{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T23:20:45Z","timestamp":1782256845260,"version":"3.54.5"},"reference-count":166,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82260896"],"award-info":[{"award-number":["82260896"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82260896"],"award-info":[{"award-number":["82260896"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82260896"],"award-info":[{"award-number":["82260896"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Aided Mol Des"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10822-025-00679-0","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T15:50:32Z","timestamp":1761321032000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["3d electron cloud descriptors for enhanced QSAR modeling of anti-colorectal cancer compounds"],"prefix":"10.1007","volume":"39","author":[{"given":"Jianmin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongling","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"679_CR1","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1136\/gutjnl-2018-317592","volume":"68","author":"FE Vuik","year":"2019","unstructured":"Vuik FE, Nieuwenburg SA, Bardou M, Lansdorp-Vogelaar I, Dinis-Ribeiro M, Bento MJ, Bastiaansen BAJ, Leerdam ME, Kuipers EJ (2019) Increasing incidence of colorectal cancer in young adults in europe over the last 25 years. Gut 68:1820\u20131826","journal-title":"Gut"},{"key":"679_CR2","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1272\/jnms.JNMS.2022_89-310","volume":"89","author":"S Shinji","year":"2022","unstructured":"Shinji S, Yamada T, Matsuda A, Sonoda H, Ohta R, Iwai T, Yoshida H (2022) Recent advances in the treatment of colorectal cancer: a review. J Nippon Med Sch 89:246\u2013254","journal-title":"J Nippon Med Sch"},{"key":"679_CR3","first-page":"233","volume":"73","author":"RL Siegel","year":"2023","unstructured":"Siegel RL, Wagle NS, Cercek A, Smith RA, Jemal A (2023) Colorectal cancer statistics, 2023. CA Cancer J Clin 73:233\u2013254","journal-title":"CA Cancer J Clin"},{"key":"679_CR4","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1136\/gutjnl-2022-327736","volume":"72","author":"E Morgan","year":"2023","unstructured":"Morgan E, Arnold M, Gini A, Lorenzoni V, Cabasag CJ, Laversanne M, Vignat J, Ferlay J, Murphy N, Bray F (2023) Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from globocan. Gut 72:338\u2013344","journal-title":"Gut"},{"key":"679_CR5","doi-asserted-by":"publisher","first-page":"1116761","DOI":"10.3389\/fonc.2023.1116761","volume":"13","author":"MF Avram","year":"2023","unstructured":"Avram MF, Laz\u0103r DC, Mari\u015f MI, Olariu S (2023) Artificial intelligence in improving the outcome of surgical treatment in colorectal cancer. Front Oncol 13:1116761","journal-title":"Front Oncol"},{"key":"679_CR6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/2191-2858-1-3","volume":"1","author":"MH Bohari","year":"2011","unstructured":"Bohari MH, Srivastava HK, Sastry GN (2011) Analogue-based approaches in anti-cancer compound modelling: the relevance of qsar models. Org Med Chem Lett 1:3","journal-title":"Org Med Chem Lett"},{"key":"679_CR7","doi-asserted-by":"publisher","first-page":"11758","DOI":"10.1038\/s41598-023-38853-9","volume":"13","author":"W Shi","year":"2023","unstructured":"Shi W, Chen J, Yao N, Wu T, Suo X, Wang Q, Chen G, Xu Q, Zhou K, Liu B (2023) The prognostic ability of radiotherapy of different colorectal cancer histological subtypes and tumor sites. Sci Rep 13:11758","journal-title":"Sci Rep"},{"key":"679_CR8","doi-asserted-by":"publisher","first-page":"2555","DOI":"10.2147\/OTT.S298333","volume":"14","author":"J Yang","year":"2021","unstructured":"Yang J, Bi F, Gou H (2021) Complete pathologic response after concurrent treatment with pembrolizumab and radiotherapy in metastatic colorectal cancer: a case report. OncoTargets Ther 14:2555\u20132561","journal-title":"OncoTargets Ther"},{"key":"679_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12967-015-0592-z","volume":"13","author":"L Zheng","year":"2015","unstructured":"Zheng L, Zhang Y, Liu Y, Zhou M, Lu Y, Yuan L, Zhang Z, Li X (2015) Mir-106b induces cell radioresistance via the pten\/pi3k\/akt pathways and p21 in colorectal cancer. J Transl Med 13:1\u201313","journal-title":"J Transl Med"},{"key":"679_CR10","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.2174\/0929867324666170111152436","volume":"24","author":"RM McQuade","year":"2017","unstructured":"McQuade RM, Stojanovska V, Bornstein JC, Nurgali K (2017) Colorectal cancer chemotherapy: the evolution of treatment and new approaches. Curr Med Chem 24:1537\u20131557","journal-title":"Curr Med Chem"},{"key":"679_CR11","first-page":"1","volume":"18","author":"AO Ibrahim","year":"2018","unstructured":"Ibrahim AO, Oyebamiji AK, Oyewole OR, Semire B (2018) A dft based qsar and molecular docking studies on potent anti colon cancer activity of pyrazole derivatives. Glob J Med Res 18:1\u201312","journal-title":"Glob J Med Res"},{"key":"679_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104373","volume":"142","author":"F Ahmed","year":"2023","unstructured":"Ahmed F, Samantasinghar A, Soomro AM, Kim S, Choi KH (2023) A systematic review of computational approaches to understand cancer biology for informed drug repurposing. J Biomed Inform 142:104373","journal-title":"J Biomed Inform"},{"key":"679_CR13","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.jrid.2019.10.001","volume":"6","author":"SY Ismail","year":"2019","unstructured":"Ismail SY, Uzairu A (2019) In silico qsar and molecular docking studies of sulfur containing shikonin oxime derivatives as anti cancer agent for colon cancer. Radiol Infect Dis 6:108\u2013121","journal-title":"Radiol Infect Dis"},{"key":"679_CR14","first-page":"15","volume":"14","author":"C Hansch","year":"1980","unstructured":"Hansch C (1980) Thoughts on the use of qsar in drug design review. Khimiko Farmatsevticheskii Zhurnal 14:15\u201330","journal-title":"Khimiko Farmatsevticheskii Zhurnal"},{"key":"679_CR15","doi-asserted-by":"publisher","first-page":"4977","DOI":"10.1021\/jm4004285","volume":"57","author":"A Cherkasov","year":"2014","unstructured":"Cherkasov A, Muratov EN, Fourches D, Varnek A, Baskin II, Cronin M, Dearden J, Gramatica P, Martin YC, Todeschini R, Consonni V, Kuz\u2019min VE, Cramer R, Benigni R, Yang C, Rathman J, Terfloth L, Gasteiger J, Richard A, Tropsha A (2014) Qsar modeling: where have you been? where are you going to? J Med Chem 57:4977\u20135010","journal-title":"J Med Chem"},{"key":"679_CR16","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1080\/1062936X.2014.899267","volume":"25","author":"P Achary","year":"2014","unstructured":"Achary P (2014) Qspr modelling of dielectric constants of $$\\pi $$ conjugated organic compounds by means of the coral software. SAR QSAR Environ Res 25:507\u2013526","journal-title":"SAR QSAR Environ Res"},{"key":"679_CR17","first-page":"769","volume":"12","author":"T Wang","year":"2017","unstructured":"Wang T, Yuan XS, Wu MB, Lin JP, Yang LR (2017) The advancement of multidimensional qsar for novel drug discovery where are we headed? Expert Opin Drug Discov 12:769\u2013784","journal-title":"Expert Opin Drug Discov"},{"key":"679_CR18","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.3390\/molecules26061617","volume":"26","author":"M Lovri\u0107","year":"2021","unstructured":"Lovri\u0107 M, Malev O, Klobu\u010dar G, Kern R, Liu JJ, Lu\u010di\u0107 B (2021) Predictive capability of qsar models based on the comptox zebrafish embryo assays: an imbalanced classification problem. Molecules 26:1617","journal-title":"Molecules"},{"key":"679_CR19","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.chemolab.2015.06.016","volume":"149","author":"S Yousefinejad","year":"2015","unstructured":"Yousefinejad S, Hemmateenejad B (2015) Chemometrics tools in qsar\/qspr studies: a historical perspective. Chemom Intell Lab Syst 149:177\u2013204","journal-title":"Chemom Intell Lab Syst"},{"key":"679_CR20","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1016\/j.jtbi.2009.07.031","volume":"261","author":"S Vilar","year":"2009","unstructured":"Vilar S, Gonz\u00e1lez-D\u00edaz H, Santana L, Uriarte E (2009) A network qsar model for prediction of genetic component biomarkers in human colorectal cancer. J Theor Biol 261:449\u2013458","journal-title":"J Theor Biol"},{"key":"679_CR21","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/biom8030056","volume":"8","author":"S Cruz","year":"2018","unstructured":"Cruz S, Gomes SE, Borralho PM, Rodrigues CM, Gaud\u00eancio SP, Pereira F (2018) In silico hct116 human colon cancer cell based models en route to the discovery of lead like anticancer drugs. Biomolecules 8:56","journal-title":"Biomolecules"},{"key":"679_CR22","doi-asserted-by":"publisher","first-page":"4848","DOI":"10.1016\/j.bmc.2012.05.071","volume":"20","author":"A Speck-Planche","year":"2012","unstructured":"Speck-Planche A, Kleandrova VV, Luan F, Cordeiro MND (2012) Rational drug design for anti cancer chemotherapy: multi target qsar models for the in silico discovery of anti colorectal cancer agents. Bioorg Med Chem 20:4848\u20134855","journal-title":"Bioorg Med Chem"},{"key":"679_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2021.104384","volume":"217","author":"L Wang","year":"2021","unstructured":"Wang L, Ding J, Pan L, Cao D, Jiang H, Ding X (2021) Quantum chemical descriptors in quantitative structure - activity relationship models and their applications. Chemom Intell Lab Syst 217:104384","journal-title":"Chemom Intell Lab Syst"},{"key":"679_CR24","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1021\/cr950202r","volume":"96","author":"M Karelson","year":"1996","unstructured":"Karelson M, Lobanov VS, Katritzky AR (1996) Quantum chemical descriptors in qsar\/qspr studies. Chem Rev 96:1027\u20131044","journal-title":"Chem Rev"},{"key":"679_CR25","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.2174\/1568026618666180719164149","volume":"18","author":"A Gupta","year":"2018","unstructured":"Gupta A, Kumar V, Aparoy P (2018) Role of topological, electronic, geometrical, constitutional and quantum chemical based descriptors in qsar: mpges-1 as a case study. Curr Top Med Chem 18:1075\u20131090","journal-title":"Curr Top Med Chem"},{"key":"679_CR26","volume-title":"Quantum Chemistry in QSAR: Quantum Chemical Descriptors: Use","author":"S Van Damme","year":"2009","unstructured":"Van Damme S (2009) Quantum Chemistry in QSAR: Quantum Chemical Descriptors: Use. Benefits and Drawbacks. Ghent University, Ghent"},{"key":"679_CR27","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s11120-009-9404-8","volume":"102","author":"M Orio","year":"2009","unstructured":"Orio M, Pantazis DA, Neese F (2009) Density functional theory. Photosynth Res 102:443\u2013453","journal-title":"Photosynth Res"},{"key":"679_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0370-1573(97)00083-5","volume":"298","author":"\u00c1 Nagy","year":"1998","unstructured":"Nagy \u00c1 (1998) Density functional. Theory and application to atoms and molecules. Phys. Rep. 298:1\u201379","journal-title":"Phys. Rep."},{"key":"679_CR29","unstructured":"ChEMBL Database: ChEMBL Database. European Bioinformatics Institute, Cambridge. https:\/\/www.ebi.ac.uk\/chembl\/ (accessed July 28, 2025) (2025)"},{"key":"679_CR30","doi-asserted-by":"publisher","first-page":"1800082","DOI":"10.1002\/minf.201800082","volume":"38","author":"M Lovri\u0107","year":"2019","unstructured":"Lovri\u0107 M, Molero JM, Kern R (2019) Pyspark and rdkit: moving towards big data in cheminformatics. Mol Inform 38:1800082","journal-title":"Mol Inform"},{"key":"679_CR31","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1103\/RevModPhys.84.621","volume":"84","author":"C Weedbrook","year":"2012","unstructured":"Weedbrook C, Pirandola S, Garc\u00eda-Patr\u00f3n R, Cerf NJ, Ralph TC, Shapiro JH, Lloyd S (2012) Gaussian quantum information. Rev Mod Phys 84:621\u2013669","journal-title":"Rev Mod Phys"},{"issue":"1","key":"679_CR32","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, Morley C, Vandermeersch T, Hutchison GR (2011) Open babel: an open chemical toolbox. J Cheminform 3(1):33","journal-title":"J Cheminform"},{"key":"679_CR33","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3847\/2515-5172\/ad0044","volume":"7","author":"K Labrie","year":"2023","unstructured":"Labrie K, Simpson C, Cardenes R, Turner J, Soraisam M, Quint B, Thomas-Osip J (2023) DRAGONS-a Quick Overview Res Notes AAS 7:214","journal-title":"DRAGONS-a Quick Overview Res Notes AAS"},{"key":"679_CR34","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1002\/jcc.22885","volume":"33","author":"T Lu","year":"2012","unstructured":"Lu T, Chen F (2012) Multiwfn: a multifunctional wavefunction analyzer. J Comput Chem 33:580\u2013592","journal-title":"J Comput Chem"},{"key":"679_CR35","doi-asserted-by":"publisher","first-page":"15100","DOI":"10.1038\/s41598-022-19363-6","volume":"12","author":"L Wang","year":"2022","unstructured":"Wang L, Bai R, Shi X, Zhang W, Cui Y, Wang X, Huang B (2022) A pocket-based 3d molecule generative model fueled by experimental electron density. Sci Rep 12:15100","journal-title":"Sci Rep"},{"key":"679_CR36","doi-asserted-by":"publisher","first-page":"2516","DOI":"10.1021\/ci300293f","volume":"52","author":"NC Firth","year":"2012","unstructured":"Firth NC, Brown N, Blagg J (2012) Plane of best fit: a novel method to characterize the three-dimensionality of molecules. J Chem Inf Model 52:2516\u20132525","journal-title":"J Chem Inf Model"},{"key":"679_CR37","volume-title":"Statistical Mechanics","author":"N Davidson","year":"2013","unstructured":"Davidson N (2013) Statistical Mechanics. Courier Corporation, North Chelmsford"},{"key":"679_CR38","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1016\/j.jmgm.2007.08.009","volume":"26","author":"L Mak","year":"2008","unstructured":"Mak L, Grandison S, Morris RJ (2008) An extension of spherical harmonics to region-based rotationally invariant descriptors for molecular shape description and comparison. J Mol Graph Model 26:1035\u20131045","journal-title":"J Mol Graph Model"},{"key":"679_CR39","doi-asserted-by":"crossref","unstructured":"Rusu RB, Bradski G, Thibaux R, Hsu J (2010) Fast 3d recognition and pose using the viewpoint feature histogram. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2155\u20132162. IEEE, Piscataway","DOI":"10.1109\/IROS.2010.5651280"},{"issue":"1","key":"679_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1515\/cmb-2020-0001","volume":"8","author":"D Bramer","year":"2020","unstructured":"Bramer D, Wei GW (2020) Atom-specific persistent homology and its application to protein flexibility analysis. Computational and mathematical biophysics 8(1):1\u201335","journal-title":"Computational and mathematical biophysics"},{"key":"679_CR41","unstructured":"Kazhdan M, Funkhouser T, Rusinkiewicz S (2003) Rotation invariant spherical harmonic representation of 3d shape descriptors. In: Symposium on Geometry Processing, vol. 6, pp. 156\u2013164. Eurographics Association, Goslar"},{"key":"679_CR42","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13321-018-0296-5","volume":"10","author":"F Pereira","year":"2018","unstructured":"Pereira F, Aires-de-Sousa J (2018) Machine learning for the prediction of molecular dipole moments obtained by density functional theory. J Cheminform 10:43","journal-title":"J Cheminform"},{"key":"679_CR43","volume-title":"Quantum Chemistry","author":"JP Lowe","year":"2011","unstructured":"Lowe JP, Peterson K (2011) Quantum Chemistry. Elsevier, Amsterdam"},{"key":"679_CR44","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379\u2013423","journal-title":"Bell Syst Tech J"},{"key":"679_CR45","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1103\/RevModPhys.2.116","volume":"2","author":"GW Stewart","year":"1930","unstructured":"Stewart GW (1930) X-ray diffraction in liquids. Rev Mod Phys 2:116","journal-title":"Rev Mod Phys"},{"key":"679_CR46","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198803195.001.0001","volume-title":"Computer Simulation of Liquids","author":"MP Allen","year":"2017","unstructured":"Allen MP, Tildesley DJ (2017) Computer Simulation of Liquids. Oxford University Press, Oxford"},{"key":"679_CR47","unstructured":"Dong Z, Chen W, Bao H, Zhang H, Peng Q (2004) Real-time voxelization for complex polygonal models. In: 12th Pacific Conference on Computer Graphics and Applications, pp 43\u201350. IEEE, Piscataway"},{"key":"679_CR48","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1145\/37402.37422","volume":"21","author":"WE Lorensen","year":"1987","unstructured":"Lorensen WE, Cline HE (1987) Marching cubes: a high resolution 3d surface construction algorithm. ACM SIGGRAPH Computer Graphics 21:163\u2013169","journal-title":"ACM SIGGRAPH Computer Graphics"},{"key":"679_CR49","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.21105\/joss.01450","volume":"4","author":"C Sullivan","year":"2019","unstructured":"Sullivan C, Kaszynski A (2019) Pyvista: 3d plotting and mesh analysis through a streamlined interface for the visualization toolkit (vtk). J Open Source Softw 4:1450","journal-title":"J Open Source Softw"},{"key":"679_CR50","doi-asserted-by":"publisher","DOI":"10.1201\/9781003527947","volume-title":"Classical Mechanics","author":"TL Chow","year":"2024","unstructured":"Chow TL (2024) Classical Mechanics. CRC Press, Boca Raton"},{"key":"679_CR51","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1021\/ci025599w","volume":"43","author":"WHB Sauer","year":"2003","unstructured":"Sauer WHB, Schwarz MK (2003) Molecular shape diversity of combinatorial libraries: a prerequisite for broad bioactivity. J Chem Inf Comput Sci 43:987\u20131003","journal-title":"J Chem Inf Comput Sci"},{"key":"679_CR52","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/BF02712873","volume":"16","author":"TM Chan","year":"1996","unstructured":"Chan TM (1996) Optimal output-sensitive convex hull algorithms in two and three dimensions. Discrete Comput Geom 16:361\u2013368","journal-title":"Discrete Comput Geom"},{"key":"679_CR53","doi-asserted-by":"publisher","DOI":"10.1017\/9781316995433","volume-title":"Introduction to Quantum Mechanics","author":"DJ Griffiths","year":"2018","unstructured":"Griffiths DJ, Schroeter DF (2018) Introduction to Quantum Mechanics. Cambridge University Press, Cambridge"},{"key":"679_CR54","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1093\/bioinformatics\/bti337","volume":"21","author":"RJ Morris","year":"2005","unstructured":"Morris RJ, Najmanovich RJ, Kahraman A, Thornton JM (2005) Real spherical harmonic expansion coefficients as 3d shape descriptors for protein binding pocket and ligand comparisons. Bioinformatics 21:2347\u20132355","journal-title":"Bioinformatics"},{"key":"679_CR55","unstructured":"Canterakis N (1999) 3d zernike moments and zernike affine invariants for 3d image analysis and recognition. In: Scandinavian Conference on Image Analysis (SCIA), p 85"},{"key":"679_CR56","doi-asserted-by":"crossref","unstructured":"Novotni M, Klein R (2003) 3d zernike descriptors for content based shape retrieval. In: Proceedings of the Eighth ACM Symposium on Solid Modeling and Applications, pp 216\u2013225","DOI":"10.1145\/781606.781639"},{"key":"679_CR57","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1016\/j.cad.2004.01.005","volume":"36","author":"M Novotni","year":"2004","unstructured":"Novotni M, Klein R (2004) Shape retrieval using 3d zernike descriptors. Comput Aided Des 36:1047\u20131062","journal-title":"Comput Aided Des"},{"key":"679_CR58","first-page":"119","volume":"10","author":"RB Rusu","year":"2008","unstructured":"Rusu RB, Marton ZC, Blodow N, Beetz M (2008) Persistent point feature histograms for 3d point clouds. Intelligent Autonomous Systems 10:119\u2013128","journal-title":"Intelligent Autonomous Systems"},{"key":"679_CR59","doi-asserted-by":"crossref","unstructured":"Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (fpfh) for 3d registration. In: 2009 IEEE International Conference on Robotics and Automation, pp 3212\u20133217","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"679_CR60","first-page":"128","volume":"8","author":"L Euler","year":"1741","unstructured":"Euler L (1741) Solutio problematis ad geometriam situs pertinentis. Comment. Acad. Sci. Petropolitanae 8:128\u2013140","journal-title":"Comment. Acad. Sci. Petropolitanae"},{"key":"679_CR61","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","volume":"1","author":"LC Freeman","year":"1978","unstructured":"Freeman LC (1978) Centrality in social networks conceptual clarification. Soc Networks 1:215\u2013239","journal-title":"Soc Networks"},{"key":"679_CR62","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1142\/S0219633602000117","volume":"1","author":"S Vishveshwara","year":"2002","unstructured":"Vishveshwara S, Brinda KV, Kannan N (2002) Protein structure: insights from graph theory. J Theor Comput Chem 1:187\u2013211","journal-title":"J Theor Comput Chem"},{"key":"679_CR63","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1038\/nrg1272","volume":"5","author":"AL Barabasi","year":"2004","unstructured":"Barabasi AL, Oltvai ZN (2004) Network biology: understanding the cell\u2019s functional organization. Nat Rev Genet 5:101\u2013113","journal-title":"Nat Rev Genet"},{"key":"679_CR64","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu Z, Ramsundar B, Feinberg EN, Gomes J, Geniesse C, Pappu AS, Pande V (2018) Moleculenet: a benchmark for molecular machine learning. Chem Sci 9:513\u2013530","journal-title":"Chem Sci"},{"key":"679_CR65","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00454-002-2885-2","volume":"28","author":"H Edelsbrunner","year":"2002","unstructured":"Edelsbrunner H, Letscher D, Zomorodian A (2002) Topological persistence and simplification. Discrete Comput Geom 28:511\u2013533","journal-title":"Discrete Comput Geom"},{"key":"679_CR66","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1002\/cnm.2655","volume":"30","author":"K Xia","year":"2014","unstructured":"Xia K, Wei GW (2014) Persistent homology analysis of protein structure, flexibility, and folding. Int J Numer Methods Biomed Eng 30:814\u2013844","journal-title":"Int J Numer Methods Biomed Eng"},{"key":"679_CR67","doi-asserted-by":"publisher","first-page":"1005690","DOI":"10.1371\/journal.pcbi.1005690","volume":"13","author":"Z Cang","year":"2017","unstructured":"Cang Z, Wei GW (2017) Topologynet: topology based deep convolutional and multi-task neural networks for biomolecular property predictions. PLoS Comput Biol 13:1005690","journal-title":"PLoS Comput Biol"},{"key":"679_CR68","volume-title":"Les Objets Fractals: Forme","author":"BB Mandelbrot","year":"1975","unstructured":"Mandelbrot BB (1975) Les Objets Fractals: Forme. Hasard et Dimension. Flammarion, Paris"},{"key":"679_CR69","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1126\/science.4071040","volume":"230","author":"M Lewis","year":"1985","unstructured":"Lewis M, Rees DC (1985) Fractal surfaces of proteins. Science 230:1163\u20131165","journal-title":"Science"},{"key":"679_CR70","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/174462.156635","volume":"13","author":"H Edelsbrunner","year":"1994","unstructured":"Edelsbrunner H, M\u00fccke EP (1994) Three-dimensional alpha shapes. ACM Trans Graph 13:43\u201372","journal-title":"ACM Trans Graph"},{"key":"679_CR71","doi-asserted-by":"publisher","first-page":"1884","DOI":"10.1002\/pro.5560070905","volume":"7","author":"J Liang","year":"1998","unstructured":"Liang J, Woodward C, Edelsbrunner H (1998) Anatomy of protein pockets and cavities: measurement of binding site geometry and implications for ligand design. Protein Sci 7:1884\u20131897","journal-title":"Protein Sci"},{"key":"679_CR72","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1093\/nar\/gkae415","volume":"52","author":"B Ye","year":"2024","unstructured":"Ye B, Tian W, Wang B, Liang J (2024) Castpfold: computed atlas of surface topography of the universe of protein folds. Nucleic Acids Res 52:194\u2013199","journal-title":"Nucleic Acids Res"},{"key":"679_CR73","first-page":"1","volume":"23","author":"A Mazhibiyeva","year":"2025","unstructured":"Mazhibiyeva A, Pham TT, Pats K, Lukac M, Moln\u00e1r F (2025) Bridging prediction and reality: comprehensive analysis of experimental and alphafold 2 full-length nuclear receptor structures. Comput Struct Biotechnol J 23:1\u201315","journal-title":"Comput Struct Biotechnol J"},{"key":"679_CR74","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1126\/science.1205438","volume":"334","author":"DN Reshef","year":"2011","unstructured":"Reshef DN, Reshef YA, Finucane HK, Grossman SR, McVean G, Turnbaugh PJ, Sabeti PC (2011) Detecting novel associations in large data sets. Science 334:1518\u20131524","journal-title":"Science"},{"key":"679_CR75","first-page":"223","volume":"37","author":"M Ergin","year":"2023","unstructured":"Ergin M, Koskan O (2023) Comparison of student - t, welch\u2019s t, and mann - whitney u tests in terms of type i error rate and test power. Selcuk J Agric Food Sci 37:223\u2013231","journal-title":"Selcuk J Agric Food Sci"},{"key":"679_CR76","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1080\/1062936X.2021.1971761","volume":"32","author":"E Shamsi","year":"2021","unstructured":"Shamsi E, Rahati A, Dehghanian E (2021) A modified binary particle swarm optimization with a machine learning algorithm and molecular docking for qsar modelling of cholinesterase inhibitors. SAR QSAR Environ Res 32:745\u2013767","journal-title":"SAR QSAR Environ Res"},{"key":"679_CR77","doi-asserted-by":"crossref","unstructured":"Kennedy J, Eberhart RC (1997) A discrete binary version of the particle swarm algorithm. 1997 IEEE International Conference on Systems, Man, and Cybernetics, vol 5. Computational Cybernetics and Simulation. IEEE, Orlando, FL, USA, pp 4104\u20134108","DOI":"10.1109\/ICSMC.1997.637339"},{"key":"679_CR78","doi-asserted-by":"crossref","unstructured":"Chuang LY, Tsai SW, Yang CH (2008) Catfish particle swarm optimization. In: 2008 IEEE Swarm Intelligence Symposium, pp 1\u20135. IEEE, St. Louis, MO, USA","DOI":"10.1109\/SIS.2008.4668277"},{"key":"679_CR79","unstructured":"Hefny HA, Azab SS (2010) Chaotic particle swarm optimization. In: 2010 The 7th International Conference on Informatics and Systems (INFOS), pp 1\u20135. IEEE, Cairo, Egypt"},{"key":"679_CR80","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1016\/j.ins.2022.11.155","volume":"622","author":"K Shang","year":"2023","unstructured":"Shang K, Shu T, Ishibuchi H, Nan Y, Pang LM (2023) Benchmarking large-scale subset selection in evolutionary multi-objective optimization. Inf Sci 622:755\u2013770","journal-title":"Inf Sci"},{"key":"679_CR81","doi-asserted-by":"publisher","first-page":"70172","DOI":"10.1111\/cts.70172","volume":"18","author":"M Wiens","year":"2025","unstructured":"Wiens M, Verone-Boyle A, Henscheid N, Podichetty JT, Burton J (2025) A tutorial and use case example of the extreme gradient boosting (xgboost) artificial intelligence algorithm for drug development applications. Clin Transl Sci 18:70172","journal-title":"Clin Transl Sci"},{"key":"679_CR82","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332","journal-title":"Mach Learn"},{"key":"679_CR83","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Liu TY (2017) Lightgbm: A highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, vol. 30, pp 3146\u20133154. MIT Press, Cambridge"},{"key":"679_CR84","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/S0925-2312(01)00644-0","volume":"48","author":"JA Suykens","year":"2002","unstructured":"Suykens JA, De Brabanter J, Lukas L, Vandewalle J (2002) Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing 48:85\u2013105","journal-title":"Neurocomputing"},{"key":"679_CR85","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281\u2013305","journal-title":"J Mach Learn Res"},{"key":"679_CR86","first-page":"2407","volume":"6","author":"S Widodo","year":"2022","unstructured":"Widodo S, Brawijaya H, Samudi S (2022) Stratified k-fold cross validation optimization on machine learning for prediction. Sinkron J Penelitian Tek Inform 6:2407\u20132414","journal-title":"Sinkron J Penelitian Tek Inform"},{"key":"679_CR87","unstructured":"Carrington AM, Manuel DG, Fieguth PW, Ramsay T, Osmani V, Wernly B, Holzinger A (2021) Deep ROC analysis and AUC as balanced average accuracy to improve model selection, understanding and interpretation. Preprint at https:\/\/arxiv.org\/abs\/2103.11357"},{"key":"679_CR88","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13040-021-00244-z","volume":"14","author":"D Chicco","year":"2021","unstructured":"Chicco D, T\u00f6tsch N, Jurman G (2021) The matthews correlation coefficient (mcc) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Min 14:13","journal-title":"BioData Min"},{"key":"679_CR89","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1093\/bioinformatics\/btaa046","volume":"36","author":"S Parvandeh","year":"2020","unstructured":"Parvandeh S, Yeh HW, Paulus MP, McKinney BA (2020) Consensus features nested cross-validation. Bioinformatics 36:3093\u20133098","journal-title":"Bioinformatics"},{"key":"679_CR90","first-page":"411","volume":"37","author":"NS Sumi","year":"2014","unstructured":"Sumi NS, Islam MA, Hossain MA (2014) Evaluation and computation of diagnostic tests: a simple alternative. Bull Malays Math Sci Soc 37:411\u2013423","journal-title":"Bull Malays Math Sci Soc"},{"key":"679_CR91","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1214\/ss\/1032280214","volume":"11","author":"TJ DiCiccio","year":"1996","unstructured":"DiCiccio TJ, Efron B (1996) Bootstrap confidence intervals. Stat Sci 11:189\u2013228","journal-title":"Stat Sci"},{"key":"679_CR92","doi-asserted-by":"publisher","first-page":"7480","DOI":"10.3390\/app14177480","volume":"14","author":"K Dashdondov","year":"2024","unstructured":"Dashdondov K, Lee S, Erdenebat MU (2024) Enhancing diabetes prediction and prevention through mahalanobis distance and machine learning integration. Appl Sci 14:7480","journal-title":"Appl Sci"},{"issue":"1","key":"679_CR93","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 JL (2018) A probabilistic molecular fingerprint for big data settings. J Cheminform 10(1):66","journal-title":"J Cheminform"},{"issue":"9","key":"679_CR94","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1080\/1062936X.2014.942696","volume":"25","author":"SW Qin","year":"2014","unstructured":"Qin SW, Li Z, Jin Y, Zhang SP (2014) Shape similarity comparison of protein cpk models based on improved l1-medial skeleton. SAR QSAR Environ Res 25(9):747\u2013759","journal-title":"SAR QSAR Environ Res"},{"key":"679_CR95","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.1038\/s41598-022-05717-7","volume":"12","author":"S Guan","year":"2022","unstructured":"Guan S, Fu N (2022) Class imbalance learning with bayesian optimization applied in drug discovery. Sci Rep 12:2069","journal-title":"Sci Rep"},{"key":"679_CR96","doi-asserted-by":"publisher","first-page":"4423","DOI":"10.3390\/electronics12214423","volume":"12","author":"J Sadaiyandi","year":"2023","unstructured":"Sadaiyandi J, Arumugam P, Sangaiah AK, Zhang C (2023) Stratified sampling-based deep learning approach to increase prediction accuracy of unbalanced dataset. Electronics 12:4423","journal-title":"Electronics"},{"key":"679_CR97","doi-asserted-by":"publisher","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","volume":"14","author":"O Rainio","year":"2024","unstructured":"Rainio O, Teuho J, Kl\u00e9n R (2024) Evaluation metrics and statistical tests for machine learning. Sci Rep 14:6086","journal-title":"Sci Rep"},{"issue":"1","key":"679_CR98","first-page":"123","volume":"47","author":"S Suprapto","year":"2024","unstructured":"Suprapto S (2024) Comparative analysis of preprocessing methods for molecular descriptors in predicting anti-cathepsin activity. S Afr J Chem Eng 47(1):123\u2013135","journal-title":"S Afr J Chem Eng"},{"key":"679_CR99","doi-asserted-by":"publisher","first-page":"2200186","DOI":"10.1002\/minf.202200186","volume":"42","author":"MS Bahia","year":"2023","unstructured":"Bahia MS, Kaspi O, Touitou M, Binayev I, Dhail S, Spiegel J, Senderowitz H (2023) A comparison between 2d and 3d descriptors in qsar modeling based on bio?active conformations. Mol Inform 42:2200186","journal-title":"Mol Inform"},{"key":"679_CR100","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1186\/s12915-025-02302-y","volume":"23","author":"S Jin","year":"2025","unstructured":"Jin S, Long H, Huang A, Wang J, Yu X, Xu Z, Xu J (2025) Accurate prediction of synergistic drug combination using a multi-source information fusion framework. BMC Biol 23:200","journal-title":"BMC Biol"},{"key":"679_CR101","volume-title":"Handbook of Molecular Descriptors","author":"R Todeschini","year":"2008","unstructured":"Todeschini R, Consonni V (2008) Handbook of Molecular Descriptors. John Wiley & Sons, Hoboken"},{"key":"679_CR102","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.jmgm.2014.10.006","volume":"54","author":"O Devinyak","year":"2014","unstructured":"Devinyak O, Havrylyuk D, Lesyk R (2014) 3d-morse descriptors explained. J Mol Graph Model 54:194\u2013203","journal-title":"J Mol Graph Model"},{"key":"679_CR103","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s13321-023-00737-5","volume":"15","author":"P Panwar","year":"2023","unstructured":"Panwar P, Yang Q, Martini A (2023) Pyl3dmd: python lammps 3d molecular descriptors package. J Cheminform 15:69","journal-title":"J Cheminform"},{"key":"679_CR104","doi-asserted-by":"crossref","unstructured":"Idakwo G, Luttrell\u00a0IV J, Chen M, Hong H, Gong P, Zhang C (2019) A review of feature reduction methods for QSAR-based toxicity prediction. In: Advances in Computational Toxicology: Methodologies and Applications in Regulatory Science, pp 119\u2013139. Springer, Berlin","DOI":"10.1007\/978-3-030-16443-0_7"},{"key":"679_CR105","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1186\/s12859-019-3135-4","volume":"20","author":"S Kwon","year":"2019","unstructured":"Kwon S, Bae H, Jo J, Yoon S (2019) Comprehensive ensemble in qsar prediction for drug discovery. BMC Bioinform 20:521","journal-title":"BMC Bioinform"},{"key":"679_CR106","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1002\/jcc.20464","volume":"27","author":"Z Xi","year":"2006","unstructured":"Xi Z, Yu Z, Niu C, Ban S, Yang G (2006) Development of a general quantum?chemical descriptor for steric effects: density functional theory based qsar study of herbicidal sulfonylurea analogues. J Comput Chem 27:1571\u20131576","journal-title":"J Comput Chem"},{"key":"679_CR107","first-page":"56","volume":"2","author":"D Gupta","year":"2012","unstructured":"Gupta D, Ghafir S (2012) An overview of methods maintaining diversity in genetic algorithms. Int J Emerg Technol Adv Eng 2:56\u201360","journal-title":"Int J Emerg Technol Adv Eng"},{"key":"679_CR108","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1016\/j.applthermaleng.2019.03.111","volume":"154","author":"H Han","year":"2019","unstructured":"Han H, Cui X, Fan Y, Qing H (2019) Least squares support vector machine (ls-svm)-based chiller fault diagnosis using fault indicative features. Appl Therm Eng 154:540\u2013547","journal-title":"Appl Therm Eng"},{"key":"679_CR109","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1007\/s00439-021-02402-z","volume":"141","author":"AM Musolf","year":"2022","unstructured":"Musolf AM, Holzinger ER, Malley JD, Bailey-Wilson JE (2022) What makes a good prediction? feature importance and beginning to open the black box of machine learning in genetics. Hum Genet 141:1515\u20131528","journal-title":"Hum Genet"},{"key":"679_CR110","first-page":"1","volume":"15","author":"Z Zhou","year":"2021","unstructured":"Zhou Z, Hooker G (2021) Unbiased measurement of feature importance in tree-based methods. ACM Trans Knowl Discov Data 15:1\u201321","journal-title":"ACM Trans Knowl Discov Data"},{"key":"679_CR111","unstructured":"Manthiramoorthi M, Mani M, Murthy AG (2021) Application of Pareto\u2019s principle on deep learning research output: A scientometric analysis. In: Proceedings of the International Conference on Machine Learning and Smart Technology\u2013ICMLST, Chennai, India, pp 22\u201326"},{"key":"679_CR112","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/S0169-7439(96)00063-9","volume":"36","author":"R Todeschini","year":"1997","unstructured":"Todeschini R, Moro G, Boggia R, Bonati L, Cosentino U, Lasagni M, Pitea D (1997) Modeling and prediction of molecular properties. Theory of grid-weighted holistic invariant molecular (G-WHIM) descriptors. Chemom. Intell. Lab. Syst. 36:65\u201373","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"679_CR113","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1080\/10629369708039126","volume":"7","author":"R Todeschini","year":"1997","unstructured":"Todeschini R, Gramatica P (1997) The whim theory: new 3d molecular descriptors for qsar in environmental modelling. SAR QSAR Environ Res 7:89\u2013115","journal-title":"SAR QSAR Environ Res"},{"key":"679_CR114","doi-asserted-by":"publisher","first-page":"83956","DOI":"10.1371\/journal.pone.0083956","volume":"8","author":"M Dehmer","year":"2013","unstructured":"Dehmer M, Emmert-Streib F, Tripathi S (2013) Large-scale evaluation of molecular descriptors by means of clustering. PLoS ONE 8:83956","journal-title":"PLoS ONE"},{"key":"679_CR115","doi-asserted-by":"publisher","first-page":"23218","DOI":"10.1021\/acsomega.3c03722","volume":"8","author":"H Kaneko","year":"2023","unstructured":"Kaneko H (2023) Interpretation of machine learning models for data sets with many features using feature importance. ACS Omega 8:23218\u201323225","journal-title":"ACS Omega"},{"key":"679_CR116","unstructured":"Lin H, Zhang O, Xu J, Liu Y, Cheng Z, Wu L, Li SZ (2025) Tokenizing Electron Cloud in Protein-Ligand Interaction Learning. Preprint at https:\/\/arxiv.org\/abs\/2505.19014"},{"key":"679_CR117","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","volume":"108","author":"M Rupp","year":"2012","unstructured":"Rupp M, Tkatchenko A, M\u00fcller KR, Von Lilienfeld OA (2012) Fast and accurate modeling of molecular atomization energies with machine learning. Phys Rev Lett 108:058301","journal-title":"Phys Rev Lett"},{"key":"679_CR118","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.chemolab.2011.05.013","volume":"117","author":"K Varmuza","year":"2012","unstructured":"Varmuza K, Filzmoser P, Liebmann B, Dehmer M (2012) Redundancy analysis for characterizing the correlation between groups of variables-applied to molecular descriptors. Chemom Intell Lab Syst 117:31\u201341","journal-title":"Chemom Intell Lab Syst"},{"key":"679_CR119","doi-asserted-by":"publisher","first-page":"1800154","DOI":"10.1002\/minf.201800154","volume":"38","author":"A R\u00e1cz","year":"2019","unstructured":"R\u00e1cz A, Bajusz D, H\u00e9berger K (2019) Intercorrelation limits in molecular descriptor preselection for qsar\/qspr. Mol Inform 38:1800154","journal-title":"Mol Inform"},{"key":"679_CR120","first-page":"237","volume":"56","author":"A Mauri","year":"2006","unstructured":"Mauri A, Consonni V, Pavan M, Todeschini R (2006) Dragon software: an easy approach to molecular descriptor calculations. Match 56:237\u2013248","journal-title":"Match"},{"key":"679_CR121","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.ejmech.2010.12.026","volume":"46","author":"A Borota","year":"2011","unstructured":"Borota A, Mracec M, Gruia A, Rad-Curp\u0103n R, Ostopovici-Halip L, Mracec M (2011) A qsar study using mtd method and dragon descriptors for a series of selective ligands of $$\\alpha $$2c adrenoceptor. Eur J Med Chem 46:877\u2013884","journal-title":"Eur J Med Chem"},{"key":"679_CR122","doi-asserted-by":"crossref","unstructured":"Mitra NJ, Nguyen A (2003) Estimating surface normals in noisy point cloud data. In: Proceedings of the Nineteenth Annual Symposium on Computational Geometry, pp 322\u2013328. ACM, New York","DOI":"10.1145\/777792.777840"},{"key":"679_CR123","volume-title":"Statistical Methods in the Atmospheric Sciences","author":"DS Wilks","year":"2011","unstructured":"Wilks DS (2011) Statistical Methods in the Atmospheric Sciences, vol 100. Academic Press, Cambridge"},{"key":"679_CR124","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1021\/ct100641a","volume":"7","author":"J Contreras-Garc\u00eda","year":"2011","unstructured":"Contreras-Garc\u00eda J, Johnson ER, Keinan S, Chaudret R, Piquemal JP, Beratan DN, Yang W (2011) Nciplot: a program for plotting noncovalent interaction regions. J Chem Theory Comput 7:625\u2013632","journal-title":"J Chem Theory Comput"},{"key":"679_CR125","first-page":"679","volume":"8","author":"J Canny","year":"2009","unstructured":"Canny J (2009) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8:679\u2013698","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"679_CR126","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1002\/jcc.20681","volume":"28","author":"PJ Ballester","year":"2007","unstructured":"Ballester PJ, Richards WG (2007) Ultrafast shape recognition to search compound databases for similar molecular shapes. J Comput Chem 28:1711\u20131723","journal-title":"J Comput Chem"},{"key":"679_CR127","volume-title":"Introduction to Computational Chemistry","author":"F Jensen","year":"2017","unstructured":"Jensen F (2017) Introduction to Computational Chemistry. John Wiley & Sons, Hoboken"},{"key":"679_CR128","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2019.106949","volume":"247","author":"L Himanen","year":"2020","unstructured":"Himanen L, J\u00e4ger MO, Morooka EV, Canova FF, Ranawat YS, Gao DZ, Foster AS (2020) Dscribe: library of descriptors for machine learning in materials science. Comput Phys Commun 247:106949","journal-title":"Comput Phys Commun"},{"key":"679_CR129","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1090\/S0273-0979-09-01249-X","volume":"46","author":"G Carlsson","year":"2009","unstructured":"Carlsson G (2009) Topology and data. Bull Am Math Soc 46:255\u2013308","journal-title":"Bull Am Math Soc"},{"key":"679_CR130","doi-asserted-by":"publisher","first-page":"1669","DOI":"10.1021\/ci900115y","volume":"49","author":"V Consonni","year":"2009","unstructured":"Consonni V, Ballabio D, Todeschini R (2009) Comments on the definition of the q 2 parameter for qsar validation. J Chem Inf Model 49:1669\u20131678","journal-title":"J Chem Inf Model"},{"key":"679_CR131","doi-asserted-by":"publisher","DOI":"10.1002\/9781119039402","volume-title":"2D and 3D Image Analysis by Moments","author":"J Flusser","year":"2016","unstructured":"Flusser J, Suk T, Zitov\u00e1 B (2016) 2D and 3D Image Analysis by Moments. John Wiley & Sons, Hoboken"},{"key":"679_CR132","doi-asserted-by":"publisher","first-page":"3558","DOI":"10.1063\/1.446210","volume":"79","author":"P Pfeifer","year":"1983","unstructured":"Pfeifer P, Avnir D (1983) Chemistry in noninteger dimensions between two and three. I. Fractal theory of heterogeneous surfaces. J. Chem. Phys. 79:3558\u20133565","journal-title":"J. Chem. Phys."},{"key":"679_CR133","doi-asserted-by":"publisher","first-page":"7262","DOI":"10.1021\/acs.jmedchem.2c00254","volume":"65","author":"Z Cai","year":"2022","unstructured":"Cai Z, Zafferani M, Akande OM, Hargrove AE (2022) Quantitative structure - activity relationship (qsar) study predicts small-molecule binding to rna structure. J Med Chem 65:7262\u20137277","journal-title":"J Med Chem"},{"key":"679_CR134","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13321-025-00948-y","volume":"17","author":"J Wellnitz","year":"2025","unstructured":"Wellnitz J, Jain S, Hochuli JE, Maxfield T, Muratov EN, Tropsha A, Zakharov AV (2025) One size does not fit all: revising traditional paradigms for assessing accuracy of qsar models used for virtual screening. J Cheminform 17:7","journal-title":"J Cheminform"},{"key":"679_CR135","doi-asserted-by":"crossref","unstructured":"Schultz TW, Diderich R, Kuseva CD, Mekenyan OG (2018) The OECD QSAR toolbox starts its second decade. In: Computational Toxicology: Methods and Protocols, pp 55\u201377. Springer, New York","DOI":"10.1007\/978-1-4939-7899-1_2"},{"key":"679_CR136","doi-asserted-by":"publisher","first-page":"343","DOI":"10.3389\/fchem.2020.00343","volume":"8","author":"EHB Maia","year":"2020","unstructured":"Maia EHB, Assis LC, De Oliveira TA, Da Silva AM, Taranto AG (2020) Structure-based virtual screening: from classical to artificial intelligence. Front Chem 8:343","journal-title":"Front Chem"},{"key":"679_CR137","doi-asserted-by":"publisher","first-page":"18477","DOI":"10.1073\/pnas.2000585117","volume":"117","author":"YO Adeshina","year":"2020","unstructured":"Adeshina YO, Deeds EJ, Karanicolas J (2020) Machine learning classification can reduce false positives in structure-based virtual screening. Proc Natl Acad Sci USA 117:18477\u201318488","journal-title":"Proc Natl Acad Sci USA"},{"key":"679_CR138","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1021\/ci100253r","volume":"50","author":"I Sushko","year":"2010","unstructured":"Sushko I, Novotarskyi S, K\u00f6rner R, Pandey AK, Cherkasov A, Li J, Gramatica P, Hansen K, Schroeter T, M\u00fcller KR, Xi L, Liu H, Yao X, \u00d6berg T, Horsey F, Patlewicz G, Tropsha A, Tetko IV (2010) Applicability domains for classification problems: benchmarking of distance to models for ames mutagenicity set. J Chem Inf Model 50:2094\u20132111","journal-title":"J Chem Inf Model"},{"key":"679_CR139","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","author":"K Yang","year":"2019","unstructured":"Yang K, Swanson K, Jin W, Coley C, Eiden P, Gao H, Gomes-Bombarelli A, Hirzel T, Hoover E, Leavitt T, Liaw P, Mehta S, Miyazaki S, Shelley E, Srinivasan A, Verderame L, Wang D, Weiss D, Barzilay R (2019) Analyzing learned molecular representations for property prediction. J Chem Inf Model 59:3370\u20133388","journal-title":"J Chem Inf Model"},{"key":"679_CR140","doi-asserted-by":"publisher","first-page":"2562","DOI":"10.1021\/acs.jcim.5b00654","volume":"55","author":"S Riniker","year":"2015","unstructured":"Riniker S, Landrum GA (2015) Better informed distance geometry: using what we know to improve conformation generation. J Chem Inf Model 55:2562\u20132574","journal-title":"J Chem Inf Model"},{"key":"679_CR141","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco D, Jurman G (2020) The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genomics 21:6","journal-title":"BMC Genomics"},{"key":"679_CR142","doi-asserted-by":"publisher","first-page":"0177678","DOI":"10.1371\/journal.pone.0177678","volume":"12","author":"S Boughorbel","year":"2017","unstructured":"Boughorbel S, Jarray F, El-Anbari M (2017) Optimal classifier for imbalanced data using matthews correlation coefficient metric. PLoS ONE 12:0177678","journal-title":"PLoS ONE"},{"key":"679_CR143","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.patcog.2019.02.023","volume":"91","author":"A Luque","year":"2019","unstructured":"Luque A, Carrasco A, Mart\u00edn A, Las Heras A (2019) The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognit 91:216\u2013231","journal-title":"Pattern Recognit"},{"key":"679_CR144","unstructured":"Powers DM (2020) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. Preprint at https:\/\/arxiv.org\/abs\/2010.16061"},{"key":"679_CR145","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s10822-008-9170-2","volume":"22","author":"A Nicholls","year":"2008","unstructured":"Nicholls A (2008) What do we know and when do we know it? J Comput Aided Mol Des 22:239\u2013255","journal-title":"J Comput Aided Mol Des"},{"key":"679_CR146","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1021\/ci600426e","volume":"47","author":"JF Truchon","year":"2007","unstructured":"Truchon JF, Bayly CI (2007) Evaluating virtual screening methods: good and bad metrics for the \u201cearly recognition\u2019\u2019 problem. J Chem Inf Model 47:488\u2013508","journal-title":"J Chem Inf Model"},{"key":"679_CR147","doi-asserted-by":"publisher","first-page":"3494","DOI":"10.2174\/138161207782794257","volume":"13","author":"A Tropsha","year":"2007","unstructured":"Tropsha A, Golbraikh A (2007) Predictive qsar modeling workflow, model applicability domains, and virtual screening. Curr Pharm Des 13:3494\u20133504","journal-title":"Curr Pharm Des"},{"key":"679_CR148","unstructured":"Westgard JF (2012) Mean, standard deviation, and coefficient of variation. Westgard Workshop. http:\/\/www.westgard.com\/lesson34.htm. Accessed 29 July 2025"},{"key":"679_CR149","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115\u2013118","journal-title":"Nature"},{"key":"679_CR150","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","volume":"577","author":"SM McKinney","year":"2020","unstructured":"McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, Back T, Chesus M, Corrado GS, Darzi A, Etemadi M, Garcia-Vicente F, Gilbert FJ, Halling-Brown M, Hassabis D, Jansen S, Karthikesalingam A, Kelly CJ, King D, Ledsam JR, Melnick D, Mostofi H, Peng L, Reicher JJ, Romera-Paredes B, Sidebottom R, Suleyman M, Tse D, Young KC, De Fauw J, Shetty S (2020) International evaluation of an ai system for breast cancer screening. Nature 577:89\u201394","journal-title":"Nature"},{"key":"679_CR151","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2024.105278","volume":"256","author":"J Li","year":"2025","unstructured":"Li J, Zhao T, Yang Q, Du S, Xu L (2025) A review of quantitative structure-activity relationship: the development and current status of data sets, molecular descriptors and mathematical models. Chemom Intell Lab Syst 256:105278","journal-title":"Chemom Intell Lab Syst"},{"key":"679_CR152","doi-asserted-by":"publisher","first-page":"2100165","DOI":"10.1002\/minf.202100165","volume":"41","author":"S Schmidt","year":"2022","unstructured":"Schmidt S, Schindler M, Eriksson L (2022) Block?wise exploration of molecular descriptors with multi?block orthogonal component analysis (moca). Mol Inform 41:2100165","journal-title":"Mol Inform"},{"key":"679_CR153","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1021\/acs.jcim.6b00591","volume":"56","author":"RP Sheridan","year":"2016","unstructured":"Sheridan RP, Wang WM, Liaw A, Ma J, Gifford EM (2016) Extreme gradient boosting as a method for quantitative structure - activity relationships. J Chem Inf Model 56:2353\u20132360","journal-title":"J Chem Inf Model"},{"key":"679_CR154","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12863-018-0633-8","volume":"19","author":"BF Darst","year":"2018","unstructured":"Darst BF, Malecki KC, Engelman CD (2018) Using recursive feature elimination in random forest to account for correlated variables in high dimensional data. BMC Genet 19:65","journal-title":"BMC Genet"},{"key":"679_CR155","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1016\/j.drudis.2016.06.013","volume":"21","author":"AU Khan","year":"2016","unstructured":"Khan AU (2016) Descriptors and their selection methods in qsar analysis: paradigm for drug design. Drug Discov Today 21:1291\u20131302","journal-title":"Drug Discov Today"},{"key":"679_CR156","unstructured":"Wang C (2023) Calibration in deep learning: A survey of the state-of-the-art. Preprint at https:\/\/arxiv.org\/abs\/2308.01222"},{"key":"679_CR157","first-page":"1","volume":"1","author":"MI Jordan","year":"2019","unstructured":"Jordan MI (2019) Artificial intelligence-the revolution hasn\u2019t happened yet. Harv Data Sci Rev 1:1\u20139","journal-title":"Harv Data Sci Rev"},{"key":"679_CR158","doi-asserted-by":"publisher","first-page":"3262","DOI":"10.1038\/s41467-025-58503-0","volume":"16","author":"LY Chen","year":"2025","unstructured":"Chen LY, Li YP (2025) Uncertainty quantification with graph neural networks for efficient molecular design. Nat Commun 16:3262","journal-title":"Nat Commun"},{"key":"679_CR159","first-page":"84246","volume":"37","author":"F Futami","year":"2024","unstructured":"Futami F, Fujisawa M (2024) Information-theoretic generalization analysis for expected calibration error. Adv Neural Inf Process Syst 37:84246\u201384297","journal-title":"Adv Neural Inf Process Syst"},{"key":"679_CR160","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1039\/D2DD00146B","volume":"2","author":"G Tom","year":"2023","unstructured":"Tom G, Hickman RJ, Zinzuwadia A, Mohajeri A, Sanchez-Lengeling B, Aspuru-Guzik A (2023) Calibration and generalizability of probabilistic models on low-data chemical datasets with dionysus. Digit Discov 2:759\u2013774","journal-title":"Digit Discov"},{"key":"679_CR161","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1002\/sim.5328","volume":"31","author":"OV Demler","year":"2012","unstructured":"Demler OV, Pencina MJ, D\u2019Agostino RB Sr (2012) Misuse of delong test to compare aucs for nested models. Stat Med 31:2577\u20132587","journal-title":"Stat Med"},{"key":"679_CR162","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1017\/S1481803500013336","volume":"8","author":"J Fan","year":"2006","unstructured":"Fan J, Upadhye S, Worster A (2006) Understanding receiver operating characteristic (roc) curves. Can J Emerg Med 8:19\u201320","journal-title":"Can J Emerg Med"},{"key":"679_CR163","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s41524-025-01573-x","volume":"11","author":"LE Schultz","year":"2025","unstructured":"Schultz LE, Wang Y, Jacobs R, Morgan D (2025) A general approach for determining applicability domain of machine learning models. Npj Comput. Mater. 11:95","journal-title":"Npj Comput. Mater."},{"key":"679_CR164","doi-asserted-by":"publisher","DOI":"10.1201\/9781003587774","volume-title":"Ensemble Methods: Foundations and Algorithms","author":"ZH Zhou","year":"2025","unstructured":"Zhou ZH (2025) Ensemble Methods: Foundations and Algorithms. CRC Press, Boca Raton"},{"key":"679_CR165","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10916-022-01807-1","volume":"46","author":"T Roland","year":"2022","unstructured":"Roland T, B\u00f6ck C, Tschoellitsch T, Maletzky A, Hochreiter S, Meier J, Klambauer G (2022) Domain shifts in machine learning based covid-19 diagnosis from blood tests. J Med Syst 46:23","journal-title":"J Med Syst"},{"key":"679_CR166","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s13321-019-0391-2","volume":"11","author":"M Glavatskikh","year":"2019","unstructured":"Glavatskikh M, Leguy J, Hunault G, Cauchy T, Da Mota B (2019) Dataset\u2019s chemical diversity limits the generalizability of machine learning predictions. J Cheminform 11:69","journal-title":"J Cheminform"}],"container-title":["Journal of Computer-Aided Molecular Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-025-00679-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10822-025-00679-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-025-00679-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:02:13Z","timestamp":1764403333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10822-025-00679-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":166,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["679"],"URL":"https:\/\/doi.org\/10.1007\/s10822-025-00679-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7286125\/v1","asserted-by":"object"}]},"ISSN":["0920-654X","1573-4951"],"issn-type":[{"value":"0920-654X","type":"print"},{"value":"1573-4951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"4 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"98"}}