{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:07:48Z","timestamp":1787317668123,"version":"build-2736575974"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Swiss National Science Foundation, NCCR TransCure"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1186\/s13321-018-0321-8","type":"journal-article","created":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T08:23:58Z","timestamp":1545121438000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":154,"title":["A probabilistic molecular fingerprint for big data settings"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-4407","authenticated-orcid":false,"given":"Daniel","family":"Probst","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Louis","family":"Reymond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,12,18]]},"reference":[{"key":"321_CR1","unstructured":"Grohe M, Rattan G, Woeginger GJ (2018) Graph similarity and approximate isomorphism. In: Graph similarity and approximate isomorphism. Schloss Dagstuhl\u2013Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, pp 20:1\u201320:16"},{"key":"321_CR2","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1021\/ci00054a008","volume":"27","author":"R Nilakantan","year":"1987","unstructured":"Nilakantan R, Bauman N, Dixon JS, Venkataraghavan R (1987) Topological torsion: a new molecular descriptor for SAR applications. Comparison with other descriptors. J Chem Inf Comput Sci 27:82\u201385. \n                    https:\/\/doi.org\/10.1021\/ci00054a008","journal-title":"J Chem Inf Comput Sci"},{"key":"321_CR3","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","volume":"5","author":"HL Morgan","year":"1965","unstructured":"Morgan HL (1965) The generation of a unique machine description for chemical structures\u2014a technique developed at chemical abstracts service. J Chem Doc 5:107\u2013113. \n                    https:\/\/doi.org\/10.1021\/c160017a018","journal-title":"J Chem Doc"},{"key":"321_CR4","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. \n                    https:\/\/doi.org\/10.1021\/ci500232g","journal-title":"J Chem Inf Model"},{"key":"321_CR5","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.endm.2010.05.087","volume":"36","author":"S Kpodjedo","year":"2010","unstructured":"Kpodjedo S, Galinier P, Antoniol G (2010) On the use of similarity metrics for approximate graph matching. Electron Notes Discrete Math 36:687\u2013694. \n                    https:\/\/doi.org\/10.1016\/j.endm.2010.05.087","journal-title":"Electron Notes Discrete Math"},{"key":"321_CR6","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. \n                    https:\/\/doi.org\/10.1021\/ci100050t","journal-title":"J Chem Inf Model"},{"key":"321_CR7","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. \n                    https:\/\/doi.org\/10.1186\/1758-2946-5-26","journal-title":"J Cheminform"},{"key":"321_CR8","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","volume":"45","author":"JJ Irwin","year":"2005","unstructured":"Irwin JJ, Shoichet BK (2005) ZINC\u2014a free database of commercially available compounds for virtual screening. J Chem Inf Model 45:177\u2013182","journal-title":"J Chem Inf Model"},{"key":"321_CR9","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. \n                    https:\/\/doi.org\/10.1021\/ci300415d","journal-title":"J Chem Inf Model"},{"key":"321_CR10","doi-asserted-by":"publisher","first-page":"W623","DOI":"10.1093\/nar\/gkp456","volume":"37","author":"Y Wang","year":"2009","unstructured":"Wang Y, Xiao J, Suzek TO et al (2009) PubChem: a public information system for analyzing bioactivities of small molecules. Nucl Acids Res 37:W623\u2013W633. \n                    https:\/\/doi.org\/10.1093\/nar\/gkp456","journal-title":"Nucl Acids Res"},{"key":"321_CR11","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1145\/361002.361007","volume":"18","author":"JL Bentley","year":"1975","unstructured":"Bentley JL (1975) Multidimensional binary search trees used for associative searching. Commun ACM 18:509\u2013517. \n                    https:\/\/doi.org\/10.1145\/361002.361007","journal-title":"Commun ACM"},{"key":"321_CR12","unstructured":"Weber R, Schek H-J, Blott S (1998) A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In: Proceedings of the 24th international conference on very large data bases. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp 194\u2013205"},{"key":"321_CR13","volume-title":"Five balltree construction algorithms","author":"SM Omohundro","year":"1989","unstructured":"Omohundro SM (1989) Five balltree construction algorithms. International Computer Science Institute, Berkeley"},{"key":"321_CR14","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1021\/ci600358f","volume":"47","author":"SJ Swamidass","year":"2007","unstructured":"Swamidass SJ, Baldi P (2007) Bounds and algorithms for fast exact searches of chemical fingerprints in linear and sublinear time. J Chem Inf Model 47:302\u2013317. \n                    https:\/\/doi.org\/10.1021\/ci600358f","journal-title":"J Chem Inf Model"},{"key":"321_CR15","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1021\/ci800076s","volume":"48","author":"P Baldi","year":"2008","unstructured":"Baldi P, Hirschberg DS, Nasr RJ (2008) Speeding up chemical database searches using a proximity filter based on the logical exclusive OR. J Chem Inf Model 48:1367\u20131378. \n                    https:\/\/doi.org\/10.1021\/ci800076s","journal-title":"J Chem Inf Model"},{"key":"321_CR16","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1021\/ci400206h","volume":"53","author":"J Schwartz","year":"2013","unstructured":"Schwartz J, Awale M, Reymond J-L (2013) SMIfp (SMILES fingerprint) chemical space for virtual screening and visualization of large databases of organic molecules. J Chem Inf Model 53:1979\u20131989. \n                    https:\/\/doi.org\/10.1021\/ci400206h","journal-title":"J Chem Inf Model"},{"key":"321_CR17","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. \n                    https:\/\/doi.org\/10.1021\/ci300513m","journal-title":"J Chem Inf Model"},{"key":"321_CR18","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1002\/cmdc.200900317","volume":"4","author":"KT Nguyen","year":"2009","unstructured":"Nguyen KT, Blum LC, van Deursen R, Reymond J-L (2009) Classification of organic molecules by molecular quantum numbers. ChemMedChem 4:1803\u20131805. \n                    https:\/\/doi.org\/10.1002\/cmdc.200900317","journal-title":"ChemMedChem"},{"key":"321_CR19","doi-asserted-by":"crossref","unstructured":"Broder AZ (1998) On the resemblance and containment of documents. In: Proceedings of compression and complexity of SEQUENCES 1997 (Cat. No. 97TB100171). IEEE Computing Society Salerno, Italy, pp 21\u201329","DOI":"10.1109\/SEQUEN.1997.666900"},{"key":"321_CR20","unstructured":"Manber U (1994) Finding similar files in a large file system. In: Usenix Winter 1994 technical conference, pp 1\u201310"},{"key":"321_CR21","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M Damashek","year":"1995","unstructured":"Damashek M (1995) Gauging similarity with n-grams: language-independent categorization of text. Science 267:843\u2013848. \n                    https:\/\/doi.org\/10.1126\/science.267.5199.843","journal-title":"Science"},{"key":"321_CR22","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin S, Page L (1998) The anatomy of a large-scale hypertextual web search engine. Comput Netw ISDN Syst 30:107\u2013117. \n                    https:\/\/doi.org\/10.1016\/S0169-7552(98)00110-X","journal-title":"Comput Netw ISDN Syst"},{"key":"321_CR23","unstructured":"Hu S (2005) Efficient video retrieval by locality sensitive hashing. In: Proceedings (ICASSP\u201905) of IEEE international conference on acoustics, speech, and signal processing, vol 2, pp ii\/449\u2013ii\/452"},{"key":"321_CR24","doi-asserted-by":"crossref","unstructured":"Indyk P, Motwani R (1998) Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the thirtieth annual ACM symposium on theory of computing. ACM, New York, pp 604\u2013613","DOI":"10.1145\/276698.276876"},{"key":"321_CR25","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. \n                    https:\/\/doi.org\/10.1186\/s13321-015-0069-3","journal-title":"J Cheminform"},{"key":"321_CR26","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1093\/bioinformatics\/btq067","volume":"26","author":"Y Cao","year":"2010","unstructured":"Cao Y, Jiang T, Girke T (2010) Accelerated similarity searching and clustering of large compound sets by geometric embedding and locality sensitive hashing. Bioinformatics 26:953\u2013959. \n                    https:\/\/doi.org\/10.1093\/bioinformatics\/btq067","journal-title":"Bioinformatics"},{"key":"321_CR27","unstructured":"Landrum G (2018) RDKit: Open-source cheminformatics. \n                    http:\/\/www.rdkit.org\n                    \n                  . Accessed 31 Aug 2018"},{"key":"321_CR28","unstructured":"ChemAxon Ltd (2018) ChemAxon JChem. \n                    http:\/\/www.chemaxon.com\n                    \n                  . Accessed 31 Aug 2018"},{"key":"321_CR29","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","volume":"3","author":"NM O\u2019Boyle","year":"2011","unstructured":"O\u2019Boyle NM, Banck M, James CA et al (2011) Open babel: an open chemical toolbox. J Cheminform 3:33. \n                    https:\/\/doi.org\/10.1186\/1758-2946-3-33","journal-title":"J Cheminform"},{"key":"321_CR30","unstructured":"Kosub S (2016) A note on the triangle inequality for the Jaccard distance. \n                    arXiv:161202696\n                    \n                   [cs, stat]"},{"key":"321_CR31","doi-asserted-by":"crossref","unstructured":"Broder AZ, Charikar M, Frieze AM, Mitzenmacher M (1998) Min-wise independent permutations (extended abstract). In: Proceedings of the thirtieth annual ACM symposium on theory of computing. ACM, New York, pp 327\u2013336","DOI":"10.1145\/276698.276781"},{"key":"321_CR32","doi-asserted-by":"crossref","unstructured":"Christiani T, Pagh R (2016) Set similarity search beyond MinHash. \n                    arXiv:161207710\n                    \n                   [cs]","DOI":"10.1145\/3055399.3055443"},{"key":"321_CR33","doi-asserted-by":"crossref","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. ACM Press, Chiba, p 651","DOI":"10.1145\/1060745.1060840"},{"key":"321_CR34","unstructured":"Atkinson MP, International Conference on Very Large Databases (1999) Very large data bases. In: Proceedings of the twenty-fifth international conference on very large data bases, Edinburgh, Scotland, 7\u201310th September 1999. Morgan Kaufmann, Orlando"},{"key":"321_CR35","doi-asserted-by":"publisher","first-page":"385","DOI":"10.2307\/2315408","volume":"73","author":"EH Mckinney","year":"1966","unstructured":"Mckinney EH (1966) Generalized birthday problem. Am Math Mon 73:385. \n                    https:\/\/doi.org\/10.2307\/2315408","journal-title":"Am Math Mon"},{"key":"321_CR36","unstructured":"Bernhardsson E (2018) Annoy (Approximate Nearest Neighbors Oh Yeah). \n                    https:\/\/github.com\/spotify\/annoy\n                    \n                  . Accessed 16 Nov 2018"},{"key":"321_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCSE.2011.37","volume":"13","author":"S Walt Van Der","year":"2011","unstructured":"Van Der Walt S, Colbert SC, Varoquaux G (2011) The NumPy array: a structure for efficient numerical computation. Comput Sci Eng 13:22\u201330. \n                    https:\/\/doi.org\/10.1109\/MCSE.2011.37","journal-title":"Comput Sci Eng"},{"key":"321_CR38","unstructured":"Zhu E, Markovtsev V (2017) Datasketch: big data looks small. \n                    https:\/\/www.zenodo.org\/record\/290602\n                    \n                  . Accessed 22 Sept 2018"},{"key":"321_CR39","doi-asserted-by":"crossref","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","DOI":"10.1137\/1.9781611974782.5"},{"key":"321_CR40","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. Nucl Acids Res 45:D945\u2013D954. \n                    https:\/\/doi.org\/10.1093\/nar\/gkw1074","journal-title":"Nucl Acids Res"},{"key":"321_CR41","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1021\/ci700353m","volume":"48","author":"RW Benz","year":"2008","unstructured":"Benz RW, Swamidass SJ, Baldi P (2008) Discovery of power-laws in chemical space. J Chem Inf Model 48:1138\u20131151. \n                    https:\/\/doi.org\/10.1021\/ci700353m","journal-title":"J Chem Inf Model"},{"key":"321_CR42","doi-asserted-by":"publisher","first-page":"6789","DOI":"10.1021\/jm0608356","volume":"49","author":"N Huang","year":"2006","unstructured":"Huang N, Shoichet BK, Irwin JJ (2006) Benchmarking sets for molecular docking. J Med Chem 49:6789\u20136801. \n                    https:\/\/doi.org\/10.1021\/jm0608356","journal-title":"J Med Chem"},{"key":"321_CR43","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1021\/ci8002649","volume":"49","author":"SG Rohrer","year":"2009","unstructured":"Rohrer SG, Baumann K (2009) Maximum unbiased validation (MUV) data sets for virtual screening based on PubChem bioactivity data. J Chem Inf Model 49:169\u2013184. \n                    https:\/\/doi.org\/10.1021\/ci8002649","journal-title":"J Chem Inf Model"},{"key":"321_CR44","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","volume":"131","author":"LC Blum","year":"2009","unstructured":"Blum LC, Reymond J-L (2009) 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. J Am Chem Soc 131:8732\u20138733. \n                    https:\/\/doi.org\/10.1021\/ja902302h","journal-title":"J Am Chem Soc"},{"key":"321_CR45","doi-asserted-by":"publisher","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","volume":"46","author":"DS Wishart","year":"2018","unstructured":"Wishart DS, Feunang YD, Guo AC et al (2018) DrugBank 5.0: a major update to the DrugBank database for 2018. Nucl Acids Res 46:D1074\u2013D1082. \n                    https:\/\/doi.org\/10.1093\/nar\/gkx1037","journal-title":"Nucl Acids Res"},{"key":"321_CR46","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.3-36.v2","author":"Y Hu","year":"2014","unstructured":"Hu Y, de la Vega de Le\u00f3n A, Zhang B, Bajorath J (2014) Matched molecular pair-based data sets for computer-aided medicinal chemistry. F1000Research. \n                    https:\/\/doi.org\/10.12688\/f1000research.3-36.v2","journal-title":"F1000Research"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-018-0321-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-018-0321-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-018-0321-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T19:05:00Z","timestamp":1576609500000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-018-0321-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["321"],"URL":"https:\/\/doi.org\/10.1186\/s13321-018-0321-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.7176350.v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]},"assertion":[{"value":"6 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"66"}}