/doi.org\/10.1101\/617860 (2019).","DOI":"10.1101\/617860"},{"key":"168_CR37","unstructured":"Hie, B. L. & Yang, K. K. Adaptive machine learning for protein engineering. Preprint at https:\/\/arxiv.org\/abs\/2106.05466 (2021)."},{"key":"168_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2018.03.001","volume":"85","author":"E Schulz","year":"2018","unstructured":"Schulz, E., Speekenbrink, M. & Krause, A. A tutorial on Gaussian process regression: modelling, exploring and exploiting functions. J. Math. Psychol. 85, 1\u201316 (2018).","journal-title":"J. Math. Psychol."},{"key":"168_CR39","unstructured":"Srinivas, N., Krause, A., Kakade, S. & Seeger, M. Gaussian process optimization in the bandit setting: no regret and experimental design. In Proc. 27th International Conference on Machine Learning 1015\u20131022 (ACM, 2010)."},{"key":"168_CR40","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1038\/nbt.3769","volume":"35","author":"TA Hopf","year":"2017","unstructured":"Hopf, T. A. et al. Mutation effects predicted from sequence co-variation. Nat. Biotechnol. 35, 128\u2013135 (2017).","journal-title":"Nat. Biotechnol."},{"key":"168_CR41","doi-asserted-by":"publisher","unstructured":"Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2021.07.09.450648 (2021).","DOI":"10.1101\/2021.07.09.450648"},{"key":"168_CR42","unstructured":"Yang, K. K., Chen, Y., Lee, A. & Yue, Y. Batched stochastic Bayesian optimization via combinatorial constraints design. In Proc. 22nd International Conference on Artificial Intelligence and Statistics 3410\u20133419 (PMLR, 2019)."},{"key":"168_CR43","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1093\/nar\/27.1.368","volume":"27","author":"S Kawashima","year":"1999","unstructured":"Kawashima, S., Ogata, H. & Kanehisa, M. AAindex: amino acid index database. Nucleic Acids Res. 27, 368\u2013369 (1999).","journal-title":"Nucleic Acids Res."},{"key":"168_CR44","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1093\/bioinformatics\/btv345","volume":"31","author":"D Ofer","year":"2015","unstructured":"Ofer, D. & Linial, M. ProFET: feature engineering captures high-level protein functions. Bioinformatics 31, 3429\u20133436 (2015).","journal-title":"Bioinformatics"},{"key":"168_CR45","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1089\/cmb.2008.0173","volume":"16","author":"AG Georgiev","year":"2009","unstructured":"Georgiev, A. G. Interpretable numerical descriptors of amino acid space. J. Comput. Biol. 16, 703\u2013723 (2009).","journal-title":"J. Comput. Biol."},{"key":"168_CR46","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.sbi.2021.01.008","volume":"69","author":"BJ Wittmann","year":"2021","unstructured":"Wittmann, B. J., Johnston, K. E., Wu, Z. & Arnold, F. H. Advances in machine learning for directed evolution. Curr. Opin. Struct. Biol. 69, 11\u201318 (2021).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"168_CR47","first-page":"1655","volume":"12","author":"S Bubeck","year":"2011","unstructured":"Bubeck, S., Munos, R., Stoltz, G. & Szepesv\u00e1ri, C. X-armed bandits. J. Mach. Learn. Res. 12, 1655\u20131695 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"168_CR48","first-page":"783","volume":"24","author":"R Munos","year":"2011","unstructured":"Munos, R. Optimistic optimization of a deterministic function without the knowledge of its smoothness. Adv. Neural Inf. Process. Syst. 24, 783\u2013791 (2011).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"168_CR49","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.3390\/ijms21072563","volume":"21","author":"S Pahari","year":"2020","unstructured":"Pahari, S. et al. SAAMBE-3D: predicting effect of mutations on protein-protein interactions. Int. J. Mol. Sci. 21, 2563 (2020).","journal-title":"Int. J. Mol. Sci."},{"key":"168_CR50","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl Acad. Sci. USA 118, e2016239118 (2021).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"168_CR51","doi-asserted-by":"crossref","unstructured":"Strain-Damerell, C. & Burgess-Brown, N. A. in High-Throughput Protein Production and Purification 281\u2013296 (Springer, 2019).","DOI":"10.1007\/978-1-4939-9624-7_13"},{"key":"168_CR52","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1126\/science.1257360","volume":"347","author":"AI Podgornaia","year":"2015","unstructured":"Podgornaia, A. I. & Laub, M. T. Pervasive degeneracy and epistasis in a protein-protein interface. Science 347, 673\u2013677 (2015).","journal-title":"Science"},{"key":"168_CR53","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"168_CR54","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/0079-6107(72)90005-3","volume":"24","author":"A Zamyatnin","year":"1972","unstructured":"Zamyatnin, A. Protein volume in solution. Progr. Biophys. Mol. Biol. 24, 107\u2013123 (1972).","journal-title":"Progr. Biophys. Mol. Biol."},{"key":"168_CR55","doi-asserted-by":"crossref","unstructured":"Rasmussen, C. E. in Summer School on Machine Learning 63\u201371 (Springer, 2003).","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"168_CR56","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1093\/bioinformatics\/bty862","volume":"35","author":"TA Hopf","year":"2019","unstructured":"Hopf, T. A. et al. The EVcouplings Python framework for coevolutionary sequence analysis. Bioinformatics 35, 1582\u20131584 (2019).","journal-title":"Bioinformatics"},{"key":"168_CR57","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1186\/s12859-019-3019-7","volume":"20","author":"M Steinegger","year":"2019","unstructured":"Steinegger, M. et al. HH-suite3 for fast remote homology detection and deep protein annotation. BMC Bioinformatics 20, 473 (2019).","journal-title":"BMC Bioinformatics"},{"key":"168_CR58","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/nbt.4096","volume":"36","author":"A Butler","year":"2018","unstructured":"Butler, A., Hoffman, P., Smibert, P., Papalexi, E. & Satija, R. Integrating single-cell transcriptomic data across different conditions, technologies and species. Nat. Biotechnol. 36, 411\u2013420 (2018).","journal-title":"Nat. Biotechnol."},{"key":"168_CR59","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s10452-007-9152-9","volume":"43","author":"D Schmera","year":"2009","unstructured":"Schmera, D., Er\u0151s, T. & Podani, J. A measure for assessing functional diversity in ecological communities. Aquatic Ecol. 43, 157\u2013167 (2009).","journal-title":"Aquatic Ecol."},{"key":"168_CR60","doi-asserted-by":"publisher","unstructured":"YuchiQiu\/CLADE: Nature Computational Science publication accompaniment (v1.0.0) (Zenodo, 2021); https:\/\/doi.org\/10.5281\/zenodo.5585394","DOI":"10.5281\/zenodo.5585394"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00168-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00168-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00168-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T17:48:21Z","timestamp":1733939301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00168-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,9]]},"references-count":60,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["168"],"URL":"https:\/\/doi.org\/10.1038\/s43588-021-00168-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-528258\/v1","asserted-by":"object"}]},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,9]]},"assertion":[{"value":"15 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}