{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:04:51Z","timestamp":1773162291073,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T00:00:00Z","timestamp":1585267200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T00:00:00Z","timestamp":1585267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003549","name":"Hungarian Scientific Research Fund","doi-asserted-by":"publisher","award":["OTKA K 119269"],"award-info":[{"award-number":["OTKA K 119269"]}],"id":[{"id":"10.13039\/501100003549","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Aided Mol Des"],"published-print":{"date-parts":[[2020,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Cytochrome P450 (CYP) enzymes play an important role in the metabolism of xenobiotics. Since they are connected to drug interactions, screening for potential inhibitors is of utmost importance in drug discovery settings. Our study provides an extensive classification model for P450-drug interactions with one of the most prominent members, the 2C9 isoenzyme. Our model involved the largest set of 45,000 molecules ever used for developing prediction models. The models are based on three different types of descriptors, (a) typical one, two and three dimensional molecular\u00a0descriptors, (b) chemical and pharmacophore fingerprints and (c) interaction fingerprints with docking scores. Two machine learning algorithms, the boosted tree and the multilayer feedforward of resilient backpropagation network were used and compared based on their performances. The models were validated both internally and using external validation sets. The results showed that the consensus voting technique with custom probability thresholds could provide promising results even in large-scale cases without any restrictions on the applicability domain. Our best model was capable to predict the 2C9 inhibitory activity with the area under the receiver operating characteristic curve (AUC) of 0.85 and 0.84 for the internal and the external test sets, respectively. The chemical space covered with the largest available dataset has reached its limit encompassing publicly available bioactivity data for the 2C9 isoenzyme.<\/jats:p>","DOI":"10.1007\/s10822-020-00308-y","type":"journal-article","created":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T05:02:52Z","timestamp":1585285372000},"page":"831-839","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Large-scale evaluation of cytochrome P450 2C9 mediated drug interaction potential with machine learning-based consensus modeling"],"prefix":"10.1007","volume":"34","author":[{"given":"Anita","family":"R\u00e1cz","sequence":"first","affiliation":[]},{"given":"Gy\u00f6rgy M.","family":"Keser\u0171","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,27]]},"reference":[{"key":"308_CR1","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1021\/tx700079z","volume":"21","author":"FP Guengerich","year":"2008","unstructured":"Guengerich FP (2008) Cytochrome P450 and chemical toxicology. Chem Res Toxicol 21:70\u201383. https:\/\/doi.org\/10.1021\/tx700079z","journal-title":"Chem Res Toxicol"},{"key":"308_CR2","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/S1359-6446(97)01081-7","volume":"2","author":"DA Smith","year":"1997","unstructured":"Smith DA, Ackland MJ, Jones BC (1997) Properties of cytochrome P450 isoenzymes and their substrates. Part 1: active site characteristics. Drug Discov Today 2:406\u2013414. https:\/\/doi.org\/10.1016\/S1359-6446(97)01081-7","journal-title":"Drug Discov Today"},{"key":"308_CR3","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1186\/1479-7364-4-4-278","volume":"4","author":"SC Sim","year":"2010","unstructured":"Sim SC, Ingelman-Sundberg M (2010) The human cytochrome P450 (CYP) allele nomenclature website: a peer-reviewed database of CYP variants and their associated effects. Hum Genomics 4:278\u2013281. https:\/\/doi.org\/10.1186\/1479-7364-4-4-278","journal-title":"Hum Genomics"},{"key":"308_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dmpk.2019.11.006","author":"H Kato","year":"2019","unstructured":"Kato H (2019) Computational prediction of cytochrome P450 inhibition and induction. Drug Metab Pharmacokinet. https:\/\/doi.org\/10.1016\/j.dmpk.2019.11.006","journal-title":"Drug Metab Pharmacokinet"},{"key":"308_CR5","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.pharmthera.2012.12.007","volume":"138","author":"UM Zanger","year":"2013","unstructured":"Zanger UM, Schwab M (2013) Cytochrome P450 enzymes in drug metabolism: regulation of gene expression, enzyme activities, and impact of genetic variation. Pharmacol Ther 138:103\u2013141. https:\/\/doi.org\/10.1016\/j.pharmthera.2012.12.007","journal-title":"Pharmacol Ther"},{"key":"308_CR6","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1038\/nrd1851","volume":"4","author":"LC Wienkers","year":"2005","unstructured":"Wienkers LC, Heath TG (2005) Predicting in vivo drug interactions from in vitro drug discovery data. Nat Rev Drug Discov 4:825\u2013833. https:\/\/doi.org\/10.1038\/nrd1851","journal-title":"Nat Rev Drug Discov"},{"key":"308_CR7","doi-asserted-by":"publisher","DOI":"10.1517\/17425250903158940","author":"K Roy","year":"2009","unstructured":"Roy K, Roy PP (2009) Review QSAR of cytochrome inhibitors. Expert Opin Drug Metab Toxicol. https:\/\/doi.org\/10.1517\/17425250903158940","journal-title":"Expert Opin Drug Metab Toxicol"},{"key":"308_CR8","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1016\/j.bmc.2012.01.049","volume":"20","author":"S\u00d3 J\u00f3nsd\u00f3ttir","year":"2012","unstructured":"J\u00f3nsd\u00f3ttir S\u00d3, Ringsted T, Nikolov NG et al (2012) Identification of cytochrome P450 2D6 and 2C9 substrates and inhibitors by QSAR analysis. Bioorgan Med Chem 20:2042\u20132053. https:\/\/doi.org\/10.1016\/j.bmc.2012.01.049","journal-title":"Bioorgan Med Chem"},{"key":"308_CR9","first-page":"1","volume":"24","author":"JP Jones","year":"1996","unstructured":"Jones JP, He M, Trager WF, Rettie AE (1996) Three-dimensional quantitative structure-activity relationship for inhibitors of cytochrome P4502C9. Drug Metab Dispos 24:1\u20136","journal-title":"Drug Metab Dispos"},{"key":"308_CR10","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1124\/dmd.105.004325","volume":"33","author":"CW Locuson","year":"2005","unstructured":"Locuson CW, Wahlstrom JL (2005) Three-dimensional quantitative structure-activity relationship analysis of cytochromes P450: effect of incorporating higher-affinity ligands and potential new applications. Drug Metab Dispos 33:873\u2013878. https:\/\/doi.org\/10.1124\/dmd.105.004325","journal-title":"Drug Metab Dispos"},{"key":"308_CR11","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1002\/qsar.200630143","volume":"26","author":"E Byvatov","year":"2007","unstructured":"Byvatov E, Baringhaus K, Schneider G, Matter H (2007) A virtual screening filter for identification of cytochrome P450. QSAR Comb Sci 26:618\u2013628. https:\/\/doi.org\/10.1002\/qsar.200630143","journal-title":"QSAR Comb Sci"},{"key":"308_CR12","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1021\/jm701122q","volume":"51","author":"MP Gleeson","year":"2008","unstructured":"Gleeson MP (2008) Generation of a set of simple, interpretable ADMET rules of thumb: supplimentary information. J Med Chem 51:S1\u2013S18. https:\/\/doi.org\/10.1021\/jm701122q","journal-title":"J Med Chem"},{"key":"308_CR13","doi-asserted-by":"publisher","first-page":"914","DOI":"10.3390\/ijms17060914","volume":"17","author":"S Nembri","year":"2016","unstructured":"Nembri S, Grisoni F, Consonni V, Todeschini R (2016) In silico prediction of cytochrome P450-drug interaction: QSARs for CYP3A4 and CYP2C9. Int J Mol Sci 17:914. https:\/\/doi.org\/10.3390\/ijms17060914","journal-title":"Int J Mol Sci"},{"key":"308_CR14","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1021\/ci0500536","volume":"45","author":"CW Yap","year":"2005","unstructured":"Yap CW, Chen YZ (2005) Prediction of cytochrome P450 3A4, 2D6, and 2C9 inhibitors and substrates by using support vector machines. J Chem Inf Model 45:982\u2013992. https:\/\/doi.org\/10.1021\/ci0500536","journal-title":"J Chem Inf Model"},{"key":"308_CR15","doi-asserted-by":"publisher","first-page":"2474","DOI":"10.1021\/ci200311w","volume":"51","author":"H Sun","year":"2012","unstructured":"Sun H, Veith H, Xia M et al (2012) Predictive models for cytochrome P450 isozymes based on quantitative high throughput screening data. J Chem Inf Model 51:2474\u20132481. https:\/\/doi.org\/10.1021\/ci200311w","journal-title":"J Chem Inf Model"},{"key":"308_CR16","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1080\/1062936X.2017.1399925","volume":"28","author":"JH Lee","year":"2017","unstructured":"Lee JH, Basith S, Cui M et al (2017) In silico prediction of multiple-category classification model for cytochrome P450 inhibitors and non-inhibitors using machine-learning method. SAR QSAR Environ Res 28:863\u2013874. https:\/\/doi.org\/10.1080\/1062936X.2017.1399925","journal-title":"SAR QSAR Environ Res"},{"key":"308_CR17","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1021\/ci200028n","volume":"51","author":"F Cheng","year":"2011","unstructured":"Cheng F, Yu Y, Shen J et al (2011) Classification of cytochrome P450 inhibitors and noninhibitors using combined classifiers. J Chem Inf Model 51:996\u20131011. https:\/\/doi.org\/10.1021\/ci200028n","journal-title":"J Chem Inf Model"},{"key":"308_CR18","doi-asserted-by":"publisher","first-page":"4587","DOI":"10.1021\/acs.jcim.9b00801","volume":"59","author":"Z Wu","year":"2019","unstructured":"Wu Z, Lei T, Shen C et al (2019) ADMET evaluation in drug discovery. 19. Reliable prediction of human cytochrome P450 inhibition using artificial intelligence approaches. J Chem Inf Model 59:4587\u20134601. https:\/\/doi.org\/10.1021\/acs.jcim.9b00801","journal-title":"J Chem Inf Model"},{"key":"308_CR19","unstructured":"National Center for Biotechnology Information. PubChem database. CYP2C9 assay, AID=777. https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/777. Accessed 22 Jan 2020"},{"key":"308_CR20","unstructured":"National Center for Biotechnology Information. PubChem database. Source=NCGC, AID=1851. https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/1851. Accessed 27 Jan 2020"},{"key":"308_CR21","unstructured":"National Center for Biotechnology Information. PubChem database. Source=NCGC, AID=883. https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/883. Accessed 27 Jan 2020"},{"key":"308_CR22","unstructured":"ChemAxon Calculator 18.1.0, Budapest, Hungary. https:\/\/chemaxon.com. Accessed 22 Jan 2020"},{"key":"308_CR23","first-page":"2019","volume-title":"LigPre","author":"Schr\u00f6dinger","year":"2019","unstructured":"Schr\u00f6dinger (2019) LigPrep. Schr\u00f6dinger, New York, pp 2019\u20132024"},{"key":"308_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/molecules24152811","volume":"24","author":"A R\u00e1cz","year":"2019","unstructured":"R\u00e1cz A, Bajusz D, H\u00e9berger K (2019) Multi-level comparison of machine learning classifiers and their performance metrics. Molecules 24:1\u201318. https:\/\/doi.org\/10.3390\/molecules24152811","journal-title":"Molecules"},{"key":"308_CR25","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1002\/qsar.200290002","volume":"21","author":"M Ashton","year":"2002","unstructured":"Ashton M, Barnard J, Casset F et al (2002) Identification of diverse database subsets using property-based and fragment-based molecular descriptions. Quant Struct Relationsh 21:598\u2013604. https:\/\/doi.org\/10.1002\/qsar.200290002","journal-title":"Quant Struct Relationsh"},{"key":"308_CR26","unstructured":"Todeschini R, Consonni V, Pavan M, Kode SRL (2017) Dragon (software for molecular descriptor calculation). https:\/\/chm.kode-solutions.net. Accessed 27 Jan 2020"},{"key":"308_CR27","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1021\/jm030644s","volume":"47","author":"TA Halgren","year":"2004","unstructured":"Halgren TA, Murphy RB, Friesner RA et al (2004) Glide: a new approach for rapid, accurate docking and scoring. 2. Enrichment factors in database screening. J Med Chem 47:1750\u20131759. https:\/\/doi.org\/10.1021\/jm030644s","journal-title":"J Med Chem"},{"key":"308_CR28","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1021\/jm0306430","volume":"47","author":"RA Friesner","year":"2004","unstructured":"Friesner RA, Banks JL, Murphy RB et al (2004) Glide: a new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy. J Med Chem 47:1739\u20131749. https:\/\/doi.org\/10.1021\/jm0306430","journal-title":"J Med Chem"},{"key":"308_CR29","doi-asserted-by":"publisher","first-page":"1800154","DOI":"10.1002\/minf.201800154","volume":"38","author":"A R\u00e1cz","year":"2019","unstructured":"R\u00e1cz A, Bajusz D, H\u00e9berger K (2019) Intercorrelation limits in molecular descriptor preselection for QSAR\/QSPR. Mol Inform 38:1800154. https:\/\/doi.org\/10.1002\/minf.201800154","journal-title":"Mol Inform"},{"key":"308_CR30","doi-asserted-by":"publisher","DOI":"10.1002\/9783527613106","volume-title":"Handbook of molecular descriptors","author":"R Todeschini","year":"2000","unstructured":"Todeschini R, Consonni V (2000) Handbook of molecular descriptors. Wiley\u2013VCH, Weinheim"},{"key":"308_CR31","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/B978-0-12-409547-2.12345-5","volume-title":"Comprehensive medicinal chemistry III","author":"D Bajusz","year":"2017","unstructured":"Bajusz D, R\u00e1cz A, H\u00e9berger K (2017) Chemical data formats, fingerprints, and other molecular descriptions for database analysis and searching. In: Chackalamannil S, Rotella DP, Ward SE (eds) Comprehensive medicinal chemistry III. Elsevier, Oxford, pp 329\u2013378"},{"key":"308_CR32","doi-asserted-by":"publisher","first-page":"7029","DOI":"10.2210\/PDB5K7K\/PDB","volume":"60","author":"NA Swain","year":"2017","unstructured":"Swain NA, Batchelor D, Beaudoin S et al (2017) Discovery of clinical candidate 4-[2-(5-amino-1H-pyrazol-4-yl)-4-chlorophenoxy]-5-chloro-2-fluoro-N-1,3-thiazol-4-ylbenzenesulfonamide (PF-05089771): design and optimization of diaryl ether aryl sulfonamides as selective inhibitors of NaV1.7. J Med Chem 60:7029\u20137042. https:\/\/doi.org\/10.2210\/PDB5K7K\/PDB","journal-title":"J Med Chem"},{"key":"308_CR33","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10822-013-9644-8","volume":"27","author":"G Madhavi Sastry","year":"2013","unstructured":"Madhavi Sastry G, Adzhigirey M, Day T et al (2013) Protein and ligand preparation: parameters, protocols, and influence on virtual screening enrichments. J Comput Aided Mol Des 27:221\u2013234. https:\/\/doi.org\/10.1007\/s10822-013-9644-8","journal-title":"J Comput Aided Mol Des"},{"key":"308_CR34","volume-title":"Release 2019-4: Maestro","author":"Schr\u00f6dinger","year":"2019","unstructured":"Schr\u00f6dinger (2019) Release 2019-4: Maestro. Schr\u00f6dinger, LLC, New York"},{"key":"308_CR35","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-018-0302-y","volume":"10","author":"A R\u00e1cz","year":"2018","unstructured":"R\u00e1cz A, Bajusz D, H\u00e9berger K (2018) Life beyond the Tanimoto coefficient: similarity measures for interaction fingerprints. J Cheminform 10:48. https:\/\/doi.org\/10.1186\/s13321-018-0302-y","journal-title":"J Cheminform"},{"key":"308_CR36","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189\u20131232","journal-title":"Ann Stat"},{"key":"308_CR37","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/ICNN.1993.298623","volume":"1","author":"M Riedmiller","year":"1993","unstructured":"Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. IEEE Int Conf Neural Netw 1:586\u2013591","journal-title":"IEEE Int Conf Neural Netw"},{"key":"308_CR38","unstructured":"KNIME (2014) Konstanz information miner. University of Konstanz, Konstanz. https:\/\/www.knime.org\/. Accessed 27 Jan 2020"},{"key":"308_CR39","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"308_CR40","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1093\/bioinformatics\/btt325","volume":"29","author":"M Rostkowski","year":"2013","unstructured":"Rostkowski M, Spjuth O, Rydberg P (2013) WhichCyp: prediction of cytochromes P450 inhibition. Bioinformatics 29:2051\u20132052. https:\/\/doi.org\/10.1093\/bioinformatics\/btt325","journal-title":"Bioinformatics"},{"key":"308_CR41","doi-asserted-by":"publisher","first-page":"4336","DOI":"10.1021\/acs.molpharmaceut.8b00110","volume":"15","author":"X Li","year":"2018","unstructured":"Li X, Xu Y, Lai L, Pei J (2018) Prediction of human cytochrome P450 inhibition using a multitask deep autoencoder neural network. Mol Pharm 15:4336\u20134345. https:\/\/doi.org\/10.1021\/acs.molpharmaceut.8b00110","journal-title":"Mol Pharm"}],"container-title":["Journal of Computer-Aided Molecular Design"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-020-00308-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10822-020-00308-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-020-00308-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,27]],"date-time":"2021-03-27T00:40:24Z","timestamp":1616805624000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10822-020-00308-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,27]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["308"],"URL":"https:\/\/doi.org\/10.1007\/s10822-020-00308-y","relation":{},"ISSN":["0920-654X","1573-4951"],"issn-type":[{"value":"0920-654X","type":"print"},{"value":"1573-4951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,27]]},"assertion":[{"value":"5 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"There are no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}