{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:10:56Z","timestamp":1777695056882,"version":"3.51.4"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T00:00:00Z","timestamp":1625184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T00:00:00Z","timestamp":1625184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"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><jats:p>Numerous ligand-based drug discovery projects are based on structure-activity relationship (SAR) analysis, such as Free-Wilson (FW) or matched molecular pair (MMP) analysis. Intrinsically they assume linearity and additivity of substituent contributions. These techniques are challenged by nonadditivity (NA) in protein\u2013ligand binding where the change of two functional groups in one molecule results in much higher or lower activity than expected from the respective single changes. Identifying nonlinear cases and possible underlying explanations is crucial for a drug design project since it might influence which lead to follow. By systematically analyzing all AstraZeneca (AZ) inhouse compound data and publicly available ChEMBL25 bioactivity data, we show significant NA events in almost every second assay among the inhouse and once in every third assay in public data sets. Furthermore, 9.4% of all compounds of the AZ database and 5.1% from public sources display significant additivity shifts indicating important SAR features or fundamental measurement errors. Using NA data in combination with machine learning showed that nonadditive data is challenging to predict and even the addition of nonadditive data into training did not result in an increase in predictivity. Overall, NA analysis should be applied on a regular basis in many areas of computational chemistry and can further improve rational drug design.<\/jats:p>","DOI":"10.1186\/s13321-021-00525-z","type":"journal-article","created":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T17:05:16Z","timestamp":1625245516000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Nonadditivity in public and inhouse data: implications for drug design"],"prefix":"10.1186","volume":"13","author":[{"given":"D.","family":"Gogishvili","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7231-7996","authenticated-orcid":false,"given":"E.","family":"Nittinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Margreitter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Tyrchan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,2]]},"reference":[{"key":"525_CR1","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1021\/jm00334a001","volume":"7","author":"SM Free","year":"1964","unstructured":"Free SM, Wilson JW (1964) A mathematical contribution to structure-activity studies. J Med Chem 7:395\u2013399","journal-title":"J Med Chem"},{"key":"525_CR2","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1021\/ci400696v","volume":"54","author":"RD Cramer","year":"2014","unstructured":"Cramer RD, Wendt B (2014) Template CoMFA: The 3D-QSAR Grail? J Chem Inf Model 54:660\u2013671","journal-title":"J Chem Inf Model"},{"key":"525_CR3","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1021\/ci900450m","volume":"50","author":"J Hussain","year":"2010","unstructured":"Hussain J, Rea C (2010) Computationally efficient algorithm to identify matched molecular pairs (MMPs) in large data sets. J Chem Inf Model 50:339\u2013348","journal-title":"J Chem Inf Model"},{"key":"525_CR4","doi-asserted-by":"publisher","first-page":"7552","DOI":"10.1021\/jm801070q","volume":"51","author":"Y Patel","year":"2008","unstructured":"Patel Y, Gillet VJ, Howe T et al (2008) Assessment of additive\/nonadditive effects in structure\u2212 activity relationships: implications for iterative drug design. J Med Chem 51:7552\u20137562","journal-title":"J Med Chem"},{"key":"525_CR5","doi-asserted-by":"publisher","first-page":"2695","DOI":"10.1021\/ja512751q","volume":"137","author":"L Wang","year":"2015","unstructured":"Wang L, Wu Y, Deng Y et al (2015) Accurate and reliable prediction of relative ligand binding potency in prospective drug discovery by way of a modern free-energy calculation protocol and force field. J Am Chem Soc 137:2695\u20132703. https:\/\/doi.org\/10.1021\/ja512751q","journal-title":"J Am Chem Soc"},{"key":"525_CR6","doi-asserted-by":"publisher","first-page":"4034","DOI":"10.1021\/acs.jcim.9b00631","volume":"59","author":"C Kramer","year":"2019","unstructured":"Kramer C (2019) Nonadditivity Analysis. J Chem Inf Model 59:4034\u20134042. https:\/\/doi.org\/10.1021\/acs.jcim.9b00631","journal-title":"J Chem Inf Model"},{"key":"525_CR7","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1002\/minf.201600023","volume":"35","author":"D Dimova","year":"2016","unstructured":"Dimova D, Bajorath J (2016) Advances in activity cliff research. Mol Inform 35:181\u2013191","journal-title":"Mol Inform"},{"key":"525_CR8","doi-asserted-by":"publisher","first-page":"3339","DOI":"10.1021\/jm400147j","volume":"56","author":"D Dimova","year":"2013","unstructured":"Dimova D, Heikamp K, Stumpfe D, Bajorath J (2013) Do medicinal chemists learn from activity cliffs? A systematic evaluation of cliff progression in evolving compound data sets. J Med Chem 56:3339\u20133345","journal-title":"J Med Chem"},{"key":"525_CR9","doi-asserted-by":"publisher","first-page":"199","DOI":"10.12688\/f1000research.2-199.v1","volume":"2","author":"Y Hu","year":"2013","unstructured":"Hu Y, Stumpfe D, Bajorath J (2013) Advancing the activity cliff concept. F1000 Research. 2:199","journal-title":"F1000 Research."},{"key":"525_CR10","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1146\/annurev-biophys-070816-033654","volume":"46","author":"DL Mobley","year":"2017","unstructured":"Mobley DL, Gilson MK (2017) Predicting binding free energies: frontiers and benchmarks. Annu Rev Biophys 46:531\u2013558","journal-title":"Annu Rev Biophys"},{"issue":"1","key":"525_CR11","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1039\/C9MD00463G","volume":"11","author":"H Hu","year":"2020","unstructured":"Hu H, Bajorath J (2020) Introducing a new category of activity cliffs combining different compound similarity criteria. RSC Med Chem. 11(1):132\u201341","journal-title":"RSC Med Chem."},{"issue":"1","key":"525_CR12","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1021\/acs.jcim.9b00731","volume":"60","author":"TM Abramyan","year":"2019","unstructured":"Abramyan TM, An Y, Kireev D (2019) Off-pocket activity cliffs: a puzzling facet of molecular recognition. J Chem Inf Model. 60(1):152\u201361","journal-title":"J Chem Inf Model."},{"key":"525_CR13","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1039\/C3MD00338H","volume":"5","author":"SP Andrews","year":"2014","unstructured":"Andrews SP, Mason JS, Hurrell E, Congreve M (2014) Structure-based drug design of chromone antagonists of the adenosine A2A receptor. Medchemcomm 5:571\u2013575. https:\/\/doi.org\/10.1039\/C3MD00338H","journal-title":"Medchemcomm"},{"key":"525_CR14","doi-asserted-by":"publisher","first-page":"12256","DOI":"10.1002\/anie.201303207","volume":"52","author":"H Sch\u00f6nherr","year":"2013","unstructured":"Sch\u00f6nherr H, Cernak T (2013) Profound methyl effects in drug discovery and a call for new C-H methylation reactions. Angew Chemie Int Ed 52:12256\u201312267","journal-title":"Angew Chemie Int Ed"},{"key":"525_CR15","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1021\/acs.jcim.5b00018","volume":"55","author":"C Kramer","year":"2015","unstructured":"Kramer C, Fuchs JE, Liedl KR (2015) Strong nonadditivity as a key structure-activity relationship feature: distinguishing structural changes from assay artifacts. J Chem Inf Model 55:483\u2013494. https:\/\/doi.org\/10.1021\/acs.jcim.5b00018","journal-title":"J Chem Inf Model"},{"key":"525_CR16","doi-asserted-by":"publisher","first-page":"7754","DOI":"10.1021\/acs.jmedchem.8b00713","volume":"61","author":"L Gomez","year":"2018","unstructured":"Gomez L, Xu R, Sinko W et al (2018) Mathematical and structural characterization of strong nonadditive structure-activity relationship caused by protein conformational changes. J Med Chem 61:7754\u20137766","journal-title":"J Med Chem"},{"key":"525_CR17","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1016\/j.jmb.2010.02.007","volume":"397","author":"B Baum","year":"2010","unstructured":"Baum B, Muley L, Smolinski M et al (2010) Non-additivity of functional group contributions in protein\u2013ligand binding: a comprehensive study by crystallography and isothermal titration calorimetry. J Mol Biol 397:1042\u20131054","journal-title":"J Mol Biol"},{"key":"525_CR18","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.bmcl.2005.09.048","volume":"16","author":"K McClure","year":"2006","unstructured":"McClure K, Hack M, Huang L et al (2006) Pyrazole CCK1 receptor antagonists. Part 1: Solution-phase library synthesis and determination of Free-Wilson additivity. Bioorg Med Chem Lett 16:72\u201376","journal-title":"Bioorg Med Chem Lett"},{"key":"525_CR19","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.bmcl.2005.09.041","volume":"16","author":"C Sehon","year":"2006","unstructured":"Sehon C, McClure K, Hack M et al (2006) Pyrazole CCK1 receptor antagonists. Part 2: SAR studies by solid-phase library synthesis and determination of Free-Wilson additivity. Bioorg Med Chem Lett 16:77\u201380","journal-title":"Bioorg Med Chem Lett"},{"key":"525_CR20","doi-asserted-by":"publisher","first-page":"3889","DOI":"10.1021\/jm00049a008","volume":"37","author":"K Hilpert","year":"2002","unstructured":"Hilpert K, Ackermann J, Banner DW et al (2002) Design and synthesis of potent and highly selective thrombin inhibitors. J Med Chem 37:3889\u20133901","journal-title":"J Med Chem"},{"key":"525_CR21","doi-asserted-by":"publisher","first-page":"2966","DOI":"10.1016\/j.bmcl.2007.03.072","volume":"17","author":"T L\u00fcbbers","year":"2007","unstructured":"L\u00fcbbers T, B\u00f6hringer M, Gobbi L et al (2007) 1, 3-disubstituted 4-aminopiperidines as useful tools in the optimization of the 2-aminobenzo [a] quinolizine dipeptidyl peptidase IV inhibitors. Bioorg Med Chem Lett 17:2966\u20132970","journal-title":"Bioorg Med Chem Lett"},{"key":"525_CR22","doi-asserted-by":"publisher","first-page":"4489","DOI":"10.1021\/jm3003697","volume":"55","author":"CS Leung","year":"2012","unstructured":"Leung CS, Leung SSF, Tirado-Rives J, Jorgensen WL (2012) Methyl effects on protein\u2013ligand binding. J Med Chem 55:4489\u20134500","journal-title":"J Med Chem"},{"key":"525_CR23","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1529\/biophysj.105.060194","volume":"89","author":"H Abeliovich","year":"2005","unstructured":"Abeliovich H (2005) An empirical extremum principle for the hill coefficient in ligand\u2013protein interactions showing negative cooperativity. Biophys J 89:76\u201379","journal-title":"Biophys J"},{"key":"525_CR24","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1074\/jbc.272.2.701","volume":"272","author":"KA Dill","year":"1997","unstructured":"Dill KA (1997) Additivity principles in biochemistry. J Biol Chem 272:701\u2013704","journal-title":"J Biol Chem"},{"key":"525_CR25","doi-asserted-by":"publisher","first-page":"18518","DOI":"10.1021\/ja9083495","volume":"131","author":"A Camara-Campos","year":"2009","unstructured":"Camara-Campos A, Musumeci D, Hunter CA, Turega S (2009) Chemical double mutant cycles for the quantification of cooperativity in H-bonded complexes. J Am Chem Soc 131:18518\u201318524","journal-title":"J Am Chem Soc"},{"key":"525_CR26","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1039\/B603842P","volume":"36","author":"SL Cockroft","year":"2007","unstructured":"Cockroft SL, Hunter CA (2007) Chemical double-mutant cycles: dissecting non-covalent interactions. Chem Soc Rev 36:172\u2013188","journal-title":"Chem Soc Rev"},{"key":"525_CR27","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1038\/nchembio831","volume":"2","author":"K Babaoglu","year":"2006","unstructured":"Babaoglu K, Shoichet BK (2006) Deconstructing fragment-based inhibitor discovery. Nat Chem Biol 2:720\u2013723","journal-title":"Nat Chem Biol"},{"key":"525_CR28","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1146\/annurev.biochem.71.110601.135446","volume":"71","author":"BG Miller","year":"2002","unstructured":"Miller BG, Wolfenden R (2002) Catalytic proficiency: the unusual case of OMP decarboxylase. Annu Rev Biochem 71:847\u2013885","journal-title":"Annu Rev Biochem"},{"key":"525_CR29","doi-asserted-by":"publisher","first-page":"5818","DOI":"10.1021\/ja9702778","volume":"119","author":"PJ Hajduk","year":"1997","unstructured":"Hajduk PJ, Sheppard G, Nettesheim DG et al (1997) Discovery of potent nonpeptide inhibitors of stromelysin using SAR by NMR. J Am Chem Soc 119:5818\u20135827","journal-title":"J Am Chem Soc"},{"key":"525_CR30","doi-asserted-by":"publisher","first-page":"4479","DOI":"10.1002\/anie.200351951","volume":"42","author":"MS Congreve","year":"2003","unstructured":"Congreve MS, Davis DJ, Devine L et al (2003) Detection of ligands from a dynamic combinatorial library by X-ray crystallography. Angew Chemie Int Ed 42:4479\u20134482","journal-title":"Angew Chemie Int Ed"},{"key":"525_CR31","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1110\/ps.04912605","volume":"14","author":"SD Sharrow","year":"2005","unstructured":"Sharrow SD, Edmonds KA, Goodman MA et al (2005) Thermodynamic consequences of disrupting a water-mediated hydrogen bond network in a protein: pheromone complex. Protein Sci 14:249\u2013256","journal-title":"Protein Sci"},{"key":"525_CR32","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1021\/jm9016416","volume":"53","author":"L Muley","year":"2010","unstructured":"Muley L, Baum B, Smolinski M et al (2010) Enhancement of hydrophobic interactions and hydrogen bond strength by cooperativity: synthesis, modeling, and molecular dynamics simulations of a congeneric series of thrombin inhibitors. J Med Chem 53:2126\u20132135","journal-title":"J Med Chem"},{"key":"525_CR33","doi-asserted-by":"publisher","first-page":"2601","DOI":"10.1021\/jm100087s","volume":"53","author":"B Kuhn","year":"2010","unstructured":"Kuhn B, Mohr P, Stahl M (2010) Intramolecular hydrogen bonding in medicinal chemistry. J Med Chem 53:2601\u20132611. https:\/\/doi.org\/10.1021\/jm100087s","journal-title":"J Med Chem"},{"key":"525_CR34","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. https:\/\/doi.org\/10.1021\/jm300131x","journal-title":"J Med Chem"},{"key":"525_CR35","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 IC50 data\u2013a statistical analysis. PLoS ONE 8:e61007","journal-title":"PLoS ONE"},{"key":"525_CR36","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":"525_CR37","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MHS Segler","year":"2018","unstructured":"Segler MHS, Kogej T, Tyrchan C, Waller MP (2018) Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci 4:120\u2013131. https:\/\/doi.org\/10.1021\/acscentsci.7b00512","journal-title":"ACS Cent Sci"},{"key":"525_CR38","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-019-0341-z","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous J, Blaschke T, Ulander S et al (2019) Exploring the GDB-13 chemical space using deep generative models. J Cheminform 11:20. https:\/\/doi.org\/10.1186\/s13321-019-0341-z","journal-title":"J Cheminform"},{"key":"525_CR39","doi-asserted-by":"publisher","DOI":"10.26434\/CHEMRXIV.12058026.V2","author":"T Blaschke","year":"2020","unstructured":"Blaschke T, Ar\u00fas-Pous J, Chen H et al (2020) REINVENT 2.0 \u2013 an AI tool for de novo drug design. J Chem Inf Model. https:\/\/doi.org\/10.26434\/CHEMRXIV.12058026.V2","journal-title":"J Chem Inf Model."},{"key":"525_CR40","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","volume":"9","author":"M Olivecrona","year":"2017","unstructured":"Olivecrona M, Blaschke T, Engkvist O, Chen H (2017) Molecular de-novo design through deep reinforcement learning. J Cheminform 9:48. https:\/\/doi.org\/10.1186\/s13321-017-0235-x","journal-title":"J Cheminform"},{"key":"525_CR41","doi-asserted-by":"publisher","first-page":"3666","DOI":"10.1093\/bioinformatics\/bty374","volume":"34","author":"MM Stepniewska-Dziubinska","year":"2018","unstructured":"Stepniewska-Dziubinska MM, Zielenkiewicz P, Siedlecki P (2018) Development and evaluation of a deep learning model for protein\u2013ligand binding affinity prediction. Bioinformatics 34:3666\u20133674. https:\/\/doi.org\/10.1093\/bioinformatics\/bty374","journal-title":"Bioinformatics"},{"key":"525_CR42","unstructured":"Gomes J, Ramsundar B, Feinberg EN, Pande VS (2017) Atomic convolutional networks for predicting protein-ligand binding affinity. arXiv:1703.10603"},{"key":"525_CR43","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1021\/acscentsci.8b00507","volume":"4","author":"EN Feinberg","year":"2018","unstructured":"Feinberg EN, Sur D, Wu Z et al (2018) PotentialNet for Molecular Property Prediction. ACS Cent Sci 4:1520\u20131530. https:\/\/doi.org\/10.1021\/acscentsci.8b00507","journal-title":"ACS Cent Sci"},{"key":"525_CR44","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1021\/acs.jcim.7b00650","volume":"58","author":"J Jim\u00e9nez","year":"2018","unstructured":"Jim\u00e9nez J, \u0160kali\u010d M, Mart\u00ednez-Rosell G, De Fabritiis G (2018) KDEEP: protein-ligand absolute binding affinity prediction via 3D-convolutional neural networks. J Chem Inf Model 58:287\u2013296. https:\/\/doi.org\/10.1021\/acs.jcim.7b00650","journal-title":"J Chem Inf Model"},{"key":"525_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep46710","volume":"7","author":"M W\u00f3jcikowski","year":"2017","unstructured":"W\u00f3jcikowski M, Ballester PJ, Siedlecki P (2017) Performance of machine-learning scoring functions in structure-based virtual screening. Sci Rep 7:1\u201310. https:\/\/doi.org\/10.1038\/srep46710","journal-title":"Sci Rep"},{"key":"525_CR46","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1021\/acs.jcim.6b00740","volume":"57","author":"M Ragoza","year":"2017","unstructured":"Ragoza M, Hochuli J, Idrobo E et al (2017) Protein-ligand scoring with convolutional neural networks. J Chem Inf Model 57:942\u2013957. https:\/\/doi.org\/10.1021\/acs.jcim.6b00740","journal-title":"J Chem Inf Model"},{"key":"525_CR47","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1021\/acs.jcim.6b00355","volume":"56","author":"JC Pereira","year":"2016","unstructured":"Pereira JC, Caffarena ER, Dos Santos CN (2016) Boosting docking-based virtual screening with deep learning. J Chem Inf Model 56:2495\u20132506. https:\/\/doi.org\/10.1021\/acs.jcim.6b00355","journal-title":"J Chem Inf Model"},{"key":"525_CR48","unstructured":"Wallach I, Dzamba M, Heifets A (2015) AtomNet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery. arXiv:1510.02855"},{"key":"525_CR49","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1093\/bioinformatics\/btq112","volume":"26","author":"PJ Ballester","year":"2010","unstructured":"Ballester PJ, Mitchell JBO (2010) A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking. Bioinformatics 26:1169\u20131175. https:\/\/doi.org\/10.1093\/bioinformatics\/btq112","journal-title":"Bioinformatics"},{"key":"525_CR50","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1021\/ci3003039","volume":"52","author":"MA Kayala","year":"2012","unstructured":"Kayala MA, Baldi P (2012) ReactionPredictor: Prediction of complex chemical reactions at the mechanistic level using machine learning. J Chem Inf Model 52:2526\u20132540. https:\/\/doi.org\/10.1021\/ci3003039","journal-title":"J Chem Inf Model"},{"key":"525_CR51","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b02120","author":"TJ Struble","year":"2020","unstructured":"Struble TJ, Alvarez JC, Brown SP et al (2020) Current and future roles of artificial intelligence in medicinal chemistry synthesis. J Med Chem. https:\/\/doi.org\/10.1021\/acs.jmedchem.9b02120","journal-title":"J Med Chem"},{"key":"525_CR52","doi-asserted-by":"publisher","first-page":"5966","DOI":"10.1002\/chem.201605499","volume":"23","author":"MHS Segler","year":"2017","unstructured":"Segler MHS, Waller MP (2017) Neural-symbolic machine learning for retrosynthesis and reaction prediction. Chem - A Eur J 23:5966\u20135971. https:\/\/doi.org\/10.1002\/chem.201605499","journal-title":"Chem - A Eur J"},{"key":"525_CR53","doi-asserted-by":"publisher","first-page":"6091","DOI":"10.1039\/c8sc02339e","volume":"9","author":"P Schwaller","year":"2018","unstructured":"Schwaller P, Gaudin T, L\u00e1nyi D et al (2018) \u201cFound in Translation\u201d: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models. Chem Sci 9:6091\u20136098. https:\/\/doi.org\/10.1039\/c8sc02339e","journal-title":"Chem Sci"},{"key":"525_CR54","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1021\/acs.jcim.9b01067","volume":"60","author":"RP Sheridan","year":"2020","unstructured":"Sheridan RP, Karnachi P, Tudor M et al (2020) Experimental error, kurtosis, activity cliffs, and methodology: what limits the predictivity of quantitative structure-activity relationship models? J Chem Inf Model 60:1969\u20131982. https:\/\/doi.org\/10.1021\/acs.jcim.9b01067","journal-title":"J Chem Inf Model"},{"key":"525_CR55","unstructured":"RDKit: Open-Source Cheminformatics Software. https:\/\/www.rdkit.org"},{"key":"525_CR56","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1021\/acs.jcim.8b00173","volume":"58","author":"A Dalke","year":"2018","unstructured":"Dalke A, Hert J, Kramer C (2018) mmpdb: an open-source matched molecular pair platform for large multiproperty data sets. J Chem Inf Model 58:902\u2013910. https:\/\/doi.org\/10.1021\/acs.jcim.8b00173","journal-title":"J Chem Inf Model"},{"key":"525_CR57","doi-asserted-by":"publisher","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","volume":"45","author":"A Gaulton","year":"2017","unstructured":"Gaulton A, Hersey A, Nowotka M et al (2017) The ChEMBL database in 2017. Nucleic Acids Res 45:D945\u2013D954","journal-title":"Nucleic Acids Res"},{"key":"525_CR58","doi-asserted-by":"publisher","unstructured":"Akiba T, Sano S, Yanase T et al (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, USA, pp 2623\u20132631. https:\/\/doi.org\/10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"key":"525_CR59","doi-asserted-by":"publisher","first-page":"329","DOI":"10.3389\/fnagi.2017.00329","volume":"9","author":"A Sarica","year":"2017","unstructured":"Sarica A, Cerasa A, Quattrone A (2017) Random forest algorithm for the classification of neuroimaging data in Alzheimer\u2019s disease: a systematic review. Front Aging Neurosci 9:329. https:\/\/doi.org\/10.3389\/fnagi.2017.00329","journal-title":"Front Aging Neurosci"},{"key":"525_CR60","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":"525_CR61","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco D, Jurman G (2020) The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21:6. https:\/\/doi.org\/10.1186\/s12864-019-6413-7","journal-title":"BMC Genomics"},{"key":"525_CR62","first-page":"83","volume":"4","author":"AN Kolmogorov","year":"1933","unstructured":"Kolmogorov AN (1933) Sulla determinazione emp\u00edrica di uma legge di distribuzione (On the empirical determination of a distribution law). Giorn Ist Ital Attuar 4:83\u201391","journal-title":"Giorn Ist Ital Attuar"},{"key":"525_CR63","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1214\/aoms\/1177730256","volume":"19","author":"N Smirnov","year":"1948","unstructured":"Smirnov N (1948) Table for estimating the goodness of fit of empirical distributions. Ann Math Stat 19:279\u2013281","journal-title":"Ann Math Stat"},{"key":"525_CR64","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","volume":"47","author":"WH Kruskal","year":"1952","unstructured":"Kruskal WH, Wallis WA (1952) Use of ranks in one-criterion variance analysis. J Am Stat Assoc 47:583\u2013621","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"525_CR65","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann HB, Whitney DR (1947) On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat 18(1):50\u201360. https:\/\/doi.org\/10.1214\/aoms\/1177730491","journal-title":"Ann Math Stat"},{"key":"525_CR66","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1021\/jm070838y","volume":"51","author":"PJ Hajduk","year":"2008","unstructured":"Hajduk PJ, Sauer DR (2008) Statistical analysis of the effects of common chemical substituents on ligand potency. J Med Chem 51:553\u2013564. https:\/\/doi.org\/10.1021\/jm070838y","journal-title":"J Med Chem"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00525-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-021-00525-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00525-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T17:08:47Z","timestamp":1625245727000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-021-00525-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,2]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["525"],"URL":"https:\/\/doi.org\/10.1186\/s13321-021-00525-z","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,2]]},"assertion":[{"value":"10 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 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. CM, CT and EN are employees of AstraZeneca and own stock options.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"47"}}