{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T10:02:02Z","timestamp":1768039322732,"version":"3.49.0"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T00:00:00Z","timestamp":1692316800000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Research Cooperability Program of the Croatian Science Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Increasing efforts are being made in the field of machine learning to advance the learning of robust and accurate models from experimentally measured data and enable more efficient drug discovery processes. The prediction of binding affinity is one of the most frequent tasks of compound bioactivity modelling. Learned models for binding affinity prediction are assessed by their average performance on unseen samples, but point predictions are typically not provided with a rigorous confidence assessment. Approaches, such as the conformal predictor framework equip conventional models with a more rigorous assessment of confidence for individual point predictions. In this article, we extend the inductive conformal prediction framework for interaction data, in particular the compound\u2013target binding affinity prediction task. The new framework is based on dynamically defined calibration sets that are specific for each testing pair and provides prediction assessment in the context of calibration pairs from its compound\u2013target neighbourhood, enabling improved estimates based on the local properties of the prediction model.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The effectiveness of the approach is benchmarked on several publicly available datasets and tested in realistic use-case scenarios with increasing levels of difficulty on a complex compound\u2013target binding affinity space. We demonstrate that in such scenarios, novel approach combining applicability domain paradigm with conformal prediction framework, produces superior confidence assessment with valid and more informative prediction regions compared to other \u2018state-of-the-art\u2019 conformal prediction approaches.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Dataset and the code are available on GitHub (https:\/\/github.com\/mlkr-rbi\/dAD).<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad465","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T15:27:57Z","timestamp":1692372477000},"source":"Crossref","is-referenced-by-count":4,"title":["Dynamic applicability domain (dAD): compound\u2013target binding affinity estimates with local conformal prediction"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5385-1031","authenticated-orcid":false,"given":"Davor","family":"Or\u0161oli\u0107","sequence":"first","affiliation":[{"name":"Division of Electronics, Ru\u0111er Bo\u0161kovi\u0107 Institute , Bijeni\u010dka cesta 54 , Zagreb 10000, Croatia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9185-9384","authenticated-orcid":false,"given":"Tomislav","family":"\u0160muc","sequence":"additional","affiliation":[{"name":"Division of Electronics, Ru\u0111er Bo\u0161kovi\u0107 Institute , Bijeni\u010dka cesta 54 , Zagreb 10000, Croatia"}]}],"member":"286","published-online":{"date-parts":[[2023,8,18]]},"reference":[{"key":"2023082607512566000_btad465-B1","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.xphs.2020.09.055","article-title":"Predicting with confidence: using conformal prediction in drug discovery","volume":"110","author":"Alvarsson","year":"2021","journal-title":"J Pharm Sci"},{"key":"2023082607512566000_btad465-B2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-016-0182-y","article-title":"A novel applicability domain technique for mapping predictive reliability across the chemical space of a QSAR: reliability-density neighbourhood","volume":"8","author":"Aniceto","year":"2016","journal-title":"J Cheminform"},{"key":"2023082607512566000_btad465-B3","first-page":"785","author":"Chen","year":"2016"},{"key":"2023082607512566000_btad465-B4","doi-asserted-by":"crossref","first-page":"e1005678","DOI":"10.1371\/journal.pcbi.1005678","article-title":"Computational-experimental approach to drug-target interaction mapping: a case study on kinase inhibitors","volume":"13","author":"Cichonska","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2023082607512566000_btad465-B5","doi-asserted-by":"crossref","first-page":"3307","DOI":"10.1038\/s41467-021-23165-1","article-title":"Crowdsourced mapping of unexplored target space of kinase inhibitors","volume":"12","author":"Cicho\u0144ska","year":"2021","journal-title":"Nat Commun"},{"key":"2023082607512566000_btad465-B6","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive analysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat Biotechnol"},{"key":"2023082607512566000_btad465-B7","first-page":"45","article-title":"Applicability domain for QSAR models: where theory meets reality","volume":"1","author":"Gadaleta","year":"2016","journal-title":"IJQSPR"},{"key":"2023082607512566000_btad465-B8","first-page":"148","author":"Gammerman","year":"1998"},{"key":"2023082607512566000_btad465-B9","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023082607512566000_btad465-B10","doi-asserted-by":"crossref","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","article-title":"BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology","volume":"44","author":"Gilson","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023082607512566000_btad465-B11","author":"Fey","year":"2019"},{"key":"2023082607512566000_btad465-B12","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s10994-014-5453-0","article-title":"Regression conformal prediction with random forests","volume":"97","author":"Johansson","year":"2014","journal-title":"Mach Learn"},{"key":"2023082607512566000_btad465-B13","author":"Kipf"},{"key":"2023082607512566000_btad465-B14","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s13321-017-0230-2","article-title":"Efficiency of different measures for defining the applicability domain of classification models","volume":"9","author":"Klingspohn","year":"2017","journal-title":"J Cheminform"},{"key":"2023082607512566000_btad465-B15","first-page":"2796","author":"Kuleshov","year":"2018"},{"key":"2023082607512566000_btad465-B16","author":"Landrum","year":"2020"},{"key":"2023082607512566000_btad465-B17","doi-asserted-by":"crossref","first-page":"5540","DOI":"10.3390\/s22155540","article-title":"Evaluating and calibrating uncertainty prediction in regression tasks","volume":"22","author":"Levi","year":"2022","journal-title":"Sensors"},{"key":"2023082607512566000_btad465-B18","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1021\/jm0608107","article-title":"Molecular recognition of protein kinase binding pockets for design of potent and selective kinase inhibitors","volume":"50","author":"Liao","year":"2007","journal-title":"J Med Chem"},{"key":"2023082607512566000_btad465-B19","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1016\/j.csbj.2021.03.004","article-title":"A review on compound-protein interaction prediction methods: data, format, representation and model","volume":"19","author":"Lim","year":"2021","journal-title":"Comput Struct Biotechnol J"},{"key":"2023082607512566000_btad465-B20","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1126\/science.1075762","article-title":"The protein kinase complement of the human genome","volume":"298","author":"Manning","year":"2002","journal-title":"Science"},{"key":"2023082607512566000_btad465-B21","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1002\/minf.201501019","article-title":"Chemoinformatic classification methods and their applicability domain","volume":"35","author":"Mathea","year":"2016","journal-title":"Mol Inform"},{"key":"2023082607512566000_btad465-B22","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.cels.2018.07.001","article-title":"Coral: clear and customizable visualization of human kinome data","volume":"7","author":"Metz","year":"2018","journal-title":"Cell Syst"},{"key":"2023082607512566000_btad465-B23","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2023082607512566000_btad465-B24","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2023082607512566000_btad465-B25","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/bib\/bbu010","article-title":"Toward more realistic drug\u2013target interaction predictions","volume":"16","author":"Pahikkala","year":"2015","journal-title":"Brief Bioinform"},{"key":"2023082607512566000_btad465-B26","volume-title":"Inductive Conformal Prediction: Theory and Application to Neural Networks","author":"Papadopoulos","year":"2008"},{"key":"2023082607512566000_btad465-B27","first-page":"32","author":"Papadopoulos","year":"2010"},{"key":"2023082607512566000_btad465-B28","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1613\/jair.3198","article-title":"Regression conformal prediction with nearest neighbours","volume":"40","author":"Papadopoulos","year":"2011","journal-title":"JAIR"},{"key":"2023082607512566000_btad465-B29","author":"Paszke","year":"2019"},{"key":"2023082607512566000_btad465-B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.phrs.2015.07.010","article-title":"A historical overview of protein kinases and their targeted small molecule inhibitors","volume":"100","author":"Roskoski","year":"2015","journal-title":"Pharmacol Res"},{"key":"2023082607512566000_btad465-B31","first-page":"371","article-title":"A tutorial on conformal prediction","volume":"9","author":"Shafer","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2023082607512566000_btad465-B32","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1021\/ci400709d","article-title":"Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis","volume":"54","author":"Tang","year":"2014","journal-title":"J Chem Inf Model"},{"key":"2023082607512566000_btad465-B33","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.chembiol.2017.11.009","article-title":"Drug target commons: a community effort to build a consensus knowledge base for drug-target interactions","volume":"25","author":"Tang","year":"2018","journal-title":"Cell Chem Biol"},{"key":"2023082607512566000_btad465-B34","first-page":"37","volume-title":"Conformal and Probabilistic Prediction and Applications","author":"Vovk","year":"2018"},{"key":"2023082607512566000_btad465-B35","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1093\/bioinformatics\/btv042","article-title":"protr\/ProtrWeb: R package and web server for generating various numerical representation schemes of protein sequences","volume":"31","author":"Xiao","year":"2015","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad465\/51158131\/btad465.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/8\/btad465\/51269405\/btad465.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/8\/btad465\/51269405\/btad465.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T07:51:58Z","timestamp":1693036318000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad465\/7245860"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad465","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,8,1]]},"published":{"date-parts":[[2023,8,1]]},"article-number":"btad465"}}