{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:35:30Z","timestamp":1778614530839,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,10,31]],"date-time":"2016-10-31T00:00:00Z","timestamp":1477872000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13321-016-0173-z","type":"journal-article","created":{"date-parts":[[2016,10,31]],"date-time":"2016-10-31T14:39:48Z","timestamp":1477924788000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Filtered circular fingerprints improve either prediction or runtime performance while retaining interpretability"],"prefix":"10.1186","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2939-2469","authenticated-orcid":false,"given":"Martin","family":"G\u00fctlein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Kramer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,31]]},"reference":[{"key":"173_CR1","doi-asserted-by":"publisher","unstructured":"Eckert H, Bajorath J (2007) Molecular similarity analysis in virtual screening: foundations, limitations and novel approaches. Drug Discov Today 12(56):225\u2013233. doi: 10.1016\/j.drudis.2007.01.011 Accessed 30 Nov 2015","DOI":"10.1016\/j.drudis.2007.01.011"},{"key":"173_CR2","doi-asserted-by":"publisher","unstructured":"Cherkasov A, Muratov EN, Fourches D, Varnek A, Baskin II, Cronin M, Dearden J, Gramatica P, Martin YC, Todeschini R, Consonni V, Kuzmin VE, Cramer R, Benigni R, Yang C, Rathman J, Terfloth L, Gasteiger J, Richard A, Tropsha A (2013) QSAR modeling: where have you been? Where are you going to? J Med Chem. doi: 10.1021\/jm4004285 . Accessed 31 Jan 2014","DOI":"10.1021\/jm4004285"},{"key":"173_CR3","unstructured":"OECD: Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models. Organisation for Economic Co-operation and Development, Paris (2014) http:\/\/www.oecd-ilibrary.org\/content\/book\/9789264085442-en . Accessed 30 Nov 2015"},{"key":"173_CR4","doi-asserted-by":"publisher","unstructured":"Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742\u2013754. doi: 10.1021\/ci100050t . Accessed 11 Apr 2014","DOI":"10.1021\/ci100050t"},{"key":"173_CR5","doi-asserted-by":"publisher","unstructured":"Morgan HL (1965) The generation of a unique machine description for chemical structures-a technique developed at chemical abstracts service. J Chem Doc 5(2):107\u2013113. doi: 10.1021\/c160017a018 . Accessed 36 March 2014","DOI":"10.1021\/c160017a018"},{"key":"173_CR6","doi-asserted-by":"publisher","unstructured":"Riniker S, Fechner N, Landrum GA (2013) Heterogeneous classifier fusion for ligand-based virtual screening: or, how decision making by committee can be a good thing. J Chem Inf Model 53(11):2829\u20132836. doi: 10.1021\/ci400466r . Accessed 20 Feb 2014","DOI":"10.1021\/ci400466r"},{"key":"173_CR7","doi-asserted-by":"publisher","unstructured":"Ahmed A, Saeed F, Salim N, Abdo A (2014) Condorcet and borda count fusion method for ligand-based virtual screening. J Cheminform 6(1):19. doi: 10.1186\/1758-2946-6-19 . Accessed 04 May 2015","DOI":"10.1186\/1758-2946-6-19"},{"key":"173_CR8","doi-asserted-by":"publisher","unstructured":"Rosenbaum L, Hinselmann G, Jahn A, Zell A (2011) Interpreting linear support vector machine models with heat map molecule coloring. J Cheminform 3(1):11. doi: 10.1186\/1758-2946-3-11 . Accessed 30 Nov 2015","DOI":"10.1186\/1758-2946-3-11"},{"key":"173_CR9","doi-asserted-by":"publisher","unstructured":"Xuan S, Wang M, Kang H, Kirchmair J, Tan L, Yan A (2013) Support vector machine (SVM) models for predicting inhibitors of the 3 processing step of HIV-1 integrase. Mol Inform 32(9\u201310):811\u2013826. doi: 10.1002\/minf.201300107 . Accessed 28 Apr 2015","DOI":"10.1002\/minf.201300107"},{"key":"173_CR10","doi-asserted-by":"publisher","unstructured":"Alvarsson J, Eklund M, Engkvist O, Spjuth O, Carlsson L, Wikberg JES, Noeske T (2014) Ligand-based target prediction with signature fingerprints. J Chem Inf Model 54(10):2647\u20132653. doi: 10.1021\/ci500361u Accessed 05 May 2015","DOI":"10.1021\/ci500361u"},{"key":"173_CR11","doi-asserted-by":"publisher","unstructured":"Riniker S, Wang Y, Jenkins JL, Landrum GA (2014) Using information from historical high-throughput screens to predict active compounds. J Chem Inf Model 54(7):1880\u20131891. doi: 10.1021\/ci500190p . Accessed 04 May 2015","DOI":"10.1021\/ci500190p"},{"key":"173_CR12","doi-asserted-by":"publisher","unstructured":"Rogers D, Brown RD, Hahn M (2005) Using extended-connectivity fingerprints with laplacian-modified Bayesian analysis in high-throughput screening follow-up. J Biomol Screen 10(7):682\u2013686. doi: 10.1177\/1087057105281365 . Accessed 28 Apr 2015","DOI":"10.1177\/1087057105281365"},{"key":"173_CR13","doi-asserted-by":"publisher","unstructured":"Xia X, Maliski EG, Gallant P, Rogers D (2004) Classification of kinase inhibitors using a Bayesian model. J Med Chem 47(18):4463\u20134470. doi: 10.1021\/jm0303195 . Accessed 28 Apr 2015","DOI":"10.1021\/jm0303195"},{"key":"173_CR14","doi-asserted-by":"publisher","unstructured":"Liu R, Wallqvist A (2014) Merging applicability domains for in silico assessment of chemical mutagenicity. J Chem Inf Model 54(3):793\u2013800. doi: 10.1021\/ci500016v . Accessed 04 May 2015","DOI":"10.1021\/ci500016v"},{"key":"173_CR15","doi-asserted-by":"publisher","unstructured":"Hert J, Willett P, Wilton DJ, Acklin P, Azzaoui K, Jacoby E, Schuffenhauer A (2004) Comparison of topological descriptors for similarity-based virtual screening using multiple bioactive reference structures. Org Biomol Chem 2(22):3256\u20133266. doi: 10.1039\/B409865J . Accessed 30 Nov 2015","DOI":"10.1039\/B409865J"},{"key":"173_CR16","doi-asserted-by":"publisher","unstructured":"Riniker S, Landrum GA (2013) Open-source platform to benchmark fingerprints for ligand-based virtual screening. J Cheminform 5(1):26. doi: 10.1186\/1758-2946-5-26 . Accessed 04 May 2015","DOI":"10.1186\/1758-2946-5-26"},{"key":"173_CR17","doi-asserted-by":"publisher","unstructured":"Hu Y, Lounkine E, Bajorath J (2009) Improving the search performance of extended connectivity fingerprints through activity-oriented feature filtering and application of a bit-density-dependent similarity function. ChemMedChem 4(4):540\u2013548. doi: 10.1002\/cmdc.200800408 . Accessed 28 Apr 2015","DOI":"10.1002\/cmdc.200800408"},{"key":"173_CR18","volume-title":"Machine learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell TM (1997) Machine learning. McGraw-Hill, New York"},{"key":"173_CR19","doi-asserted-by":"publisher","unstructured":"Truchon J-F, Bayly CI (2007) Evaluating virtual screening methods: good and bad metrics for the early recognition problem. J Chem Inf Model 47(2):488\u2013508. doi: 10.1021\/ci600426e . Accessed 23 Feb 2016","DOI":"10.1021\/ci600426e"},{"issue":"1","key":"173_CR20","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/s13321-015-0100-8","volume":"7","author":"C Empereur-mot","year":"2015","unstructured":"Empereur-mot C, Guillemain H, Latouche A, Zagury J-F, Viallon V, Montes M (2015) Predictiveness curves in virtual screening. J Cheminform 7(1):52. doi: 10.1186\/s13321-015-0100-8 Accessed-2015-11-10","journal-title":"J Cheminform"},{"key":"173_CR21","doi-asserted-by":"publisher","unstructured":"Davis J, Goadrich M (2006) The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning. ICML \u201906. ACM, New York, NY, USA, pp. 233\u2013240. doi: 10.1145\/1143844.1143874 . Accessed 21 Oct 2015","DOI":"10.1145\/1143844.1143874"},{"key":"173_CR22","doi-asserted-by":"publisher","unstructured":"Bunescu R, Ge R, Kate RJ, Marcotte EM, Mooney RJ, Ramani AK, Wong YW (2005) Comparative experiments on learning information extractors for proteins and their interactions. Artif Intell Med 33(2):139\u2013155. doi: 10.1016\/j.artmed.2004.07.016 . Accessed 30 Nov 2015","DOI":"10.1016\/j.artmed.2004.07.016"},{"key":"173_CR23","first-page":"193","volume":"17","author":"J Bockhorst","year":"2005","unstructured":"Bockhorst J, Craven M (2005) Markov networks for detecting overlapping elements in sequence data. Adv Neural Inf Process Syst 17:193","journal-title":"Adv Neural Inf Process Syst"},{"key":"173_CR24","doi-asserted-by":"publisher","unstructured":"Nicholls A (2008) What do we know and when do we know it? J Comput Aided Mol Des 22(3\u20134):239\u2013255. doi: 10.1007\/s10822-008-9170-2 . Accessed 22 Sept 2016","DOI":"10.1007\/s10822-008-9170-2"},{"key":"173_CR25","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-642-40994-3_29","volume-title":"Machine learning and knowledge discovery in databases. Lecture notes in computer science","author":"K Boyd","year":"2013","unstructured":"Boyd K, Eng KH, Page CD (2013) Area under the precision-recall curve: point estimates and confidence intervals. In: Blockeel H, Kersting K, Nijssen S, elezn F (eds) Machine learning and knowledge discovery in databases. Lecture notes in computer science. Springer, Heidelberg, pp 451\u2013466. doi: 10.1007\/978-3-642-40994-3_29"},{"key":"173_CR26","doi-asserted-by":"publisher","unstructured":"G\u00fctlein M, Helma C, Karwath A, Kramer S (2013) A large-scale empirical evaluation of cross-validation and external test set validation in (Q)SAR. Mol Inf 32(5\u20136):516\u2013528. doi: 10.1002\/minf.201200134 . Accessed 08 Jan 2014","DOI":"10.1002\/minf.201200134"},{"key":"173_CR27","doi-asserted-by":"publisher","unstructured":"Baumann D, Baumann K (2014) Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation. J Cheminform 6(1):47. doi: 10.1186\/s13321-014-0047-1 . Accessed 17 July 2015","DOI":"10.1186\/s13321-014-0047-1"},{"key":"173_CR28","doi-asserted-by":"publisher","unstructured":"Helma C (2006) Lazy structure-activity relationships (lazar) for the prediction of rodent carcinogenicity and Salmonella mutagenicity. Mol Diversity 10(2):147\u2013158. doi: 10.1007\/s11030-005-9001-5 . Accessed 30 July 2014","DOI":"10.1007\/s11030-005-9001-5"},{"key":"173_CR29","doi-asserted-by":"publisher","unstructured":"Fjodorova N, Vrako M, Novi M, Roncaglioni A, Benfenati E (2010) New public QSAR model for carcinogenicity. Chem Cent J 4(Suppl 1):3. doi: 10.1186\/1752-153X-4-S1-S3 . Accessed 19 Jan 2016","DOI":"10.1186\/1752-153X-4-S1-S3"},{"issue":"6","key":"173_CR30","doi-asserted-by":"publisher","first-page":"2432","DOI":"10.1021\/ci060159g","volume":"46","author":"A Karwath","year":"2006","unstructured":"Karwath A, De Raedt L (2006) SMIREP: predicting chemical activity from SMILES. J Chem Inf Model 46(6):2432\u20132444. doi: 10.1021\/ci060159g","journal-title":"J Chem Inf Model"},{"key":"173_CR31","doi-asserted-by":"publisher","unstructured":"Cao D-S, Yang Y-N, Zhao J-C, Yan J, Liu S, Hu Q-N, Xu Q-S, Liang Y-Z (2012) Computer-aided prediction of toxicity with substructure pattern and random forest. J Chemom 26(1\u20132):7\u201315. doi: 10.1002\/cem.1416 . Accessed 03 March 2016","DOI":"10.1002\/cem.1416"},{"issue":"5","key":"173_CR32","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1177\/026119290503300508","volume":"33","author":"J Jaworska","year":"2005","unstructured":"Jaworska J, Nikolova-Jeliazkova N (2005) QSAR applicabilty domain estimation by projection of the training set descriptor space: a review. Altern Lab Anim 33(5):445\u2013459","journal-title":"Altern Lab Anim"},{"issue":"3","key":"173_CR33","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1021\/tx000208y","volume":"14","author":"H Fang","year":"2001","unstructured":"Fang H, Tong W, Shi LM, Blair R, Perkins R, Branham W, Hass BS, Xie Q, Dial SL, Moland CL, Sheehan DM (2001) Structure-activity relationships for a large diverse set of natural, synthetic, and environmental estrogens. Chem Res Toxicol 14(3):280\u2013294","journal-title":"Chem Res Toxicol"},{"key":"173_CR34","doi-asserted-by":"publisher","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor Newsl 11(1):10\u201318. doi: 10.1145\/1656274.1656278 . Accessed 02 Dec 2015","DOI":"10.1145\/1656274.1656278"},{"key":"173_CR35","doi-asserted-by":"publisher","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332. doi: 10.1023\/A:1010933404324 . Accessed 08 Jan 2014","DOI":"10.1023\/A:1010933404324"},{"key":"173_CR36","unstructured":"John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the 11th conference on uncertainty in artificial intelligence. UAI\u201995. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp. 338\u2013345. http:\/\/dl.acm.org\/citation.cfm?id=2074158.2074196 . Accessed 08 May 2014"},{"key":"173_CR37","doi-asserted-by":"crossref","unstructured":"Platt J et al (1999) Fast training of support vector machines using sequential minimal optimization. Advances in kernel methodssupport vector learning 3","DOI":"10.7551\/mitpress\/1130.003.0016"},{"key":"173_CR38","doi-asserted-by":"publisher","unstructured":"Nadeau C, Bengio Y (2003) Inference for the generalization error. Mach Learn 52(3):239\u2013281. doi: 10.1023\/A:1024068626366 . Accessed 15 Apr 2015","DOI":"10.1023\/A:1024068626366"},{"key":"173_CR39","doi-asserted-by":"publisher","unstructured":"Steinbeck C, Han Y, Kuhn S, Horlacher O, Luttmann E, Willighagen E (2003) The chemistry development kit (CDK): an open-source Java library for chemo- and bioinformatics. J Chem Inf Comput Sci 43(2):493\u2013500. doi: 10.1021\/ci025584y . Accessed 17 Jan 2014","DOI":"10.1021\/ci025584y"},{"key":"173_CR40","doi-asserted-by":"publisher","unstructured":"Hardy B, Douglas N, Helma C, Rautenberg M, Jeliazkova N, Jeliazkov V, Nikolova I, Benigni R, Tcheremenskaia O, Kramer S, Girschick T, Buchwald F, Wicker J, Karwath A, G\u00fctlein M, Maunz A, Sarimveis H, Melagraki G, Afantitis A, Sopasakis P, Gallagher D, Poroikov V, Filimonov D, Zakharov A, Lagunin A, Gloriozova T, Novikov S, Skvortsova N, Druzhilovsky D, Chawla S, Ghosh I, Ray S, Patel H, Escher S (2010) Collaborative development of predictive toxicology applications. J Cheminform 2(1):7. doi: 10.1186\/1758-2946-2-7 . Accessed 08 Jan 2014","DOI":"10.1186\/1758-2946-2-7"},{"key":"173_CR41","doi-asserted-by":"publisher","unstructured":"G\u00fctlein M, Karwath A, Kramer S (2012) CheS-Mapper\u2014chemical space mapping and visualization in 3d. J Cheminform 4(1):7. doi: 10.1186\/1758-2946-4-7 . Accessed 08 Jan 2014","DOI":"10.1186\/1758-2946-4-7"},{"key":"173_CR42","doi-asserted-by":"publisher","unstructured":"Yan X, Han J (2003) CloseGraph: mining closed frequent graph patterns. In: Proceedings of the 9th ACM SIGKDD international conference on knowledge discovery and data mining. KDD \u201903. ACM, New York, NY, USA, pp 286\u2013295. doi: 10.1145\/956750.956784 . Accessed 27 Nov 2015","DOI":"10.1145\/956750.956784"},{"key":"173_CR43","doi-asserted-by":"publisher","unstructured":"Maunz A, Helma C, Kramer S (2009) Large-scale graph mining using backbone refinement classes. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining. KDD \u201909. ACM, New York, NY, USA, pp. 617\u2013626. doi: 10.1145\/1557019.1557089 . Accessed 30 Apr 2014","DOI":"10.1145\/1557019.1557089"},{"key":"173_CR44","doi-asserted-by":"publisher","unstructured":"Ahlberg E, Spjuth O, Hasselgren C, Carlsson L (2015) Interpretation of conformal prediction classification models. In: Gammerman A, Vovk V, Papadopoulos H (eds) Statistical learning and data sciences. Lecture notes in computer science. Springer, Heidelberg, pp. 323\u2013334. doi: 10.1007\/978-3-319-17091-6_27","DOI":"10.1007\/978-3-319-17091-6_27"},{"key":"173_CR45","doi-asserted-by":"publisher","unstructured":"O\u2019Boyle NM, Banck M, James CA, Morley C, Vandermeersch T, Hutchison GR (2011) Open babel: an open chemical toolbox. J Cheminform 3(1):33. doi: 10.1186\/1758-2946-3-33 . Accessed 18 Jan 2014","DOI":"10.1186\/1758-2946-3-33"},{"issue":"5","key":"173_CR46","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1021\/ci0498719","volume":"44","author":"A Bender","year":"2004","unstructured":"Bender A, Mussa HY, Glen RC, Reiling S (2004) Similarity searching of chemical databases using atom environment descriptors (MOLPRINT 2d): evaluation of performance. J Chem Inf Comput Sci 44(5):1708\u20131718. doi: 10.1021\/ci0498719","journal-title":"J Chem Inf Comput Sci"},{"key":"173_CR47","doi-asserted-by":"publisher","unstructured":"Kazius J, McGuire R, Bursi R (2005) Derivation and validation of toxicophores for mutagenicity prediction. J Med Chem 48(1):312\u2013320. doi: 10.1021\/jm040835a . Accessed 14 Apr 2015","DOI":"10.1021\/jm040835a"},{"key":"173_CR48","unstructured":"Gold LS, Manley NB, Slone TH, Rohrbach L (1999) Supplement to the carcinogenic potency database (CPDB): results of animal bioassays published in the general literature in 1993 to 1994 and by the National Toxicology Program in 1995 to 1996. Environ Health Perspect 107(Suppl 4):527\u2013600. Accessed 08 Jan 2014"},{"key":"173_CR49","doi-asserted-by":"publisher","unstructured":"Heikamp K, Bajorath J (2011) Large-scale similarity search profiling of ChEMBL compound data sets. J Chem Inf Model 51(8):1831\u20131839. doi: 10.1021\/ci200199u . Accessed 12 Jan 2016","DOI":"10.1021\/ci200199u"},{"key":"173_CR50","doi-asserted-by":"publisher","unstructured":"Huang N, Shoichet BK, Irwin JJ (2006) Benchmarking sets for molecular docking. J Med Chem 49(23):6789\u20136801. doi: 10.1021\/jm0608356 Accessed 12 Jan 2016","DOI":"10.1021\/jm0608356"},{"key":"173_CR51","doi-asserted-by":"publisher","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(2):169\u2013184. doi: 10.1021\/ci8002649 . Accessed 12 Jan 2016","DOI":"10.1021\/ci8002649"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-016-0173-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-016-0173-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-016-0173-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T17:55:14Z","timestamp":1692554114000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-016-0173-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,31]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["173"],"URL":"https:\/\/doi.org\/10.1186\/s13321-016-0173-z","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,31]]},"assertion":[{"value":"19 May 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"60"}}