{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:29:22Z","timestamp":1772166562958,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T00:00:00Z","timestamp":1629331200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T00:00:00Z","timestamp":1629331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/M011194\/1"],"award-info":[{"award-number":["BB\/M011194\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004325","name":"AstraZeneca","doi-asserted-by":"publisher","award":["BB\/M011194\/1"],"award-info":[{"award-number":["BB\/M011194\/1"]}],"id":[{"id":"10.13039\/100004325","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Measurements of protein\u2013ligand interactions have reproducibility limits due to experimental errors. Any model based on such assays will consequentially have such unavoidable errors influencing their performance which should ideally be factored into modelling and output predictions, such as the actual standard deviation of experimental measurements (\u03c3) or the associated comparability of activity values between the aggregated heterogenous activity units (i.e., K\n                    <jats:sub>i<\/jats:sub>\n                    versus IC\n                    <jats:sub>50<\/jats:sub>\n                    values) during dataset assimilation. However, experimental errors are usually a neglected aspect of model generation. In order to improve upon the current state-of-the-art, we herein present a novel approach toward predicting protein\u2013ligand interactions using a Probabilistic Random Forest (PRF) classifier. The PRF algorithm was applied toward in silico protein target prediction across ~\u2009550 tasks from ChEMBL and PubChem. Predictions were evaluated by taking into account various scenarios of experimental standard deviations in both training and test sets and performance was assessed using fivefold stratified shuffled splits for validation. The largest benefit in incorporating the experimental deviation in PRF was observed for data points close to the binary threshold boundary, when such information was not considered in any way in the original RF algorithm. For example, in cases when \u03c3 ranged between 0.4\u20130.6 log units and when ideal probability estimates between 0.4\u20130.6, the PRF outperformed RF with a median absolute error margin of ~\u200917%. In comparison, the baseline RF outperformed PRF for cases with high confidence to belong to the active class (far from the binary decision threshold), although the RF models gave errors smaller than the experimental uncertainty, which could indicate that they were\n                    <jats:italic>overtrained<\/jats:italic>\n                    and\/or\n                    <jats:italic>over-confident<\/jats:italic>\n                    . Finally, the PRF models trained with putative inactives decreased the performance compared to PRF models without putative inactives and this could be because putative inactives were not assigned an experimental pXC\n                    <jats:sub>50<\/jats:sub>\n                    value, and therefore they were considered inactives with a low uncertainty (which in practice might not be true). In conclusion, PRF can be useful for target prediction models in particular for data where class boundaries overlap with the measurement uncertainty, and where a substantial part of the training data is located close to the classification threshold.\n                  <\/jats:p>","DOI":"10.1186\/s13321-021-00539-7","type":"journal-article","created":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T07:07:19Z","timestamp":1629356839000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty"],"prefix":"10.1186","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7271-0824","authenticated-orcid":false,"given":"Lewis H.","family":"Mervin","sequence":"first","affiliation":[]},{"given":"Maria-Anna","family":"Trapotsi","sequence":"additional","affiliation":[]},{"given":"Avid M.","family":"Afzal","sequence":"additional","affiliation":[]},{"given":"Ian P.","family":"Barrett","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Bender","sequence":"additional","affiliation":[]},{"given":"Ola","family":"Engkvist","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"539_CR1","doi-asserted-by":"publisher","first-page":"185","DOI":"10.2174\/1389200219666180820112457","volume":"20","author":"N Stephenson","year":"2019","unstructured":"Stephenson N, Shane E, Chase J, Rowland J, Ries D, Justice N, Zhang J, Chan L, Cao R (2019) Survey of machine learning techniques in drug discovery. Curr Drug Metab 20:185\u2013193","journal-title":"Curr Drug Metab"},{"key":"539_CR2","doi-asserted-by":"publisher","first-page":"2573","DOI":"10.4155\/fmc-2018-0161","volume":"10","author":"CP Green","year":"2018","unstructured":"Green CP, Engkvist O, Pairaudeau G (2018) The convergence of artificial intelligence and chemistry for improved drug discovery. Future Med Chem 10:2573\u20132576","journal-title":"Future Med Chem"},{"key":"539_CR3","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.4155\/fmc-2018-0212","volume":"10","author":"MA Sellwood","year":"2018","unstructured":"Sellwood MA, Ahmed M, Segler MH, Brown N (2018) Artificial intelligence in drug discovery. Future Med Chem 10:2025\u20132028","journal-title":"Future Med Chem"},{"key":"539_CR4","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s42256-018-0004-1","volume":"1","author":"E Begoli","year":"2019","unstructured":"Begoli E, Bhattacharya T, Kusnezov D (2019) The need for uncertainty quantification in machine-assisted medical decision making. Nat Mach Intell 1:20\u201323","journal-title":"Nat Mach Intell"},{"key":"539_CR5","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","volume":"555","author":"MHS Segler","year":"2018","unstructured":"Segler MHS, Preuss M, Waller MP (2018) Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555:604\u2013610","journal-title":"Nature"},{"key":"539_CR6","doi-asserted-by":"publisher","first-page":"24825","DOI":"10.1021\/acsami.9b01226","volume":"11","author":"T Dimitrov","year":"2019","unstructured":"Dimitrov T, Kreisbeck C, Becker JS, Aspuru-Guzik A, Saikin SK (2019) Autonomous molecular design: then and now. ACS Appl Mater Interfaces 11:24825\u201324836","journal-title":"ACS Appl Mater Interfaces"},{"key":"539_CR7","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.drudis.2020.11.027","volume":"26","author":"LH Mervin","year":"2021","unstructured":"Mervin LH, Johansson S, Semenova E, Giblin KA, Engkvist O (2021) Uncertainty quantification in drug design. Drug Discov Today 26:474\u2013489","journal-title":"Drug Discov Today"},{"key":"539_CR8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s13321-020-0408-x","volume":"12","author":"N Schaduangrat","year":"2020","unstructured":"Schaduangrat N, Lampa S, Simeon S, Gleeson MP, Spjuth O, Nantasenamat C (2020) Towards reproducible computational drug discovery. J Cheminform 12:9","journal-title":"J Cheminform"},{"key":"539_CR9","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1021\/ci060003g","volume":"46","author":"A Nidhi","year":"2006","unstructured":"Nidhi A, Glick M, Davies JW, Jenkins JL (2006) Prediction of biological targets for compounds using multiple-category Bayesian models trained on chemogenomics databases. J Chem Inf Model 46:1124\u20131133","journal-title":"J Chem Inf Model"},{"key":"539_CR10","doi-asserted-by":"publisher","first-page":"5441","DOI":"10.1039\/C8SC00148K","volume":"9","author":"A Mayr","year":"2018","unstructured":"Mayr A, Klambauer G, Unterthiner T, Steijaert M, Wegner JK, Ceulemans H, Clevert DA, Hochreiter S (2018) Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chem Sci 9:5441\u20135451","journal-title":"Chem Sci"},{"key":"539_CR11","unstructured":"Unterthiner T, Mayr A, Klambauer G, Steijaert M, Wegner JK, Ceulemans H, Hochreiter S. Deep learning for drug target prediction. In: Conference neural information processing systems foundation (NIPS 2014), workshop on representation and learning methods for complex outputs, 2014; 2014."},{"key":"539_CR12","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, Papadatos G, van Vlijmen HWT, Kowalczyk W, Ijzerman AP, van Westen GJP (2017) Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set. J Cheminform 9:45","journal-title":"J Cheminform"},{"key":"539_CR13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s13321-020-00468-x","volume":"12","author":"G Idakwo","year":"2020","unstructured":"Idakwo G, Thangapandian S, Luttrell J, Li Y, Wang N, Zhou Z, Hong H, Yang B, Zhang C, Gong P (2020) Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets. J Cheminform 12:66","journal-title":"J Cheminform"},{"key":"539_CR14","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 K(i) data. J Med Chem 55:5165\u20135173","journal-title":"J Med Chem"},{"key":"539_CR15","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, Chambers J, Davies M, Hersey A, Light Y, McGlinchey S, Michalovich D, Al-Lazikani B, Overington JP (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107","journal-title":"Nucleic Acids Res"},{"key":"539_CR16","doi-asserted-by":"publisher","first-page":"e61007","DOI":"10.1371\/journal.pone.0061007","volume":"8","author":"T Kalliokoski","year":"2013","unstructured":"Kalliokoski T, Kramer C, Vulpetti A, Gedeck P (2013) Comparability of mixed IC(5)(0) data\u2014a statistical analysis. PLoS ONE 8:e61007","journal-title":"PLoS ONE"},{"key":"539_CR17","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1093\/bioinformatics\/btx525","volume":"34","author":"LH Mervin","year":"2018","unstructured":"Mervin LH, Bulusu KC, Kalash L, Afzal AM, Svensson F, Firth MA, Barrett I, Engkvist O, Bender A (2018) Orthologue chemical space and its influence on target prediction. Bioinformatics 34:72\u201379","journal-title":"Bioinformatics"},{"key":"539_CR18","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1111\/cbdd.12578","volume":"86","author":"D Dimova","year":"2015","unstructured":"Dimova D, Stumpfe D, Bajorath J (2015) Identification of orthologous target pairs with shared active compounds and comparison of organism-specific activity patterns. Chem Biol Drug Des 86:1105\u20131114","journal-title":"Chem Biol Drug Des"},{"key":"539_CR19","doi-asserted-by":"publisher","first-page":"2721","DOI":"10.1093\/bioinformatics\/btv214","volume":"31","author":"D Gfeller","year":"2015","unstructured":"Gfeller D, Zoete V (2015) Protein homology reveals new targets for bioactive small molecules. Bioinformatics 31:2721\u20132727","journal-title":"Bioinformatics"},{"key":"539_CR20","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1002\/cmdc.201500424","volume":"11","author":"I Cort\u00e9s-Ciriano","year":"2016","unstructured":"Cort\u00e9s-Ciriano I, Bender A (2016) How consistent are publicly reported cytotoxicity data? Large-scale statistical analysis of the concordance of public independent cytotoxicity measurements. ChemMedChem 11:57\u201371","journal-title":"ChemMedChem"},{"key":"539_CR21","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1016\/j.drudis.2016.03.015","volume":"21","author":"C Kramer","year":"2016","unstructured":"Kramer C, Dahl G, Tyrchan C, Ulander J (2016) A comprehensive company database analysis of biological assay variability. Drug Discov Today 21:1213\u20131221","journal-title":"Drug Discov Today"},{"key":"539_CR22","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1021\/ci100176x","volume":"50","author":"D Fourches","year":"2010","unstructured":"Fourches D, Muratov E, Tropsha A (2010) Trust, but verify: on the importance of chemical structure curation in cheminformatics and QSAR modeling research. J Chem Inf Model 50:1189\u20131204","journal-title":"J Chem Inf Model"},{"key":"539_CR23","doi-asserted-by":"publisher","first-page":"3056","DOI":"10.1021\/ci5005509","volume":"54","author":"Y Hu","year":"2014","unstructured":"Hu Y, Bajorath J (2014) Influence of search parameters and criteria on compound selection, promiscuity, and pan assay interference characteristics. J Chem Inf Model 54:3056\u20133066","journal-title":"J Chem Inf Model"},{"key":"539_CR24","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1021\/ci400099q","volume":"53","author":"P Tiikkainen","year":"2013","unstructured":"Tiikkainen P, Bellis L, Light Y, Franke L (2013) Estimating error rates in bioactivity databases. J Chem Inf Model 53:2499\u20132505","journal-title":"J Chem Inf Model"},{"key":"539_CR25","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.drudis.2009.01.012","volume":"14","author":"SP Brown","year":"2009","unstructured":"Brown SP, Muchmore SW, Hajduk PJ (2009) Healthy skepticism: assessing realistic model performance. Drug Discov Today 14:420\u2013427","journal-title":"Drug Discov Today"},{"key":"539_CR26","unstructured":"Li G, Zrimec J, Ji B, Geng J, Larsbrink J, Zelezniak A, Nielsen J, Engqvist MK. Performance of regression models as a function of experiment noise. arXiv preprint; 2019. https:\/\/arxiv.org\/abs\/1912.08141."},{"key":"539_CR27","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1021\/acs.jcim.5b00101","volume":"55","author":"I Cortes-Ciriano","year":"2015","unstructured":"Cortes-Ciriano I, Bender A, Malliavin TE (2015) Comparing the influence of simulated experimental errors on 12 machine learning algorithms in bioactivity modeling using 12 diverse data sets. J Chem Inf Model 55:1413\u20131425","journal-title":"J Chem Inf Model"},{"key":"539_CR28","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1214\/09-AOAS285","volume":"4","author":"HA Chipman","year":"2010","unstructured":"Chipman HA, George EI, McCulloch RE (2010) BART: Bayesian additive regression trees. Ann Appl Stat 4:266\u2013298","journal-title":"Ann Appl Stat"},{"key":"539_CR29","doi-asserted-by":"publisher","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","volume":"44","author":"S Kim","year":"2016","unstructured":"Kim S, Thiessen PA, Bolton EE, Chen J, Fu G, Gindulyte A, Han L, He J, He S, Shoemaker BA, Wang J, Yu B, Zhang J, Bryant SH (2016) PubChem substance and compound databases. Nucleic Acids Res 44:D1202\u2013D1213","journal-title":"Nucleic Acids Res"},{"key":"539_CR30","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3847\/1538-3881\/aaf101","volume":"157","author":"I Reis","year":"2018","unstructured":"Reis I, Baron D, Shahaf S (2018) Probabilistic random forest: A machine learning algorithm for noisy data sets. Astron J 157:16","journal-title":"Astron J"},{"key":"539_CR31","doi-asserted-by":"publisher","first-page":"26","DOI":"10.3847\/1538-4365\/abafc1","volume":"250","author":"K Boutsia","year":"2020","unstructured":"Boutsia K, Grazian A, Calderone G, Cristiani S, Cupani G, Guarneri F, Fontanot F, Amorin R, D\u2019Odorico V, Giallongo E (2020) The spectroscopic follow-up of the QUBRICS bright quasar survey. Astrophys J Suppl Ser 250:26","journal-title":"Astrophys J Suppl Ser"},{"key":"539_CR32","doi-asserted-by":"publisher","first-page":"D1083","DOI":"10.1093\/nar\/gkt1031","volume":"42","author":"AP Bento","year":"2014","unstructured":"Bento AP, Gaulton A, Hersey A, Bellis LJ, Chambers J, Davies M, Kr\u00fcger FA, Light Y, Mak L, McGlinchey S, Nowotka M, Papadatos G, Santos R, Overington JP (2014) The ChEMBL bioactivity database: an update. Nucleic Acids Res 42:D1083\u2013D1090","journal-title":"Nucleic Acids Res"},{"key":"539_CR33","unstructured":"Landrum, G. RDKit: Open-source cheminformatics; 2012. http:\/\/www.rdkit.org."},{"key":"539_CR34","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1103\/PhysRev.106.620","volume":"106","author":"ET Jaynes","year":"1957","unstructured":"Jaynes ET (1957) Information theory and statistical mechanics. Phys Rev 106:620","journal-title":"Phys Rev"},{"key":"539_CR35","unstructured":"Jones E, Oliphant T, Peterson P. {SciPy}: open source scientific tools for {Python}; 2014."},{"key":"539_CR36","doi-asserted-by":"publisher","first-page":"4546","DOI":"10.1021\/acs.jcim.0c00476","volume":"60","author":"L Mervin","year":"2020","unstructured":"Mervin L, Afzal AM, Engkvist O, Bender A (2020) A comparison of scaling methods to obtain calibrated probabilities of activity for ligand-target predictions. J Chem Inf Model 60:4546\u20134559","journal-title":"J Chem Inf Model"},{"key":"539_CR37","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332","journal-title":"Mach Learn"},{"key":"539_CR38","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","journal-title":"J Comput Aided Mol Des"},{"key":"539_CR39","unstructured":"Vaicenavicius J, Widmann D, Andersson C, Lindsten F, Roll J, Sch\u00f6n TB. Evaluating model calibration in classification. arXiv preprint; 2019. https:\/\/arxiv.org\/abs\/1902.06977."},{"key":"539_CR40","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/1758-2946-6-32","volume":"6","author":"R Kurczab","year":"2014","unstructured":"Kurczab R, Smusz S, Bojarski AJ (2014) The influence of negative training set size on machine learning-based virtual screening. J Cheminform 6:32","journal-title":"J Cheminform"},{"key":"539_CR41","doi-asserted-by":"publisher","first-page":"2763","DOI":"10.2174\/092986711796011238","volume":"18","author":"C Raimondi","year":"2011","unstructured":"Raimondi C, Falasca M (2011) Targeting PDK1 in cancer. Curr Med Chem 18:2763\u20132769","journal-title":"Curr Med Chem"},{"key":"539_CR42","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1016\/j.jmgm.2008.01.002","volume":"26","author":"S Weaver","year":"2008","unstructured":"Weaver S, Gleeson MP (2008) The importance of the domain of applicability in QSAR modeling. J Mol Graph Model 26:1315\u20131326","journal-title":"J Mol Graph Model"},{"key":"539_CR43","doi-asserted-by":"publisher","DOI":"10.1039\/C9SC02298H","author":"J Jon Paul","year":"2019","unstructured":"Jon Paul J, Chenru D, Tzuhsiung Y, Aditya N, Heather K (2019) Uncertain times call for quantitative uncertainty metrics: controlling error in neural network predictions for chemical discovery. Chem Sci. https:\/\/doi.org\/10.1039\/C9SC02298H","journal-title":"Chem Sci"},{"key":"539_CR44","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-030-16443-0_11","volume-title":"Advances in computational toxicology","author":"T Hanser","year":"2019","unstructured":"Hanser T, Barber C, Guesn\u00e9 S, Marchaland JF, Werner S (2019) Applicability domain: towards a more formal framework to express the applicability of a model and the confidence in individual predictions. In: Werner S (ed) Advances in computational toxicology. Springer, Berlin, pp 215\u2013232"},{"key":"539_CR45","doi-asserted-by":"publisher","first-page":"4791","DOI":"10.3390\/molecules17054791","volume":"17","author":"F Sahigara","year":"2012","unstructured":"Sahigara F, Mansouri K, Ballabio D, Mauri A, Consonni V, Todeschini R (2012) Comparison of different approaches to define the applicability domain of QSAR models. Molecules 17:4791\u20134810","journal-title":"Molecules"},{"key":"539_CR46","doi-asserted-by":"publisher","first-page":"103350","DOI":"10.1016\/j.jbi.2019.103350","volume":"101","author":"T Pereira","year":"2020","unstructured":"Pereira T, Cardoso S, Guerreiro M, de Mendonca A, Madeira SC, Alzheimer\u2019s Disease Neuroimaging, I (2020) Targeting the uncertainty of predictions at patient-level using an ensemble of classifiers coupled with calibration methods, Venn-ABERS, and Conformal Predictors: a case study in AD. J Biomed Inform 101:103350","journal-title":"J Biomed Inform"},{"key":"539_CR47","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.1021\/acs.jcim.0c00250","volume":"60","author":"U Norinder","year":"2020","unstructured":"Norinder U, Spjuth O, Svensson F (2020) Using predicted bioactivity profiles to improve predictive modeling. J Chem Inf Model 60:2830\u20132837","journal-title":"J Chem Inf Model"},{"key":"539_CR48","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1021\/acs.jcim.8b00542","volume":"59","author":"I Cortes-Ciriano","year":"2019","unstructured":"Cortes-Ciriano I, Bender A (2019) Deep confidence: a computationally efficient framework for calculating reliable prediction errors for deep neural networks. J Chem Inf Model 59:1269\u20131281","journal-title":"J Chem Inf Model"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00539-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-021-00539-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00539-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T08:09:45Z","timestamp":1629360585000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-021-00539-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,19]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["539"],"URL":"https:\/\/doi.org\/10.1186\/s13321-021-00539-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.14544291.v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,19]]},"assertion":[{"value":"7 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"62"}}