{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T19:36:53Z","timestamp":1760297813894},"reference-count":47,"publisher":"American Chemical Society (ACS)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2007,7,1]]},"DOI":"10.1021\/ci600552n","type":"journal-article","created":{"date-parts":[[2007,6,7]],"date-time":"2007-06-07T12:01:00Z","timestamp":1181217660000},"page":"1328-1340","source":"Crossref","is-referenced-by-count":12,"title":["Molecular Basis SetsA General Similarity-Based Approach for Representing Chemical Spaces"],"prefix":"10.1021","volume":"47","author":[{"given":"Akshay S.","family":"Raghavendra","sequence":"first","affiliation":[{"name":"Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721"}]},{"given":"Gerald M.","family":"Maggiora","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, BIO5 Institute, and College of Pharmacy, University of Arizona, Tucson, Arizona 85721"}]}],"member":"316","published-online":{"date-parts":[[2007,6,7]]},"reference":[{"key":"ci600552nb00001\/ci600552nb00001_1","volume-title":"Large Compound Databases for Structure\u2212Activity Relationships Studies in Drug Discovery. Mini-Rev. Med. Chem","author":"Scior T."},{"key":"ci600552nb00002\/ci600552nb00002_1","first-page":"50","volume-title":"Cheminformatics:\u2009 Concepts, Methods, and Tools for Drug Discovery","author":"Maggiora G. M.","year":"2004"},{"key":"ci600552nb00003\/ci600552nb00003_1","volume-title":"Linear Algebra for Quantum Theory","author":"L\u00f6wdin P. O.","year":"1998"},{"key":"ci600552nb00004\/ci600552nb00004_1","first-page":"126","volume":"23","author":"L\u00f6wdin P. O","year":"1992","journal-title":"Adv. Quantum Chem."},{"key":"ci600552nb00005\/ci600552nb00005_1","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1103\/PhysRev.105.102","volume":"105","author":"Carlson B. C.","year":"1957","journal-title":"Phys. Rev."},{"key":"ci600552nb00006\/ci600552nb00006_1","unstructured":"In kernel-based machine-learning applications, this matrix is usually called the Gram matrix.7-9"},{"key":"ci600552nb00007\/ci600552nb00007_1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809682","volume-title":"Kernel Methods for Pattern Analysis","author":"Shawn-Taylor J.","year":"2004"},{"key":"ci600552nb00008\/ci600552nb00008_1","volume-title":"Learning Kernel Classifiers","author":"Herbrich R.","year":"2002"},{"key":"ci600552nb00009\/ci600552nb00009_1","volume-title":"Learning with Kernels","author":"Sch\u00f6lkopf B.","year":"2002"},{"key":"ci600552nb00010\/ci600552nb00010_1","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1021\/ci9800211","volume":"38","author":"Willett P.","year":"1998","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ci600552nb00011\/ci600552nb00011_1","volume-title":"http:\/\/www.mdli.com (accessed","author":"Structural Keys MDL","year":"2007"},{"key":"ci600552nb00012\/ci600552nb00012_1","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1021\/ci00057a006","volume":"28","author":"Weininger D. SMILES","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ci600552nb00013\/ci600552nb00013_1","volume-title":"An Introduction to Chemoinformatics","author":"Leach A. R.","year":"2003"},{"key":"ci600552nb00014\/ci600552nb00014_1","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1002\/(SICI)1096-987X(199705)18:7<934::AID-JCC6>3.0.CO;2-S","volume":"18","author":"Mestres J.","year":"1997","journal-title":"J. Comput. Chem."},{"key":"ci600552nb00015\/ci600552nb00015_1","doi-asserted-by":"crossref","first-page":"4520","DOI":"10.1021\/jm981037l","volume":"41","author":"Lemmen C.","year":"1998","journal-title":"J. Med. Chem."},{"key":"ci600552nb00016\/ci600552nb00016_1","volume-title":"http:\/\/www.eyesopen.com (accessed","author":"OpenEye Scientific Software","year":"2007"},{"key":"ci600552nb00017\/ci600552nb00017_1","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1023\/A:1008194019144","volume":"14","author":"Lemmen C.","year":"2000","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"ci600552nb00018\/ci600552nb00018_1","first-page":"338","volume":"9","author":"Good A. C.","year":"1998","journal-title":"Perspect. Drug Discovery"},{"key":"ci600552nb00019\/ci600552nb00019_1","volume-title":"L. W.","author":"This","year":"1982"},{"key":"ci600552nb00021\/ci600552nb00021_1","volume-title":"Principal Component Analysis","author":"Jolliffe I. T.","year":"2002","edition":"2"},{"key":"ci600552nb00022\/ci600552nb00022_1","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1093\/biomet\/53.3-4.325","volume":"53","author":"Gower J. C","year":"1966","journal-title":"Biometrika"},{"key":"ci600552nb00023\/ci600552nb00023_1","first-page":"793","volume":"16","author":"Klein C.","year":"2003","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"ci600552nb00024\/ci600552nb00024_1","first-page":"166","volume":"3","author":"Oprea T. I.","year":"2001","journal-title":"The Art of Navigating in Chemical Space."},{"key":"ci600552nb00026\/ci600552nb00026_1","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1021\/ci00002a018","volume":"31","author":"Randic M","year":"1991","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ci600552nb00028\/ci600552nb00028_1","volume-title":"http:\/\/dtp. nci. nih. gov\/docs\/aids\/aids_screen.html and http:\/\/dtp.nci.nih.gov\/docs\/aids\/aids_data.html (accessed","author":"National Institutes of Health. Screening Services.","year":"2007"},{"key":"ci600552nb00029\/ci600552nb00029_1","unstructured":"Also called the Gram matrix in the machine learning literature.7-9"},{"key":"ci600552nb00031\/ci600552nb00031_1","volume-title":"Linear Algebra and Its Applications","author":"Lay D. C.","year":"1997","edition":"2"},{"key":"ci600552nb00033\/ci600552nb00033_1","first-page":"270","volume":"31","year":"2002","journal-title":"J. Math. Chem."},{"key":"ci600552nb00036\/ci600552nb00036_1","first-page":"352","volume":"84","year":"1977","journal-title":"Features of Similarity. Pyschol. Rev."},{"key":"ci600552nb00038\/ci600552nb00038_1","unstructured":"In mathematics, a solid hypersphere embedded in a p-dimensional Euclidean space is also called a closed p-ball. The surface (boundary) of the solid hypersphere in that space is a p-dimensional hypersphere. Removal of the hypersphere that is removing the boundary of the p-dimensional solid hypersphere (closed p-ball) generates an open p-ball. For consistency, the terms solid hypersphere and hypersphere will be used in this work. For additional discussion on these points see the following:\u2009 Encyclopedic Dictionary of Mathematics; MIT Press:\u2009 Cambridge, MA, 1980; Vol. 1. Oden, J. T.; Demkowicz, L. F. Applied Functional Analysis. Chemical Rubber Publishing Company:\u2009 Boca Raton, FL, 1996. Lastly, the p-dimensional hypersphere can also be considered as a manifold in a (p-1)-dimensional subspace that is embedded within the p-dimensional Euclidean space, but this approach will not be exploited here. See, for example:\u2009 Small, C. G. The Statistical Theory of Shape; Springer:\u2009 New York, 1996."},{"key":"ci600552nb00039\/ci600552nb00039_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-0039-7","volume-title":"Lectures on Discrete Geometry","author":"Matou\u0161ek J.","year":"2002"},{"key":"ci600552nb00040\/ci600552nb00040_1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316849","volume-title":"Multivariate Density Estimation","author":"Scott D. W.","year":"1992"},{"key":"ci600552nb00042\/ci600552nb00042_1","volume-title":"http:\/\/www.mathworks.com\/products\/matlab\/ (accessed","author":"Matlab","year":"2007"},{"key":"ci600552nb00043\/ci600552nb00043_1","volume-title":"http:\/\/www.chemcomp.com (accessed","author":"Molecular Operating Environment","year":"2007"},{"key":"ci600552nb00046\/ci600552nb00046_1","unstructured":"Altman, D. G. Practical Statistics for Medical Research; Chapman & Hall:\u2009 London, 1991; pp 285\u2212288."},{"key":"ci600552nb00047\/ci600552nb00047_1","first-page":"167","volume":"41","author":"Agrafiotis D. K","year":"2001","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ci600552nb00052\/ci600552nb00052_1","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1990.10474926","volume":"85","author":"Wegman E. J","year":"1990","journal-title":"J. Am. Stat. Assoc."},{"key":"ci600552nb00054\/ci600552nb00054_1","volume-title":"where","author":"In"},{"key":"ci600552nb00058\/ci600552nb00058_1","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1002\/cem.1180070402","volume":"7","author":"Domine D.","year":"1993","journal-title":"J. Chemom."},{"key":"ci600552nb00059\/ci600552nb00059_1","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1002\/1096-987X(200103)22:4<373::AID-JCC1009>3.0.CO;2-8","volume":"22","author":"Rassokhin D. N.","year":"2001","journal-title":"J. Comput. Chem."},{"key":"ci600552nb00060\/ci600552nb00060_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2711-1","volume-title":"Modern Multidimensional ScalingTheory and Applications","author":"Borg I.","year":"1997"},{"key":"ci600552nb00061\/ci600552nb00061_1","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"Tenenbaum J. B.","year":"2000","journal-title":"Science"},{"key":"ci600552nb00062\/ci600552nb00062_1","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1126\/science.290.5500.2323","volume":"290","author":"Roweis S. T.","year":"2000","journal-title":"Science"},{"key":"ci600552nb00063\/ci600552nb00063_1","doi-asserted-by":"crossref","DOI":"10.1109\/T-C.1974.224051","volume-title":"A Projection Pursuit Algorithm for Exploratory Data Analysis","author":"Friedman J.","year":"1974"},{"key":"ci600552nb00064\/ci600552nb00064_1","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1002\/jcc.10234","volume":"24","author":"Agrafiotis D. K","year":"2003","journal-title":"J. Comput. Chem."},{"key":"ci600552nb00065\/ci600552nb00065_1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1021\/ci025631m","volume":"43","author":"Agrafiotis D. K.","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ci600552nb00066\/ci600552nb00066_1","volume-title":"Proc. Natl. Acad. Sci. U.S.A.","author":"Donoho D. L.","year":"2003"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/ci600552n","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T04:48:05Z","timestamp":1678855685000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/ci600552n"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,6,7]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2007,7,1]]}},"alternative-id":["10.1021\/ci600552n"],"URL":"https:\/\/doi.org\/10.1021\/ci600552n","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,6,7]]}}}