{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:15:06Z","timestamp":1787318106528,"version":"build-2736575974"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T00:00:00Z","timestamp":1581465600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T00:00:00Z","timestamp":1581465600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["51NF40-185544"],"award-info":[{"award-number":["51NF40-185544"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The chemical sciences are producing an unprecedented amount of large, high-dimensional data sets containing chemical structures and associated properties. However, there are currently no algorithms to visualize such data while preserving both global and local features with a sufficient level of detail to allow for human inspection and interpretation. Here, we propose a solution to this problem with a new data visualization method, TMAP, capable of representing data sets of up to millions of data points and arbitrary high dimensionality as a two-dimensional tree (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/tmap.gdb.tools\">http:\/\/tmap.gdb.tools<\/jats:ext-link>\n                    ). Visualizations based on TMAP are better suited than t-SNE or UMAP for the exploration and interpretation of large data sets due to their tree-like nature, increased local and global neighborhood and structure preservation, and the transparency of the methods the algorithm is based on. We apply TMAP to the most used chemistry data sets including databases of molecules such as ChEMBL, FDB17, the Natural Products Atlas, DSSTox, as well as to the MoleculeNet benchmark collection of data sets. We also show its broad applicability with further examples from biology, particle physics, and literature.\n                  <\/jats:p>","DOI":"10.1186\/s13321-020-0416-x","type":"journal-article","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T12:02:43Z","timestamp":1581508963000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":253,"title":["Visualization of very large high-dimensional data sets as minimum spanning trees"],"prefix":"10.1186","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-4407","authenticated-orcid":false,"given":"Daniel","family":"Probst","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2724-2942","authenticated-orcid":false,"given":"Jean-Louis","family":"Reymond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,2,12]]},"reference":[{"key":"416_CR1","doi-asserted-by":"publisher","unstructured":"Callahan SP, et al (2006) VisTrails: Visualization meets data management. In: Proceedings of the 2006 ACM SIGMOD international conference on management of data. ACM. pp 745\u2013747. https:\/\/doi.org\/10.1145\/1142473.1142574","DOI":"10.1145\/1142473.1142574"},{"key":"416_CR2","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1126\/science.1197654","volume":"331","author":"P Fox","year":"2011","unstructured":"Fox P, Hendler J (2011) Changing the equation on scientific data visualization. Science 331:705\u2013708","journal-title":"Science"},{"key":"416_CR3","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1126\/science.1199644","volume":"331","author":"J-B Michel","year":"2011","unstructured":"Michel J-B et al (2011) Quantitative analysis of culture using millions of digitized books. Science 331:176\u2013182","journal-title":"Science"},{"key":"416_CR4","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MCG.2013.54","volume":"33","author":"D Keim","year":"2013","unstructured":"Keim D, Qu H, Ma K (2013) Big-data visualization. IEEE Comput Graphics Appl 33:20\u201321","journal-title":"IEEE Comput Graphics Appl"},{"key":"416_CR5","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1016\/j.drudis.2013.10.012","volume":"19","author":"FF Costa","year":"2014","unstructured":"Costa FF (2014) Big data in biomedicine. Drug Disc Today 19:433\u2013440","journal-title":"Drug Disc Today"},{"key":"416_CR6","doi-asserted-by":"publisher","first-page":"e1002195","DOI":"10.1371\/journal.pbio.1002195","volume":"13","author":"ZD Stephens","year":"2015","unstructured":"Stephens ZD et al (2015) Big data: astronomical or genomical? PLoS Biol 13:e1002195","journal-title":"PLoS Biol"},{"key":"416_CR7","unstructured":"Bikakis N, Sellis T (2016) Exploration and visualization in the web of big linked data: a survey of the state of the art. arXiv:1601.08059"},{"key":"416_CR8","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.ccell.2018.07.001","volume":"34","author":"A Kahles","year":"2018","unstructured":"Kahles A et al (2018) Comprehensive analysis of alternative splicing across tumors from 8,705 patients. Cancer Cell 34:211\u2013224.e6","journal-title":"Cancer Cell"},{"key":"416_CR9","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 et al (2019) Exploring the GDB-13 chemical space using deep generative models. J Cheminform 11:20","journal-title":"J Cheminform"},{"key":"416_CR10","first-page":"66","volume":"10","author":"L van der Maaten","year":"2009","unstructured":"van der Maaten L, Postma EO, van der Herik HJ (2009) Dimensionality reduction : a comparative review. J Mach Learn Res 10:66\u201371","journal-title":"J Mach Learn Res"},{"key":"416_CR11","doi-asserted-by":"publisher","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","volume":"45","author":"A Gaulton","year":"2017","unstructured":"Gaulton A et al (2017) The ChEMBL database in 2017. Nucleic Acids Res 45:D945\u2013D954","journal-title":"Nucleic Acids Res"},{"key":"416_CR12","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","volume":"52","author":"L Ruddigkeit","year":"2012","unstructured":"Ruddigkeit L, van Deursen R, Blum LC, Reymond J-L (2012) Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J Chem Inf Model 52:2864\u20132875","journal-title":"J Chem Inf Model"},{"key":"416_CR13","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1021\/acs.jcim.7b00020","volume":"57","author":"R Visini","year":"2017","unstructured":"Visini R, Awale M, Reymond J-L (2017) Fragment database FDB-17. J Chem Inf Model 57:700\u2013709","journal-title":"J Chem Inf Model"},{"key":"416_CR14","doi-asserted-by":"publisher","first-page":"661","DOI":"10.2533\/chimia.2017.661","volume":"71","author":"M Awale","year":"2017","unstructured":"Awale M, Visini R, Probst D, Ar\u00fas-Pous J, Reymond J-L (2017) Chemical space: big data challenge for molecular diversity. Chimia 71:661\u2013666","journal-title":"Chimia"},{"key":"416_CR15","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/S0027-5107(01)00289-5","volume":"499","author":"AM Richard","year":"2002","unstructured":"Richard AM, Williams CR (2002) Distributed structure-searchable toxicity (DSSTox) public database network: a proposal. Mutat Res 499:27\u201352","journal-title":"Mutat Res"},{"key":"416_CR16","unstructured":"Natural Products Atlas. https:\/\/www.npatlas.org\/joomla\/"},{"key":"416_CR17","doi-asserted-by":"publisher","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","volume":"46","author":"DS Wishart","year":"2018","unstructured":"Wishart DS et al (2018) DrugBank 5.0: a major update to the DrugBank database for 2018. Nucleic Acids Res. 46:D1074\u2013D1082","journal-title":"Nucleic Acids Res."},{"key":"416_CR18","unstructured":"Wu Z, et al (2017) MoleculeNet: A benchmark for molecular machine learning. arXiv:1703.00564[physics, stat]"},{"key":"416_CR19","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1021\/cc0000388","volume":"3","author":"TI Oprea","year":"2001","unstructured":"Oprea TI, Gottfries J (2001) Chemography: the art of navigating in chemical space. J Comb Chem 3:157\u2013166","journal-title":"J Comb Chem"},{"key":"416_CR20","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1021\/ci300513m","volume":"53","author":"M Awale","year":"2013","unstructured":"Awale M, van Deursen R, Reymond J-L (2013) MQN-Mapplet: visualization of chemical space with interactive maps of DrugBank, ChEMBL, PubChem, GDB-11, and GDB-13. J Chem Inf Model 53:509\u2013518","journal-title":"J Chem Inf Model"},{"key":"416_CR21","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1021\/acs.jcim.5b00182","volume":"55","author":"M Awale","year":"2015","unstructured":"Awale M, Reymond J-L (2015) Similarity Mapplet: interactive visualization of the directory of useful decoys and ChEMBL in high dimensional chemical spaces. J Chem Inf Model 55:1509\u20131516","journal-title":"J Chem Inf Model"},{"key":"416_CR22","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1186\/s12859-015-0776-9","volume":"16","author":"X Jin","year":"2015","unstructured":"Jin X et al (2015) PDB-explorer: a web-based interactive map of the protein data bank in shape space. BMC Bioinform 16:339","journal-title":"BMC Bioinform"},{"key":"416_CR23","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/s13321-016-0138-2","volume":"8","author":"M Awale","year":"2016","unstructured":"Awale M, Reymond J-L (2016) Web-based 3D-visualization of the DrugBank chemical space. J. Cheminform 8:25","journal-title":"J. Cheminform"},{"key":"416_CR24","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1021\/acs.jcim.6b00690","volume":"57","author":"M Awale","year":"2017","unstructured":"Awale M, Probst D, Reymond J-L (2017) WebMolCS: a web-based interface for visualizing molecules in three-dimensional chemical spaces. J Chem Inf Model 57:643\u2013649","journal-title":"J Chem Inf Model"},{"key":"416_CR25","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1093\/bioinformatics\/btx760","volume":"34","author":"D Probst","year":"2018","unstructured":"Probst D, Reymond J-L (2018) FUn: a framework for interactive visualizations of large, high-dimensional datasets on the web. Bioinformatics 34:1433\u20131435","journal-title":"Bioinformatics"},{"key":"416_CR26","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J (2018) UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426 [cs, stat]","DOI":"10.21105\/joss.00861"},{"key":"416_CR27","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"416_CR28","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504\u2013507","journal-title":"Science"},{"key":"416_CR29","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/089976698300017953","volume":"10","author":"CM Bishop","year":"1998","unstructured":"Bishop CM, Svens\u00e9n M, Williams CKIGTM (1998) The generative topographic mapping. Neural Comput 10:215\u2013234","journal-title":"Neural Comput"},{"key":"416_CR30","unstructured":"Kohonen T (1997) Exploration of very large databases by self-organizing maps. In: Proceedings of international conference on neural networks (ICNN\u201997) vol. 1 PL1-PL6 vol.1"},{"key":"416_CR31","doi-asserted-by":"publisher","unstructured":"Dong W, Moses C, Li K (2011) Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proceedings of the 20th international conference on World wide web\u2014WWW\u201911 577, ACM Press. https:\/\/doi.org\/10.1145\/1963405.1963487","DOI":"10.1145\/1963405.1963487"},{"key":"416_CR32","first-page":"406","volume":"4","author":"N Saitou","year":"1987","unstructured":"Saitou N, Nei M (1987) The neighbor-joining method: a new method for reconstructing phylogenetic trees. Mol Biol Evol 4:406\u2013425","journal-title":"Mol Biol Evol"},{"key":"416_CR33","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1101\/gr.232397.117","volume":"28","author":"Z Zhou","year":"2018","unstructured":"Zhou Z et al (2018) GrapeTree: visualization of core genomic relationships among 100,000 bacterial pathogens. Genome Res 28:1395\u20131404","journal-title":"Genome Res"},{"key":"416_CR34","doi-asserted-by":"crossref","first-page":"3584","DOI":"10.1093\/bioinformatics\/btw523","volume":"32","author":"J Lu","year":"2016","unstructured":"Lu J, Carlson HA (2016) ChemTreeMap: an interactive map of biochemical similarity in molecular datasets. Bioinformatics 32:3584\u20133592","journal-title":"Bioinformatics"},{"key":"416_CR35","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s12859-019-2610-2","volume":"20","author":"C P\u2019ng","year":"2019","unstructured":"P\u2019ng C et al (2019) BPG: seamless, automated and interactive visualization of scientific data. BMC Bioinform. 20:42","journal-title":"BMC Bioinform."},{"key":"416_CR36","doi-asserted-by":"publisher","unstructured":"Idreos S, Papaemmanouil O, Chaudhuri S (2015) Overview of data exploration techniques. In: Proceedings of the 2015 ACM SIGMOD international conference on management of data. ACM, pp 277\u2013281. https:\/\/doi.org\/10.1145\/2723372.2731084","DOI":"10.1145\/2723372.2731084"},{"key":"416_CR37","doi-asserted-by":"publisher","unstructured":"Andoni A, Razenshteyn I, Nosatzki NS (2017) LSH Forest: practical algorithms made theoretical. In: Proceedings of the twenty-eighth annual ACM-SIAM symposium on discrete algorithms. Society for Industrial and Applied Mathematics, pp 67\u201378 https:\/\/doi.org\/10.1137\/1.9781611974782.5","DOI":"10.1137\/1.9781611974782.5"},{"key":"416_CR38","doi-asserted-by":"publisher","unstructured":"Bawa M, Condie T, Ganesan P (2005) LSH forest: self-tuning indexes for similarity search. In: Proceedings of the 14th international conference on World Wide Web\u2014WWW\u201905 651. ACM Press. https:\/\/doi.org\/10.1145\/1060745.1060840","DOI":"10.1145\/1060745.1060840"},{"key":"416_CR39","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1090\/S0002-9939-1956-0078686-7","volume":"7","author":"JB Kruskal","year":"1956","unstructured":"Kruskal JB (1956) On the shortest spanning subtree of a graph and the traveling salesman problem. Proc Am Math Soc 7:48\u201348","journal-title":"Proc Am Math Soc"},{"key":"416_CR40","first-page":"543","volume":"2011","author":"M Chimani","year":"2013","unstructured":"Chimani M et al (2013) The open graph drawing framework (OGDF). Handbook Graph Draw Vis 2011:543\u2013569","journal-title":"Handbook Graph Draw Vis"},{"key":"416_CR41","doi-asserted-by":"publisher","unstructured":"Broder AZ ((1997) On the resemblance and containment of documents. In: Proceedings. Compression and Complexity of SEQUENCES 1997 (Cat. No. 97TB100171) 21\u201329. https:\/\/doi.org\/10.1109\/sequen.1997.666900","DOI":"10.1109\/sequen.1997.666900"},{"key":"416_CR42","unstructured":"Manber U (1994) Finding similar files in a large file system. In: Usenix Winter 1994 technical conference 1\u201310"},{"key":"416_CR43","unstructured":"Wu W, Li B, Chen L, Zhang C, Yu P (2017). Improved consistent weighted sampling revisited. arXiv:1706.01172 [cs]"},{"key":"416_CR44","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-015-0069-3","volume":"7","author":"D Bajusz","year":"2015","unstructured":"Bajusz D, R\u00e1cz A, H\u00e9berger K (2015) Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J Cheminform 7:20","journal-title":"J Cheminform"},{"key":"416_CR45","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s13321-018-0321-8","volume":"10","author":"D Probst","year":"2018","unstructured":"Probst D, Reymond J-L (2018) A probabilistic molecular fingerprint for big data settings. J Cheminform 10:66","journal-title":"J Cheminform"},{"key":"416_CR46","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50:742\u2013754","journal-title":"J Chem Inf Model"},{"key":"416_CR47","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/1758-2946-5-26","volume":"5","author":"S Riniker","year":"2013","unstructured":"Riniker S, Landrum GA (2013) Open-source platform to benchmark fingerprints for ligand-based virtual screening. J Cheminform. 5:26","journal-title":"J Cheminform."},{"key":"416_CR48","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1021\/acs.jcim.8b00524","volume":"59","author":"M Awale","year":"2019","unstructured":"Awale M, Reymond J-L (2019) Polypharmacology Browser PPB2: target prediction combining nearest neighbors with machine learning. J Chem Inf Model 59:10\u201317","journal-title":"J Chem Inf Model"},{"key":"416_CR49","doi-asserted-by":"publisher","unstructured":"Binding DB (2014) BindingDB Entry 6310: Compounds and compositions as Syk kinase inhibitors. https:\/\/doi.org\/10.7270\/q24q7sns","DOI":"10.7270\/q24q7sns"},{"key":"416_CR50","unstructured":"Wang J, Shen HT, Song J, Ji J (2014) Hashing for similarity search: a survey. arXiv:1408.2927[cs]"},{"key":"416_CR51","doi-asserted-by":"publisher","unstructured":"Marcais G, DeBlasio D, Pandey P, Kingsford C (2019) Locality sensitive hashing for the edit distance. http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/534446 https:\/\/doi.org\/10.1101\/534446","DOI":"10.1101\/534446"},{"key":"416_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/acs.jcim.7b00425","volume":"58","author":"D Probst","year":"2018","unstructured":"Probst D, Reymond J-L (2018) SmilesDrawer: parsing and drawing SMILES-encoded molecular structures using client-side JavaScript. J Chem Inf Model 58:1\u20137","journal-title":"J Chem Inf Model"},{"key":"416_CR53","doi-asserted-by":"publisher","first-page":"084111","DOI":"10.1063\/1.4928757","volume":"143","author":"R Ramakrishnan","year":"2015","unstructured":"Ramakrishnan R, Hartmann M, Tapavicza E, von Lilienfeld OA (2015) Electronic spectra from TDDFT and machine learning in chemical space. J Chem Phys 143:084111","journal-title":"J Chem Phys"},{"key":"416_CR54","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","volume":"28","author":"HM Berman","year":"2000","unstructured":"Berman HM et al (2000) The protein data bank. Nucleic Acids Res 28:235\u2013242","journal-title":"Nucleic Acids Res"},{"key":"416_CR55","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1021\/ci500232g","volume":"54","author":"M Awale","year":"2014","unstructured":"Awale M, Reymond J-L (2014) Atom pair 2D-fingerprints perceive 3D-molecular shape and pharmacophores for very fast virtual screening of ZINC and GDB-17. J Chem Inf Model 54:1892\u20131907","journal-title":"J Chem Inf Model"},{"key":"416_CR56","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","volume":"45","author":"The Cancer Genome Atlas Research Network","year":"2013","unstructured":"The Cancer Genome Atlas Research Network et al (2013) The Cancer Genome Atlas Pan-Cancer analysis project. Nat Genet 45:1113\u20131120","journal-title":"Nat Genet"},{"key":"416_CR57","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1038\/s41587-019-0298-5","volume":"37","author":"G Kustatscher","year":"2019","unstructured":"Kustatscher G et al (2019) Co-regulation map of the human proteome enables identification of protein functions. Nat Biotechnol 37:1361\u20131371","journal-title":"Nat Biotechnol"},{"key":"416_CR58","doi-asserted-by":"publisher","first-page":"e57002","DOI":"10.1371\/journal.pone.0057002","volume":"8","author":"MB Hanley","year":"2013","unstructured":"Hanley MB, Lomas W, Mittar D, Maino V, Park E (2013) Detection of low abundance RNA molecules in individual cells by flow cytometry. PLoS ONE 8:e57002","journal-title":"PLoS ONE"},{"key":"416_CR59","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.nima.2004.12.018","volume":"543","author":"BP Roe","year":"2005","unstructured":"Roe BP et al (2005) Boosted decision trees as an alternative to artificial neural networks for particle identification. Nucl Instrum Methods Phys Res 543:577\u2013584","journal-title":"Nucl Instrum Methods Phys Res"},{"key":"416_CR60","unstructured":"Bernhardsson E. Annoy (Approximate Nearest Neighbors Oh Yeah). https:\/\/github.com\/spotify\/annoy"},{"key":"416_CR61","doi-asserted-by":"crossref","unstructured":"Lahiri S (2013) Complexity of word collocation networks: a preliminary structural analysis. arXiv:1310.5111[physics]","DOI":"10.3115\/v1\/E14-3011"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-0416-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-020-0416-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-0416-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T15:39:23Z","timestamp":1695742763000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-020-0416-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,12]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["416"],"URL":"https:\/\/doi.org\/10.1186\/s13321-020-0416-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.9698861.v1","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.9698861.v2","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,12]]},"assertion":[{"value":"9 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12"}}