{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:53:28Z","timestamp":1780710808733,"version":"3.54.1"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"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\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["LZ19H300001"],"award-info":[{"award-number":["LZ19H300001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Leading Talent of \u2018Ten Thousand Plan\u2019\u2013National High-Level Talents Special Support Plan"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81773632"],"award-info":[{"award-number":["81773632"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21575128"],"award-info":[{"award-number":["21575128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Zhejiang Province","award":["2020C03010"],"award-info":[{"award-number":["2020C03010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure\u2013activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM\u2009&amp;gt;\u2009XGBoost &amp;gt; rbf-GPR\u2009&amp;gt;\u2009Cubist &amp;gt; GBM\u2009&amp;gt;\u2009DNN\u2009&amp;gt;\u2009RF\u2009&amp;gt;\u2009pca-ANN\u2009&amp;gt;\u2009MARS &amp;gt; linear-GPR\u2009\u2248\u2009KNN\u2009&amp;gt;\u2009linear-SVM\u2009\u2248\u2009PLSR &amp;gt; CART \u2248 PCR\u2009\u2248\u2009MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms.<\/jats:p>","DOI":"10.1093\/bib\/bbaa321","type":"journal-article","created":{"date-parts":[[2020,10,20]],"date-time":"2020-10-20T11:19:05Z","timestamp":1603192745000},"source":"Crossref","is-referenced-by-count":175,"title":["Do we need different machine learning algorithms for QSAR modeling? A comprehensive assessment of 16 machine learning algorithms on 14 QSAR data sets"],"prefix":"10.1093","volume":"22","author":[{"given":"Zhenxing","family":"Wu","sequence":"first","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minfeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xiangya School of Pharmaceutical Sciences, Central South University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Kang","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elaine Lai-Han","family":"Leung","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Quality Research in Chinese Medicine, Macau Institute for Applied Research in Medicine and Health, Macau University of Science and Technology, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2067-1787","authenticated-orcid":false,"given":"Tailong","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dejun","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Hangzhou Institute of Innovative Medicine, Zhejiang University, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Central South University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingjun","family":"Hou","sequence":"additional","affiliation":[{"name":"Peking University, China. He is currently a professor in the College of Pharmaceutical Sciences, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,12,14]]},"reference":[{"issue":"12","key":"2021072117041900100_ref1","doi-asserted-by":"crossref","first-page":"4977","DOI":"10.1021\/jm4004285","article-title":"QSAR modeling: where have you been? Where are you going to?","volume":"57","author":"Cherkasov","year":"2014","journal-title":"J Med Chem"},{"issue":"12","key":"2021072117041900100_ref2","doi-asserted-by":"crossref","DOI":"10.1289\/EHP3264","article-title":"Best practices for QSAR model reporting: physical and chemical properties, ecotoxicity, environmental fate, human health, and toxicokinetics endpoints","volume":"126","author":"Piir","year":"2018","journal-title":"Environ Health Perspect"},{"issue":"6","key":"2021072117041900100_ref3","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1021\/acs.jcim.6b00088","article-title":"A historical excursus on the statistical validation parameters for QSAR models: a clarification concerning metrics and terminology","volume":"56","author":"Gramatica","year":"2016","journal-title":"J Chem Inf Model"},{"issue":"8","key":"2021072117041900100_ref4","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.1021\/ja01062a035","article-title":"p-\u03c3-\u03c0 analysis. A method for the correlation of biological activity and chemical structure","volume":"86","author":"Hansch","year":"1964","journal-title":"J Am Chem Soc"},{"issue":"11","key":"2021072117041900100_ref5","doi-asserted-by":"crossref","first-page":"3525","DOI":"10.1039\/D0CS00098A","article-title":"QSAR without borders","volume":"49","author":"Muratov","year":"2020","journal-title":"Chem Soc Rev"},{"issue":"3","key":"2021072117041900100_ref6","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1021\/cr9400976","article-title":"Comparative QSAR: toward a deeper understanding of chemicobiological interactions","volume":"96","author":"Hansch","year":"1996","journal-title":"Chem Rev"},{"issue":"3","key":"2021072117041900100_ref7","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1021\/cr0102009","article-title":"Chem-bioinformatics: comparative QSAR at the interface between chemistry and biology","volume":"102","author":"Hansch","year":"2002","journal-title":"Chem Rev"},{"key":"2021072117041900100_ref8","doi-asserted-by":"crossref","first-page":"67","DOI":"10.4018\/978-1-5225-0549-5.ch003","volume-title":"Information Resources Management A. (ed) Oncology: breakthroughs in research and practice","author":"Dearden","year":"2017"},{"issue":"2","key":"2021072117041900100_ref9","first-page":"36","article-title":"The history and development of quantitative structure-activity relationships (QSARs): addendum","volume":"2","author":"Dearden","year":"2017","journal-title":"Int. J. Quant. Struct.-Prop. Relatsh."},{"key":"2021072117041900100_ref10","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1016\/j.chemolab.2015.07.009","article-title":"In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines","volume":"146","author":"Cao","year":"2015","journal-title":"Chemom Intel Lab Syst"},{"issue":"1","key":"2021072117041900100_ref11","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10822-011-9519-9","article-title":"Drug design for ever, from hype to hope","volume":"26","author":"Seddon","year":"2012","journal-title":"J Comput Aid Mol Des"},{"issue":"10","key":"2021072117041900100_ref12","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1021\/jm00280a002","article-title":"Utilization of operational schemes for analog synthesis in drug design","volume":"15","author":"Topliss","year":"1972","journal-title":"J Med Chem"},{"issue":"11","key":"2021072117041900100_ref13","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1021\/jm00269a004","article-title":"Strategy in drug design. Cluster analysis as an aid in the selection of substituents","volume":"16","author":"Hansch","year":"1973","journal-title":"J Med Chem"},{"issue":"3","key":"2021072117041900100_ref14","doi-asserted-by":"crossref","first-page":"229","DOI":"10.2174\/1389200219666181019094526","article-title":"Survey of machine learning techniques for prediction of the isoform specificity of cytochrome P450 substrates","volume":"20","author":"Xiong","year":"2019","journal-title":"Curr Drug Metab"},{"issue":"4","key":"2021072117041900100_ref15","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1016\/j.drudis.2020.03.003","article-title":"Machine learning models for drug\u2013target interactions: current knowledge and future directions","volume":"25","author":"D'Souza","year":"2020","journal-title":"Drug Discov Today"},{"key":"2021072117041900100_ref16","volume-title":"TEST (Toxicity Estimation Software Tool) Ver 4.1","author":"Martin","year":"2012"},{"key":"2021072117041900100_ref17","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.envpol.2019.06.081","article-title":"Deep learning driven QSAR model for environmental toxicology: effects of endocrine disrupting chemicals on human health","volume":"253","author":"Heo","year":"2019","journal-title":"Environ Pollut"},{"issue":"2","key":"2021072117041900100_ref18","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1021\/ci990162i","article-title":"The characterization of chemical structures using molecular properties. A survey","volume":"40","author":"Livingstone","year":"2000","journal-title":"J Chem Inf Comput Sci"},{"key":"2021072117041900100_ref19","first-page":"113","article-title":"Computational analysis of structure\u2013activity relationships. Progress in medicinal chemistry","volume":"49","author":"Gedeck","year":"2010","journal-title":"Elsevier"},{"issue":"3","key":"2021072117041900100_ref20","first-page":"31","article-title":"Artificial neural networks: a tutorial","volume":"29","author":"Jain","year":"1996","journal-title":"Computertomographie"},{"issue":"6","key":"2021072117041900100_ref21","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: a classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J Chem Inf Comput Sci"},{"issue":"2","key":"2021072117041900100_ref22","first-page":"67","article-title":"Support vector machine applications in bioinformatics","volume":"2","author":"Byvatov","year":"2003","journal-title":"Appl Bioinformatics"},{"key":"2021072117041900100_ref23","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.asoc.2017.09.040","article-title":"Deep neural network in QSAR studies using deep belief network","volume":"62","author":"Ghasemi","year":"2018","journal-title":"Appl Soft Comput"},{"issue":"10","key":"2021072117041900100_ref24","doi-asserted-by":"crossref","first-page":"1784","DOI":"10.1016\/j.drudis.2018.06.016","article-title":"Neural network and deep-learning algorithms used in QSAR studies: merits and drawbacks","volume":"23","author":"Ghasemi","year":"2018","journal-title":"Drug Discov Today"},{"issue":"5","key":"2021072117041900100_ref25","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1021\/ci060138m","article-title":"The pharmacophore kernel for virtual screening with support vector machines","volume":"46","author":"Mah\u00e9","year":"2006","journal-title":"J Chem Inf Model"},{"issue":"1","key":"2021072117041900100_ref26","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1021\/ci600332j","article-title":"Contemporary QSAR classifiers compared","volume":"47","author":"Bruce","year":"2007","journal-title":"J Chem Inf Model"},{"issue":"2","key":"2021072117041900100_ref27","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1021\/ci600205g","article-title":"Accurate solubility prediction with error bars for electrolytes: a machine learning approach","volume":"47","author":"Schwaighofer","year":"2007","journal-title":"J Chem Inf Model"},{"key":"2021072117041900100_ref28","first-page":"1265","article-title":"Predicting lipophilicity of drug-discovery molecules using Gaussian process models","volume-title":"Chemmedchem","author":"Schroeter","year":"2007"},{"issue":"11","key":"2021072117041900100_ref29","doi-asserted-by":"crossref","first-page":"4587","DOI":"10.1021\/acs.jcim.9b00801","article-title":"ADMET evaluation in drug discovery. 19. Reliable prediction of human cytochrome P450 inhibition using artificial intelligence approaches","volume":"59","author":"Wu","year":"2019","journal-title":"J Chem Inf Model"},{"issue":"12","key":"2021072117041900100_ref30","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.1021\/acs.jcim.6b00591","article-title":"Extreme gradient boosting as a method for quantitative structure\u2013activity relationships","volume":"56","author":"Sheridan","year":"2016","journal-title":"J Chem Inf Model"},{"issue":"3","key":"2021072117041900100_ref31","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1021\/ci0500379","article-title":"Boosting: an ensemble learning tool for compound classification and QSAR modeling","volume":"45","author":"Svetnik","year":"2005","journal-title":"J Chem Inf Model"},{"issue":"11","key":"2021072117041900100_ref32","doi-asserted-by":"crossref","first-page":"2294","DOI":"10.1021\/jm0105427","article-title":"Antitumor agents. 213. Modeling of epipodophyllotoxin derivatives using variable selection k nearest neighbor QSAR method","volume":"45","author":"Xiao","year":"2002","journal-title":"J Med Chem"},{"issue":"1","key":"2021072117041900100_ref33","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1021\/ci980033m","article-title":"Novel variable selection quantitative structure\u2212 property relationship approach based on the k-nearest-neighbor principle","volume":"40","author":"Zheng","year":"2000","journal-title":"J Chem Inf Comput Sci"},{"issue":"1\u20132","key":"2021072117041900100_ref34","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1080\/10629360701843482","article-title":"Prediction of PAH mutagenicity in human cells by QSAR classification","volume":"19","author":"Papa","year":"2008","journal-title":"SAR QSAR Environ Res"},{"issue":"1","key":"2021072117041900100_ref35","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Trans Evol Comput"},{"issue":"8","key":"2021072117041900100_ref36","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1021\/acs.jcim.6b00753","article-title":"Comparison of the predictive performance and interpretability of random forest and linear models on benchmark data sets","volume":"57","author":"Marchese Robinson","year":"2017","journal-title":"J Chem Inf Model"},{"issue":"10","key":"2021072117041900100_ref37","doi-asserted-by":"crossref","first-page":"4336","DOI":"10.1021\/acs.molpharmaceut.8b00110","article-title":"Prediction of human cytochrome P450 inhibition using a multitask deep autoencoder neural network","volume":"15","author":"Li","year":"2018","journal-title":"Mol Pharm"},{"key":"2021072117041900100_ref38","first-page":"1919","article-title":"Meta-weight-net: learning an explicit mapping for sample weighting","author":"Shu","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2021072117041900100_ref39","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2020.3015691","article-title":"MHF-Net: an interpretable deep network for multispectral and hyperspectral image fusion","author":"Xie","year":"2020","journal-title":"Trans Pattern Anal Mach Intell"},{"issue":"9","key":"2021072117041900100_ref40","doi-asserted-by":"crossref","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","article-title":"Graph networks as a universal machine learning framework for molecules and crystals","volume":"31","author":"Chen","year":"2019","journal-title":"Chem Mater"},{"issue":"15","key":"2021072117041900100_ref41","doi-asserted-by":"crossref","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J Med Chem"},{"issue":"4","key":"2021072117041900100_ref42","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1021\/ci025535l","article-title":"Using molecular equivalence numbers to visually explore structural features that distinguish chemical libraries","volume":"42","author":"Xu","year":"2002","journal-title":"J Chem Inf Comput Sci"},{"issue":"9","key":"2021072117041900100_ref43","doi-asserted-by":"crossref","first-page":"3714","DOI":"10.1021\/acs.jcim.9b00541","article-title":"Structural analysis and identification of colloidal aggregators in drug discovery","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"issue":"7","key":"2021072117041900100_ref44","doi-asserted-by":"crossref","first-page":"1823","DOI":"10.1021\/acs.jafc.8b06596","article-title":"FungiPAD: a free web tool for compound property evaluation and fungicide-likeness analysis","volume":"67","author":"Wang","year":"2019","journal-title":"J Agric Food Chem"},{"issue":"9","key":"2021072117041900100_ref45","doi-asserted-by":"crossref","first-page":"1725","DOI":"10.1021\/acs.jcim.8b00285","article-title":"PADFrag: a database built for the exploration of bioactive fragment space for drug discovery","volume":"58","author":"Yang","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2021072117041900100_ref46","volume-title":"MOE Molecular Simulation Package","year":"2010"},{"issue":"18","key":"2021072117041900100_ref47","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.2174\/156802608786786624","article-title":"Medicinal chemistry and the molecular operating environment (MOE): application of QSAR and molecular docking to drug discovery","volume":"8","author":"Vilar","year":"2008","journal-title":"Curr Top Med Chem"},{"issue":"5","key":"2021072117041900100_ref48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Softw"},{"issue":"1","key":"2021072117041900100_ref49","doi-asserted-by":"crossref","DOI":"10.1088\/1749-4699\/8\/1\/014008","article-title":"Hyperopt: a python library for model selection and hyperparameter optimization","volume":"8","author":"Bergstra","year":"2015","journal-title":"Comput Sci Discov"},{"issue":"5","key":"2021072117041900100_ref50","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1002\/qsar.200610151","article-title":"Principles of QSAR models validation: internal and external","volume":"26","author":"Gramatica","year":"2007","journal-title":"QSAR Comb Sci"},{"issue":"6\u20137","key":"2021072117041900100_ref51","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1002\/minf.201000061","article-title":"Best practices for QSAR model development, validation, and exploitation","volume":"29","author":"Tropsha","year":"2010","journal-title":"Mol Inf"},{"issue":"1","key":"2021072117041900100_ref52","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Fern\u00e1ndez-Delgado","year":"2014","journal-title":"J Mach Learn Res"},{"key":"2021072117041900100_ref53","volume-title":"The Master Algorithm: How the Quest for the Ultimate Learning Machine will Remake our World","author":"Domingos","year":"2015"},{"issue":"4","key":"2021072117041900100_ref54","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1021\/jm049254b","article-title":"Greater than the sum of its parts: combining models for useful ADMET prediction","volume":"48","author":"O'Brien","year":"2005","journal-title":"J Med Chem"},{"issue":"4","key":"2021072117041900100_ref55","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1021\/ci700016d","article-title":"Consensus QSAR models: do the benefits outweigh the complexity?","volume":"47","author":"Hewitt","year":"2007","journal-title":"J Chem Inf Model"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/4\/bbaa321\/39156178\/bbaa321.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/4\/bbaa321\/39156178\/bbaa321.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T17:33:20Z","timestamp":1626888800000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaa321\/6032614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7,20]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaa321","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7]]},"published":{"date-parts":[[2020,12,14]]},"article-number":"bbaa321"}}