{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T03:57:31Z","timestamp":1784865451450,"version":"3.55.0"},"reference-count":145,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["716063"],"award-info":[{"award-number":["716063"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Integrative Life Science Doctoral Programme, University of Helsinki"},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["322675"],"award-info":[{"award-number":["322675"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Application of machine and deep learning methods in drug discovery and cancer research has gained a considerable amount of attention in the past years. As the field grows, it becomes crucial to systematically evaluate the performance of novel computational solutions in relation to established techniques. To this end, we compare rule-based and data-driven molecular representations in prediction of drug combination sensitivity and drug synergy scores using standardized results of 14 high-throughput screening studies, comprising 64 200 unique combinations of 4153 molecules tested in 112 cancer cell lines. We evaluate the clustering performance of molecular representations and quantify their similarity by adapting the Centered Kernel Alignment metric. Our work demonstrates that to identify an optimal molecular representation type, it is necessary to supplement quantitative benchmark results with qualitative considerations, such as model interpretability and robustness, which may vary between and throughout preclinical drug development projects.<\/jats:p>","DOI":"10.1093\/bib\/bbab291","type":"journal-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T19:47:18Z","timestamp":1628538438000},"source":"Crossref","is-referenced-by-count":101,"title":["Comparative analysis of molecular fingerprints in prediction of drug combination effects"],"prefix":"10.1093","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8386-110X","authenticated-orcid":false,"given":"B","family":"Zagidullin","sequence":"first","affiliation":[{"name":"Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5624-5275","authenticated-orcid":false,"given":"Z","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering & Computer Science, University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8275-2852","authenticated-orcid":false,"given":"Y","family":"Guan","sequence":"additional","affiliation":[{"name":"Department of Computational Medicine & Bioinformatics, University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9818-6370","authenticated-orcid":false,"given":"E","family":"Pitk\u00e4nen","sequence":"additional","affiliation":[{"name":"Institute for Molecular Medicine Finland (FIMM) & Applied Tumor Genomics Research Program, Research Programs Unit, University of Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7480-7710","authenticated-orcid":false,"given":"J","family":"Tang","sequence":"additional","affiliation":[{"name":"Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,8,17]]},"reference":[{"key":"2021123023023577900_ref1","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1038\/nbt.4233","article-title":"Deep learning in biomedicine","volume":"36","author":"Wainberg","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2021123023023577900_ref2","doi-asserted-by":"publisher","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J R Soc Interface"},{"key":"2021123023023577900_ref3","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1016\/j.drudis.2018.05.010","article-title":"Machine learning in chemoinformatics and drug discovery","volume":"23","author":"Lo","year":"2018","journal-title":"Drug Discov Today"},{"key":"2021123023023577900_ref4","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"2021123023023577900_ref5","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat Methods"},{"key":"2021123023023577900_ref6","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2021123023023577900_ref7","doi-asserted-by":"crossref","first-page":"11242","DOI":"10.1038\/s41598-018-29523-2","article-title":"Prognostication and risk factors for cystic fibrosis via automated machine learning","volume":"8","author":"Alaa","year":"2018","journal-title":"Sci Rep"},{"key":"2021123023023577900_ref8","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","volume":"577","author":"Senior","year":"2020","journal-title":"Nature"},{"key":"2021123023023577900_ref9","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"},{"key":"2021123023023577900_ref10","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/s41746-019-0122-0","article-title":"Deep learning and alternative learning strategies for retrospective real-world clinical data","volume":"2","author":"Chen","year":"2019","journal-title":"NPJ Digit Med"},{"key":"2021123023023577900_ref11","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1038\/s41563-019-0332-5","article-title":"Opportunities and challenges using artificial intelligence in ADME\/Tox","volume":"18","author":"Bhhatarai","year":"2019","journal-title":"Nat Mater"},{"key":"2021123023023577900_ref12","doi-asserted-by":"crossref","first-page":"5441","DOI":"10.1039\/C8SC00148K","article-title":"Large-scale comparison of machine learning methods for drug target prediction on ChEMBL","volume":"9","author":"Mayr","year":"2018","journal-title":"Chem Sci"},{"key":"2021123023023577900_ref13","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0149-7189(79)90048-X","article-title":"Assessing the impact of planned social change","volume":"2","author":"Campbell","year":"1979","journal-title":"Eval Program Plann"},{"key":"2021123023023577900_ref14","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-1-349-17295-5_4","article-title":"Problems of monetary management: the UK experience","author":"Goodhart","year":"1984","journal-title":"Monetary Theory Practice"},{"key":"2021123023023577900_ref15","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1136\/bmj.39377.387373.AD","article-title":"Measuring performance and missing the point?","volume":"335","author":"Heath","year":"2007","journal-title":"BMJ"},{"key":"2021123023023577900_ref16","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","article-title":"Potential biases in machine learning algorithms using electronic health record data","volume":"178","author":"Gianfrancesco","year":"2018","journal-title":"JAMA Intern Med"},{"key":"2021123023023577900_ref17","volume-title":"World Models","author":"Ha","year":"2018"},{"key":"2021123023023577900_ref18","volume-title":"arXiv [cs.LG]","author":"Wagstaff","year":"2012"},{"key":"2021123023023577900_ref19","doi-asserted-by":"crossref","first-page":"3770","DOI":"10.1021\/acs.jcim.0c00502","article-title":"Uncertainty quantification using neural networks for molecular property prediction","volume":"60","author":"Hirschfeld","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref20","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/bib\/bbu010","article-title":"Toward more realistic drug-target interaction predictions","volume":"16","author":"Pahikkala","year":"2015","journal-title":"Brief Bioinform"},{"key":"2021123023023577900_ref21","doi-asserted-by":"crossref","first-page":"8154","DOI":"10.1039\/C9SC00616H","article-title":"Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning","volume":"10","author":"Zhang","year":"2019","journal-title":"Chem Sci"},{"key":"2021123023023577900_ref22","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.3389\/fphar.2019.01303","article-title":"Applications of deep-learning in exploiting large-scale and heterogeneous compound data in industrial pharmaceutical research","volume":"10","author":"David","year":"2019","journal-title":"Front Pharmacol"},{"key":"2021123023023577900_ref23","doi-asserted-by":"crossref","first-page":"23","DOI":"10.2174\/13816128113199990470","article-title":"Network pharmacology strategies toward multi-target anticancer therapies: from computational models to experimental design principles","volume":"20","author":"Tang","year":"2014","journal-title":"Curr Pharm Des"},{"key":"2021123023023577900_ref24","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1007\/978-1-4939-7154-1_30","article-title":"Informatics approaches for predicting, understanding, and testing cancer drug combinations","volume":"1636","author":"Tang","year":"2017","journal-title":"Methods Mol Biol"},{"key":"2021123023023577900_ref25","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1158\/2159-8290.CD-13-0350","article-title":"Individualized systems medicine strategy to tailor treatments for patients with chemorefractory acute myeloid leukemia","volume":"3","author":"Pemovska","year":"2013","journal-title":"Cancer Discov"},{"key":"2021123023023577900_ref26","doi-asserted-by":"crossref","first-page":"3564","DOI":"10.1158\/0008-5472.CAN-17-0489","article-title":"The National Cancer Institute ALMANAC: a comprehensive screening resource for the detection of anticancer drug pairs with enhanced therapeutic activity","volume":"77","author":"Holbeck","year":"2017","journal-title":"Cancer Res"},{"key":"2021123023023577900_ref27","doi-asserted-by":"crossref","first-page":"7977","DOI":"10.1073\/pnas.1337088100","article-title":"Systematic discovery of multicomponent therapeutics","volume":"100","author":"Borisy","year":"2003","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2021123023023577900_ref28","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1177\/1947601912440575","article-title":"Quantitative methods for assessing drug synergism","volume":"2","author":"Tallarida","year":"2011","journal-title":"Genes Cancer"},{"key":"2021123023023577900_ref29","doi-asserted-by":"crossref","first-page":"e1006752","DOI":"10.1371\/journal.pcbi.1006752","article-title":"Drug combination sensitivity scoring facilitates the discovery of synergistic and efficacious drug combinations in cancer","volume":"15","author":"Malyutina","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2021123023023577900_ref30","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1111\/j.1744-7348.1939.tb06990.x","article-title":"The toxicity of poisons applied jointly1","volume":"26","author":"Bliss","year":"1939","journal-title":"Ann Appl Biol"},{"key":"2021123023023577900_ref31","first-page":"93","article-title":"What is synergy?","volume":"41","author":"Berenbaum","year":"1989","journal-title":"Pharmacol Rev"},{"key":"2021123023023577900_ref32","first-page":"331","article-title":"The search for synergy: a critical review from a response surface perspective","volume":"47","author":"Greco","year":"1995","journal-title":"Pharmacol Rev"},{"key":"2021123023023577900_ref33","first-page":"285","article-title":"The problem of synergism and antagonism of combined drugs","volume":"3","author":"Loewe","year":"1953","journal-title":"Arzneimittelforschung"},{"key":"2021123023023577900_ref34","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.csbj.2015.09.001","article-title":"Searching for drug synergy in complex dose-response landscapes using an interaction potency model","volume":"13","author":"Yadav","year":"2015","journal-title":"Comput Struct Biotechnol J"},{"key":"2021123023023577900_ref35","doi-asserted-by":"crossref","first-page":"3186","DOI":"10.1021\/jm401411z","article-title":"Molecular similarity in medicinal chemistry","volume":"57","author":"Maggiora","year":"2014","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref36","doi-asserted-by":"crossref","first-page":"4977","DOI":"10.1021\/jm4004285","article-title":"QSAR modeling: where have you been? Where are you going to?","volume":"57","author":"Cherkasov","year":"2014","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref37","doi-asserted-by":"crossref","DOI":"10.3389\/fphar.2018.01275","article-title":"QSAR-based virtual screening: advances and applications in drug discovery","volume":"9","author":"Neves","year":"2018","journal-title":"Front Pharmacol"},{"key":"2021123023023577900_ref38","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13321-016-0148-0","article-title":"Comparing structural fingerprints using a literature-based similarity benchmark","volume":"8","author":"O\u2019Boyle","year":"2016","journal-title":"J Chem"},{"key":"2021123023023577900_ref39","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of MDL keys for use in drug discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J Chem Inf Comput Sci"},{"key":"2021123023023577900_ref40","volume-title":"Molecular Descriptors for Chemoinformatics, 2 Volume Set: Volume I: Alphabetical Listing\/Volume II: Appendices, References","author":"Todeschini","year":"2009"},{"key":"2021123023023577900_ref41","doi-asserted-by":"crossref","first-page":"8705","DOI":"10.1021\/acs.jmedchem.0c00385","article-title":"Learning molecular representations for medicinal chemistry","volume":"63","author":"Chuang","year":"2020","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref42","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The generation of a unique machine description for chemical structures-a technique developed at chemical abstracts service","volume":"5","author":"Morgan","year":"1965","journal-title":"J Chem Doc"},{"key":"2021123023023577900_ref43","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref44","doi-asserted-by":"crossref","first-page":"81","DOI":"10.2147\/JRLCR.S46843","article-title":"Pharmacophore modeling: advances, limitations, and current utility in drug discovery","volume":"7","author":"Voet","year":"2014","journal-title":"J Receptor Ligand Channel Res"},{"key":"2021123023023577900_ref45","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1093\/bib\/bby061","article-title":"Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases","volume":"20","author":"Rifaioglu","year":"2019","journal-title":"Brief Bioinform"},{"key":"2021123023023577900_ref46","article-title":"Dive into Deep Learning","volume-title":"arXiv preprint arXiv:2106.11342","year":"2021"},{"key":"2021123023023577900_ref47","volume-title":"arXiv [stat.ML]","author":"Goh","year":"2017"},{"key":"2021123023023577900_ref48","volume-title":"arXiv [stat.ML]","author":"Goh","year":"2017"},{"key":"2021123023023577900_ref49","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS Cent Sci"},{"key":"2021123023023577900_ref50","volume-title":"arXiv [cs.CL]","author":"Cho","year":"2014"},{"key":"2021123023023577900_ref51","volume-title":"arXiv [stat.ML]","author":"Kingma","year":"2013"},{"key":"2021123023023577900_ref52","volume-title":"arXiv [cs.LG]","author":"Honda","year":"2019"},{"key":"2021123023023577900_ref53","doi-asserted-by":"crossref","first-page":"4797","DOI":"10.1021\/acs.molpharmaceut.9b00520","article-title":"Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders","volume":"16","author":"Manica","year":"2019","journal-title":"Mol Pharm"},{"key":"2021123023023577900_ref54","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2021123023023577900_ref55","volume-title":"arXiv [q-bio.QM]","author":"Wang","year":"2020"},{"key":"2021123023023577900_ref56","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1039\/C8SC04175J","article-title":"Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations","volume":"10","author":"Winter","year":"2019","journal-title":"Chem Sci"},{"key":"2021123023023577900_ref57","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref58","volume-title":"Daylight Theory: SMARTS \u2013 A Language for Describing Molecular Patterns","author":"Daylight Theory Manual. Daylight Version 4.9","year":"2011"},{"key":"2021123023023577900_ref59","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/1758-2946-4-22","article-title":"Towards a universal SMILES representation - a standard method to generate canonical SMILES based on the InChI","volume":"4","author":"O\u2019Boyle","year":"2012","journal-title":"J Chem"},{"key":"2021123023023577900_ref60","volume-title":"arXiv [stat.ML]","author":"Ramsundar","year":"2015"},{"key":"2021123023023577900_ref61","volume-title":"arXiv [cs.LG]","author":"Kipf","year":"2016"},{"key":"2021123023023577900_ref62","volume-title":"arXiv [stat.ML]","author":"Kipf","year":"2016"},{"key":"2021123023023577900_ref63","volume-title":"arXiv [cs.LG]","author":"Gilmer","year":"2017"},{"key":"2021123023023577900_ref64","volume-title":"arXiv [cs.LG]","author":"Duvenaud","year":"2015"},{"key":"2021123023023577900_ref65","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref66","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","article-title":"Molecular graph convolutions: moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J Comput Aided Mol Des"},{"key":"2021123023023577900_ref67","volume-title":"Machine Learning on Graphs: A Model and Comprehensive Taxonomy","author":"Chami","year":"2020"},{"key":"2021123023023577900_ref68","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem Sci"},{"key":"2021123023023577900_ref69","volume-title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","author":"Hu","year":"2020"},{"key":"2021123023023577900_ref70","volume-title":"arXiv [cs.LG]","author":"Dwivedi","year":"2020"},{"key":"2021123023023577900_ref71","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.tips.2020.01.011","article-title":"Charting the fragmented landscape of drug synergy","volume":"41","author":"Meyer","year":"2020","journal-title":"Trends Pharmacol Sci"},{"key":"2021123023023577900_ref72","doi-asserted-by":"crossref","first-page":"181","DOI":"10.3389\/fphar.2015.00181","article-title":"What is synergy? The Saariselk\u00e4 agreement revisited","volume":"6","author":"Tang","year":"2015","journal-title":"Front Pharmacol"},{"key":"2021123023023577900_ref73","doi-asserted-by":"crossref","first-page":"W43","DOI":"10.1093\/nar\/gkz337","article-title":"DrugComb: an integrative cancer drug combination data portal","volume":"47","author":"Zagidullin","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2021123023023577900_ref74","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":"2021123023023577900_ref75","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s13321-020-00456-1","article-title":"An open source chemical structure curation pipeline using RDKit","volume":"12","author":"Bento","year":"2020","journal-title":"J Chem"},{"key":"2021123023023577900_ref76","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/1758-2946-5-26","article-title":"Open-source platform to benchmark fingerprints for ligand-based virtual screening","volume":"5","author":"Riniker","year":"2013","journal-title":"J Chem"},{"key":"2021123023023577900_ref77","doi-asserted-by":"crossref","first-page":"7393","DOI":"10.1021\/acs.jmedchem.7b00696","article-title":"A simple representation of three-dimensional molecular structure","volume":"60","author":"Axen","year":"2017","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref78","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1073\/pnas.37.11.760","article-title":"Maximum properties and inequalities for the eigenvalues of completely continuous operators","volume":"37","author":"Fan","year":"1951","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2021123023023577900_ref79","volume-title":"arXiv [stat.ML]","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2021123023023577900_ref80","volume-title":"arXiv [cs.LG]","author":"Hu","year":"2019"},{"key":"2021123023023577900_ref81","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018","journal-title":"Semantic Web"},{"key":"2021123023023577900_ref82","volume-title":"arXiv [cs.SI]","author":"Hamilton","year":"2017"},{"key":"2021123023023577900_ref83","volume-title":"arXiv [cs.DS]","author":"Luxburg","year":"2007"},{"key":"2021123023023577900_ref84","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","author":"Glorot","year":"2011"},{"key":"2021123023023577900_ref85","volume-title":"arXiv [cs.LG]","author":"Klambauer","year":"2017"},{"key":"2021123023023577900_ref86","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","author":"Glorot","year":"2010"},{"key":"2021123023023577900_ref87","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","article-title":"ZINC 15--ligand discovery for everyone","volume":"55","author":"Sterling","year":"2015","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref88","volume-title":"arXiv [cs.LG]","author":"Kingma","year":"2014"},{"key":"2021123023023577900_ref89","volume-title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","author":"Wang","year":"2019"},{"key":"2021123023023577900_ref90","volume-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv [cs.LG]","author":"Paszke","year":"2019"},{"key":"2021123023023577900_ref91","doi-asserted-by":"crossref","DOI":"10.1145\/3292500.3330701","volume-title":"Optuna: A Next-Generation Hyperparameter Optimization Framework","author":"Akiba","year":"2019"},{"key":"2021123023023577900_ref92","doi-asserted-by":"crossref","first-page":"3902","DOI":"10.1021\/acs.jmedchem.7b00204","article-title":"Prediction of antibiotic interactions using descriptors derived from molecular structure","volume":"60","author":"Mason","year":"2017","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref93","first-page":"1089","article-title":"No unbiased estimator of the variance of K-fold cross-validation","volume":"5","author":"Bengio","year":"2004","journal-title":"J Mach Learn Res"},{"key":"2021123023023577900_ref94","doi-asserted-by":"crossref","DOI":"10.21236\/ADA150798","volume-title":"Better Bootstrap Confidence Intervals","author":"Efron","year":"1984"},{"key":"2021123023023577900_ref95","first-page":"507","article-title":"Frequency distribution of the values of the correlation coefficient in samples from an indefinitely large population","volume":"10","author":"Fisher","year":"1915","journal-title":"Biometrika"},{"key":"2021123023023577900_ref96","first-page":"1","article-title":"Introduction","author":"Efron","year":"1993","journal-title":"An Introduction to the Bootstrap"},{"key":"2021123023023577900_ref97","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1080\/00221309809595548","article-title":"Averaging correlations: expected values and bias in combined Pearsons and Fisher\u2019s z-transformations","volume":"125","author":"Corey","year":"1998","journal-title":"J Gen Psychol"},{"key":"2021123023023577900_ref98","doi-asserted-by":"crossref","first-page":"294","DOI":"10.3758\/s13428-016-0702-8","article-title":"Confidence intervals for correlations when data are not normal","volume":"49","author":"Bishara","year":"2017","journal-title":"Behav Res Methods"},{"key":"2021123023023577900_ref99","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/biomet\/52.3-4.591","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"key":"2021123023023577900_ref100","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1021\/ci800249s","article-title":"How similar are similarity searching methods? A principal component analysis of molecular descriptor space","volume":"49","author":"Bender","year":"2009","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref101","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s13321-015-0069-3","article-title":"Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?","volume":"7","author":"Bajusz","year":"2015","journal-title":"J Chem"},{"key":"2021123023023577900_ref102","doi-asserted-by":"crossref","first-page":"2884","DOI":"10.1021\/ci300261r","article-title":"Similarity coefficients for binary chemoinformatics data: overview and extended comparison using simulated and real data sets","volume":"52","author":"Todeschini","year":"2012","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref103","first-page":"1","article-title":"Similarity measures in chemometrics and chemoinformatics","author":"Todeschini","year":"2020","journal-title":"Encyclop Anal Chem"},{"key":"2021123023023577900_ref104","volume-title":"Book in Progress","author":"Algebra, Topology, Differential Calculus, and Optimization Theory for Computer Science and Machine Learning","year":"2020"},{"key":"2021123023023577900_ref105","volume-title":"On the Generalization of Tanimoto-Type Kernels to Real Valued Functions","author":"Szedmak","year":"2020"},{"key":"2021123023023577900_ref106","article-title":"The kernel trick for distances","volume":"13","author":"Sch\u00f6lkopf","year":"2001","journal-title":"Adv Neural Inform Process Syst"},{"key":"2021123023023577900_ref107","article-title":"SVCCA: singular vector canonical correlation analysis for deep learning dynamics and interpretability","volume":"30","author":"Raghu","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2021123023023577900_ref108","volume-title":"Insights on Representational Similarity in Neural Networks with Canonical Correlation","author":"Morcos","year":"2018"},{"key":"2021123023023577900_ref109","volume-title":"Similarity of Neural Network Representations Revisited","author":"Kornblith","year":"2019"},{"key":"2021123023023577900_ref110","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/11564089_7","article-title":"Measuring statistical dependence with Hilbert-Schmidt norms","author":"Gretton","year":"2005","journal-title":"Algorithmic Learning Theory"},{"key":"2021123023023577900_ref111","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1145\/1273496.1273600","article-title":"Supervised feature selection via dependence estimation","volume-title":"Proceedings of the 24th International Conference on Machine Learning","author":"Song","year":"2007"},{"key":"2021123023023577900_ref112","first-page":"2075","article-title":"Kernel methods for measuring independence","volume":"6","author":"Gretton","year":"2005","journal-title":"J Mach Learn Res"},{"key":"2021123023023577900_ref113","doi-asserted-by":"crossref","DOI":"10.32470\/CCN.2019.1300-0","volume-title":"The Effect of Task and Training on Intermediate Representations in Convolutional Neural Networks Revealed with Modified RV Similarity Analysis","author":"Thompson","year":"2019"},{"key":"2021123023023577900_ref114","doi-asserted-by":"crossref","first-page":"257","DOI":"10.2307\/2347233","article-title":"A unifying tool for linear multivariate statistical methods: the RV- coefficient","volume":"25","author":"Robert","year":"1976","journal-title":"Appl Stat"},{"key":"2021123023023577900_ref115","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1214\/16-SS116","article-title":"Measuring multivariate association and beyond","volume":"10","author":"Josse","year":"2016","journal-title":"Stat Surv"},{"key":"2021123023023577900_ref116","volume-title":"WHO ATC Code - PubChem Data Source","author":"PubChem","year":"2018"},{"key":"2021123023023577900_ref117","volume-title":"Finding Groups in Data: An Introduction to Cluster Analysis","author":"Kaufman","year":"2009"},{"key":"2021123023023577900_ref118","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/03610917408548446","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Calinski","year":"1974","journal-title":"Commun Stat Simul Comput"},{"key":"2021123023023577900_ref119","doi-asserted-by":"crossref","DOI":"10.1002\/9781118887486","volume-title":"Applied Multivariate Data Analysis","author":"Everitt","year":"2001"},{"key":"2021123023023577900_ref120","doi-asserted-by":"crossref","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J Med Chem"},{"key":"2021123023023577900_ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (XAI): toward medical XAI","author":"Tjoa","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2021123023023577900_ref122","doi-asserted-by":"crossref","first-page":"3330","DOI":"10.1021\/acs.jcim.9b00297","article-title":"Reliable prediction errors for deep neural networks using test-time dropout","volume":"59","author":"Cort\u00e9s-Ciriano","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2021123023023577900_ref123","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1016\/j.drudis.2020.11.037","article-title":"Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data","volume":"26","author":"Bender","year":"2021","journal-title":"Drug Discov Today"},{"key":"2021123023023577900_ref124","doi-asserted-by":"crossref","first-page":"8373","DOI":"10.1039\/D0CP00305K","article-title":"Are 2D fingerprints still valuable for drug discovery?","volume":"22","author":"Gao","year":"2020","journal-title":"Phys Chem Chem Phys"},{"key":"2021123023023577900_ref125","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.ccell.2020.09.014","article-title":"Predicting drug response and synergy using a deep learning model of human cancer cells","volume":"38","author":"Kuenzi","year":"2020","journal-title":"Cancer Cell"},{"key":"2021123023023577900_ref126","volume-title":"ProtTrans: Towards Cracking the Language of Life\u2019s Code Through Self-Supervised Deep Learning and High Performance Computing","author":"Elnaggar","year":"2020"},{"key":"2021123023023577900_ref127","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1093\/bib\/bbz153","article-title":"Improving drug response prediction by integrating multiple data sources: matrix factorization, kernel and network-based approaches","volume":"22","author":"G\u00fcven\u00e7 Paltun","year":"2021","journal-title":"Brief Bioinform"},{"key":"2021123023023577900_ref128","first-page":"7079","article-title":"Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules Using SELFIES","volume-title":"Chem Sci","author":"Nigam","year":"2021"},{"key":"2021123023023577900_ref129","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1038\/s41467-019-13807-w","article-title":"De novo generation of hit-like molecules from gene expression signatures using artificial intelligence","volume":"11","author":"M\u00e9ndez-Lucio","year":"2020","journal-title":"Nat Commun"},{"key":"2021123023023577900_ref130","volume-title":"Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models","author":"Jin","year":"2020"},{"key":"2021123023023577900_ref131","doi-asserted-by":"crossref","first-page":"4037","DOI":"10.1038\/s41598-021-83102-6","article-title":"Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy","volume":"11","author":"Bychkov","year":"2021","journal-title":"Sci Rep"},{"key":"2021123023023577900_ref132","volume-title":"Deep Neural Decision Trees. arXiv [cs.LG]","author":"Yang","year":"2018"},{"key":"2021123023023577900_ref133","author":"Abutbul","year":"2020"},{"key":"2021123023023577900_ref134","volume-title":"CatBoost: unbiased boosting with categorical features. arXiv [cs.LG]","author":"Prokhorenkova","year":"2017"},{"key":"2021123023023577900_ref135","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1023\/A:1017934522171","article-title":"Using iterated bagging to Debias regressions","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2021123023023577900_ref136","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"Bent\u00e9jac","year":"2021","journal-title":"Artif Intell Rev"},{"key":"2021123023023577900_ref137","first-page":"192","article-title":"Data-driven advice for applying machine learning to bioinformatics problems","volume":"23","author":"Olson","year":"2018","journal-title":"Pac Symp Biocomput"},{"key":"2021123023023577900_ref138","volume-title":"Cyclical Learning Rates for Training Neural Networks. arXiv [cs.CV]","author":"Smith","year":"2015"},{"key":"2021123023023577900_ref139","volume-title":"GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation. arXiv [cs.LG]","author":"Brockschmidt","year":"2019"},{"key":"2021123023023577900_ref140","volume-title":"On the Bottleneck of Graph Neural Networks and its Practical Implications. arXiv [cs.LG]","author":"Alon","year":"2020"},{"key":"2021123023023577900_ref141","volume-title":"Scaling Laws for Neural Language Models. arXiv [cs.LG]","author":"Kaplan","year":"2020"},{"key":"2021123023023577900_ref142","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-09799-2","article-title":"Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen","volume":"10","author":"Menden","year":"2019","journal-title":"Nat Commun"},{"key":"2021123023023577900_ref143","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/bioinformatics\/btx806","article-title":"DeepSynergy: predicting anti-cancer drug synergy with deep learning","volume":"34","author":"Preuer","year":"2018","journal-title":"Bioinformatics"},{"key":"2021123023023577900_ref144","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1158\/1535-7163.MCT-15-0843","article-title":"An unbiased oncology compound screen to identify novel combination strategies","volume":"15","author":"O\u2019Neil","year":"2016","journal-title":"Mol Cancer Ther"},{"key":"2021123023023577900_ref145","doi-asserted-by":"crossref","first-page":"509","DOI":"10.3389\/fchem.2019.00509","article-title":"Predicting synergism of cancer drug combinations using NCI-ALMANAC data","volume":"7","author":"Sidorov","year":"2019","journal-title":"Front Chem"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab291\/41974966\/bbab291.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab291\/41974966\/bbab291.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,30]],"date-time":"2021-12-30T23:03:55Z","timestamp":1640905435000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbab291\/6353238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":145,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab291","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,11]]},"published":{"date-parts":[[2021,8,17]]},"article-number":"bbab291"}}