{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:11:24Z","timestamp":1767964284172,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,5,13]],"date-time":"2020-05-13T00:00:00Z","timestamp":1589328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,5,13]],"date-time":"2020-05-13T00:00:00Z","timestamp":1589328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003958","name":"Stichting voor de Technische Wetenschappen","doi-asserted-by":"publisher","award":["14410"],"award-info":[{"award-number":["14410"]}],"id":[{"id":"10.13039\/501100003958","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The development of drugs is often hampered due to off-target interactions leading to adverse effects. Therefore, computational methods to assess the selectivity of ligands are of high interest. Currently, selectivity is often deduced from bioactivity predictions of a ligand for multiple targets (individual machine learning models). Here we show that modeling selectivity directly, by using the affinity difference between two drug targets as output value, leads to more accurate selectivity predictions. We test multiple approaches on a dataset consisting of ligands for the A<jats:sub>1<\/jats:sub> and A<jats:sub>2A<\/jats:sub> adenosine receptors (among others classification, regression, and we define different selectivity classes). Finally, we present a regression model that predicts selectivity between these two drug targets by directly training on the difference in bioactivity, modeling the selectivity-window. The quality of this model was good as shown by the performances for fivefold cross-validation: ROC A<jats:sub>1<\/jats:sub>AR-selective 0.88\u2009\u00b1\u20090.04 and ROC A<jats:sub>2A<\/jats:sub>AR-selective 0.80\u2009\u00b1\u20090.07. To increase the accuracy of this selectivity model even further, inactive compounds were identified and removed prior to selectivity prediction by a combination of statistical models and structure-based docking. As a result, selectivity between the A<jats:sub>1<\/jats:sub> and A<jats:sub>2A<\/jats:sub> adenosine receptors was predicted effectively using the selectivity-window model. The approach presented here can be readily applied to other selectivity cases.<\/jats:p>","DOI":"10.1186\/s13321-020-00438-3","type":"journal-article","created":{"date-parts":[[2020,5,13]],"date-time":"2020-05-13T14:04:03Z","timestamp":1589378643000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Quantitative prediction of selectivity between the A1 and A2A adenosine receptors"],"prefix":"10.1186","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2442-0443","authenticated-orcid":false,"given":"Lindsey","family":"Burggraaff","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1915-3141","authenticated-orcid":false,"given":"Herman W. T.","family":"van Vlijmen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1182-2259","authenticated-orcid":false,"given":"Adriaan P.","family":"IJzerman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0717-1817","authenticated-orcid":false,"given":"Gerard J. P.","family":"van Westen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,13]]},"reference":[{"key":"438_CR1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13321-019-0337-8","volume":"11","author":"L Burggraaff","year":"2019","unstructured":"Burggraaff L, Oranje P, Gouka R et al (2019) Identification of novel small molecule inhibitors for solute carrier SGLT1 using proteochemometric modeling. J Cheminform 11:15. https:\/\/doi.org\/10.1186\/s13321-019-0337-8","journal-title":"J Cheminform"},{"key":"438_CR2","doi-asserted-by":"publisher","first-page":"e27518","DOI":"10.1371\/journal.pone.0027518","volume":"6","author":"GJP van Westen","year":"2011","unstructured":"van Westen GJP, Wegner JK, Geluykens P et al (2011) Which compound to select in lead optimization? Prospectively validated proteochemometric models guide preclinical development. PLoS ONE 6:e27518. https:\/\/doi.org\/10.1371\/journal.pone.0027518","journal-title":"PLoS ONE"},{"key":"438_CR3","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1021\/acs.jcim.6b00314","volume":"56","author":"EB Lenselink","year":"2016","unstructured":"Lenselink EB, Jespers W, van Vlijmen HWT et al (2016) Interacting with GPCRs: using interaction fingerprints for virtual screening. J Chem Inf Model 56:2053\u20132060. https:\/\/doi.org\/10.1021\/acs.jcim.6b00314","journal-title":"J Chem Inf Model"},{"key":"438_CR4","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1021\/acsomega.6b00086","volume":"1","author":"EB Lenselink","year":"2016","unstructured":"Lenselink EB, Louvel J, Forti AF et al (2016) Predicting binding affinities for GPCR ligands using free-energy perturbation. ACS Omega 1:293\u2013304. https:\/\/doi.org\/10.1021\/acsomega.6b00086","journal-title":"ACS Omega"},{"key":"438_CR5","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s13321-019-0348-5","volume":"11","author":"W Jespers","year":"2019","unstructured":"Jespers W, Esguerra M, \u00c5qvist J, Guti\u00e9rrez-de-Ter\u00e1n H (2019) QligFEP: an automated workflow for small molecule free energy calculations in Q. J Cheminform 11:26. https:\/\/doi.org\/10.1186\/s13321-019-0348-5","journal-title":"J Cheminform"},{"key":"438_CR6","doi-asserted-by":"publisher","first-page":"7874","DOI":"10.1021\/jm5006463","volume":"57","author":"A Anighoro","year":"2014","unstructured":"Anighoro A, Bajorath J, Rastelli G (2014) Polypharmacology: challenges and opportunities in drug discovery. J Med Chem 57:7874\u20137887. https:\/\/doi.org\/10.1021\/jm5006463","journal-title":"J Med Chem"},{"key":"438_CR7","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1038\/nrd1983","volume":"5","author":"KA Jacobson","year":"2006","unstructured":"Jacobson KA, Gao Z-G (2006) Adenosine receptors as therapeutic targets. Nat Rev Drug Discov 5:247\u2013264. https:\/\/doi.org\/10.1038\/nrd1983","journal-title":"Nat Rev Drug Discov"},{"key":"438_CR8","first-page":"527","volume":"53","author":"BB Fredholm","year":"2001","unstructured":"Fredholm BB, IJzerman AP, Jacobson KA et al (2001) International union of pharmacology. XXV. Nomenclature and classification of adenosine receptors. Pharmacol Rev 53:527\u2013552","journal-title":"Pharmacol Rev"},{"key":"438_CR9","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/S0022-2836(77)80200-3","volume":"112","author":"FC Bernstein","year":"1977","unstructured":"Bernstein FC, Koetzle TF, Williams GJB et al (1977) The protein data bank: a computer-based archival file for macromolecular structures. J Mol Biol 112:535\u2013542. https:\/\/doi.org\/10.1016\/S0022-2836(77)80200-3","journal-title":"J Mol Biol"},{"key":"438_CR10","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1016\/j.cell.2017.01.042","volume":"168","author":"A Glukhova","year":"2017","unstructured":"Glukhova A, Thal DM, Nguyen AT et al (2017) Structure of the adenosine A1 receptor reveals the basis for subtype selectivity. Cell 168:867\u2013877.e13. https:\/\/doi.org\/10.1016\/j.cell.2017.01.042","journal-title":"Cell"},{"key":"438_CR11","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1016\/j.str.2017.06.012","volume":"25","author":"RKY Cheng","year":"2017","unstructured":"Cheng RKY, Segala E, Robertson N et al (2017) Structures of human A1 and A2A adenosine receptors with xanthines reveal determinants of selectivity. Structure\u00a025:1275\u20131285.e4. https:\/\/doi.org\/10.1016\/j.str.2017.06.012","journal-title":"Structure"},{"key":"438_CR12","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1038\/s41586-018-0236-6","volume":"558","author":"CJ Draper-Joyce","year":"2018","unstructured":"Draper-Joyce CJ, Khoshouei M, Thal DM et al (2018) Structure of the adenosine-bound human adenosine A1 receptor\u2013Gi complex. Nature 558:559\u2013563. https:\/\/doi.org\/10.1038\/s41586-018-0236-6","journal-title":"Nature"},{"key":"438_CR13","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.1021\/acs.jcim.9b00298","volume":"59","author":"G Mattedi","year":"2019","unstructured":"Mattedi G, Deflorian F, Mason JS et al (2019) Understanding ligand binding selectivity in a prototypical GPCR family. J Chem Inf Model 59:2830\u20132836. https:\/\/doi.org\/10.1021\/acs.jcim.9b00298","journal-title":"J Chem Inf Model"},{"key":"438_CR14","doi-asserted-by":"publisher","first-page":"7010","DOI":"10.1021\/jm3003069","volume":"55","author":"GJP van Westen","year":"2012","unstructured":"van Westen GJP, van den Hoven OO, van der Pijl R et al (2012) Identifying novel adenosine receptor ligands by simultaneous proteochemometric modeling of rat and human bioactivity data. J Med Chem 55:7010\u20137020. https:\/\/doi.org\/10.1021\/jm3003069","journal-title":"J Med Chem"},{"key":"438_CR15","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s13321-017-0232-0","volume":"9","author":"EB Lenselink","year":"2017","unstructured":"Lenselink EB, ten Dijke N, Bongers B et al (2017) Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set. J Cheminform 9:45. https:\/\/doi.org\/10.1186\/s13321-017-0232-0","journal-title":"J Cheminform"},{"key":"438_CR16","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A, Bellis LJ, Bento AP et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107","journal-title":"Nucleic Acids Res"},{"key":"438_CR17","doi-asserted-by":"publisher","first-page":"1846","DOI":"10.1111\/j.1476-5381.2012.01897.x","volume":"166","author":"D Guo","year":"2012","unstructured":"Guo D, Mulder-Krieger T, IJzerman AP, Heitman LH (2012) Functional efficacy of adenosine A2A receptor agonists is positively correlated to their receptor residence time. Br J Pharmacol 166:1846\u20131859. https:\/\/doi.org\/10.1111\/j.1476-5381.2012.01897.x","journal-title":"Br J Pharmacol"},{"key":"438_CR18","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1021\/jm049408n","volume":"48","author":"L Cappellacci","year":"2005","unstructured":"Cappellacci L, Franchetti P, Pasqualini M et al (2005) Synthesis, biological evaluation, and molecular modeling of ribose-modified adenosine analogues as adenosine receptor agonists. J Med Chem 48:1550\u20131562. https:\/\/doi.org\/10.1021\/jm049408n","journal-title":"J Med Chem"},{"key":"438_CR19","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1007\/s10822-015-9860-5","volume":"29","author":"G Papadatos","year":"2015","unstructured":"Papadatos G, Gaulton A, Hersey A, Overington JP (2015) Activity, assay and target data curation and quality in the ChEMBL database. J Comput Aided Mol Des 29:885\u2013896. https:\/\/doi.org\/10.1007\/s10822-015-9860-5","journal-title":"J Comput Aided Mol Des"},{"key":"438_CR20","first-page":"2579","volume":"9","author":"L Van Der Maaten","year":"2008","unstructured":"Van Der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"438_CR21","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41598-017-18570-w","volume":"8","author":"P Rucktooa","year":"2018","unstructured":"Rucktooa P, Cheng RKY, Segala E et al (2018) Towards high throughput GPCR crystallography: in meso soaking of adenosine A2A receptor crystals. Sci Rep 8:41. https:\/\/doi.org\/10.1038\/s41598-017-18570-w","journal-title":"Sci Rep"},{"key":"438_CR22","doi-asserted-by":"publisher","first-page":"13987","DOI":"10.1074\/jbc.270.23.13987","volume":"270","author":"J Kim","year":"1995","unstructured":"Kim J, Wess J, van Rhee AM et al (1995) Site-directed mutagenesis identifies residues involved in ligand recognition in the human A(2a) adenosine receptor. J Biol Chem 270:13987\u201313997","journal-title":"J Biol Chem"},{"key":"438_CR23","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1021\/ci800138n","volume":"48","author":"S Sciabola","year":"2008","unstructured":"Sciabola S, Stanton RV, Wittkopp S et al (2008) Predicting kinase selectivity profiles using free-Wilson QSAR analysis. J Chem Inf Model 48:1851\u20131867. https:\/\/doi.org\/10.1021\/ci800138n","journal-title":"J Chem Inf Model"},{"key":"438_CR24","doi-asserted-by":"publisher","first-page":"5165","DOI":"10.1021\/jm300131x","volume":"55","author":"C Kramer","year":"2012","unstructured":"Kramer C, Kalliokoski T, Gedeck P, Vulpetti A (2012) The experimental uncertainty of heterogeneous public Ki data. J Med Chem 55:5165\u20135173. https:\/\/doi.org\/10.1021\/jm300131x","journal-title":"J Med Chem"},{"key":"438_CR25","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1021\/acs.jcim.6b00290","volume":"56","author":"G Subramanian","year":"2016","unstructured":"Subramanian G, Ramsundar B, Pande V, Denny RA (2016) Computational modeling of \u03b2-Secretase 1 (BACE-1) inhibitors using ligand based approaches. J Chem Inf Model 56:1936\u20131949. https:\/\/doi.org\/10.1021\/acs.jcim.6b00290","journal-title":"J Chem Inf Model"},{"key":"438_CR26","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1021\/ci0500379","volume":"45","author":"V Svetnik","year":"2005","unstructured":"Svetnik V, Wang T, Tong C et al (2005) Boosting: an ensemble learning tool for compound classification and QSAR modeling. J Chem Inf Model 45:786\u2013799. https:\/\/doi.org\/10.1021\/ci0500379","journal-title":"J Chem Inf Model"},{"key":"438_CR27","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1016\/j.bmcl.2012.12.067","volume":"23","author":"L Zhao","year":"2013","unstructured":"Zhao L, Xiang Y, Song J, Zhang Z (2013) A novel two-step QSAR modeling work flow to predict selectivity and activity of HDAC inhibitors. Bioorg Med Chem Lett 23:929\u2013933. https:\/\/doi.org\/10.1016\/j.bmcl.2012.12.067","journal-title":"Bioorg Med Chem Lett"},{"issue":"D1","key":"438_CR28","doi-asserted-by":"publisher","first-page":"D1083","DOI":"10.1093\/nar\/gkt1031","volume":"42","author":"AP Bento","year":"2014","unstructured":"Bento AP et al (2014) The ChEMBL bioactivity database: an update. Nucleic acids Res 42(D1):D1083\u2013D1090","journal-title":"Nucleic acids Res"},{"key":"438_CR29","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey BJ, Dueck D (2007) Clustering by passing messages between data points. Science 315:972\u2013976. https:\/\/doi.org\/10.1126\/science.1136800","journal-title":"Science"},{"key":"438_CR30","unstructured":"Dassault Syst\u00e8mes BIOVIA (2018) BIOVIA Pipeline Pilot"},{"key":"438_CR31","volume-title":"Studies in classification, data analysis, and knowledge organization","author":"MR Berthold","year":"2007","unstructured":"Berthold MR, Cebron N, Dill F et al (2007) KNIME: the Konstanz information miner. Studies in classification, data analysis, and knowledge organization. Springer, Berlin"},{"key":"438_CR32","doi-asserted-by":"publisher","first-page":"e1003559","DOI":"10.1371\/journal.pcbi.1003559","volume":"10","author":"GJP van Westen","year":"2014","unstructured":"van Westen GJP, Gaulton A, Overington JP (2014) Chemical, target, and bioactive properties of allosteric modulation. PLoS Comput Biol 10:e1003559. https:\/\/doi.org\/10.1371\/journal.pcbi.1003559","journal-title":"PLoS Comput Biol"},{"key":"438_CR33","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27:861\u2013874. https:\/\/doi.org\/10.1016\/j.patrec.2005.10.010","journal-title":"Pattern Recognit Lett"},{"key":"438_CR34","doi-asserted-by":"crossref","unstructured":"Schr\u00f6dinger (2017) Schr\u00f6dinger Maestro Release 2017-4","DOI":"10.2307\/j.ctvcm4h07.62"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-00438-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-020-00438-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-00438-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T23:33:37Z","timestamp":1620862417000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-020-00438-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,13]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["438"],"URL":"https:\/\/doi.org\/10.1186\/s13321-020-00438-3","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,13]]},"assertion":[{"value":"10 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"33"}}