{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T01:07:20Z","timestamp":1773018440261,"version":"3.50.1"},"reference-count":21,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T00:00:00Z","timestamp":1619222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["Research program P1\u20100017 (V.D.)"],"award-info":[{"award-number":["Research program P1\u20100017 (V.D.)"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["PhD study grant for young researchers (B.B.)"],"award-info":[{"award-number":["PhD study grant for young researchers (B.B.)"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>The hepatotoxic potential of drugs is one of the main reasons why a number of drugs never reach the market or have to be withdrawn from the market. Therefore, the evaluation of the hepatotoxic potential of drugs is an important part of the drug development process. The aim of this work was to evaluate the relative abilities of different supervised self-organizing algorithms in classifying the hepatotoxic potential of drugs. Two modifications of standard counter-propagation training algorithms were proposed to achieve good separation of clusters on the self-organizing map. A series of optimizations were performed using genetic algorithm to select models developed with counter-propagation neural networks, X-Y fused networks, and the two newly proposed algorithms. The cluster separations achieved by the different algorithms were evaluated using a simple measure presented in this paper. Both proposed algorithms showed a better formation of clusters compared to the standard counter-propagation algorithm. The X-Y fused neural network confirmed its high ability to form well-separated clusters. Nevertheless, one of the proposed algorithms came close to its clustering results, which also resulted in a similar number of selected models.<\/jats:p>","DOI":"10.3390\/ijms22094443","type":"journal-article","created":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T21:49:20Z","timestamp":1619300960000},"page":"4443","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Application of Supervised SOM Algorithms in Predicting the Hepatotoxic Potential of Drugs"],"prefix":"10.3390","volume":"22","author":[{"given":"Viktor","family":"Drgan","sequence":"first","affiliation":[{"name":"Laboratory for Cheminformatics, Theory Department, National Institute of Chemistry, Hajdrihova 19, 1001 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Baj\u017eelj","sequence":"additional","affiliation":[{"name":"Laboratory for Cheminformatics, Theory Department, National Institute of Chemistry, Hajdrihova 19, 1001 Ljubljana, Slovenia"},{"name":"Biotechnical Faculty, University of Ljubljana, Jamnikarjeva 101, 1000 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0925-2312(98)00030-7","article-title":"The self-organizing map","volume":"21","author":"Kohonen","year":"1998","journal-title":"Neurocomputing"},{"key":"ref_2","first-page":"75","article-title":"A modified kohonen self-organizing map (KSOM) clustering for four categorical data","volume":"78","author":"Ahmad","year":"2016","journal-title":"J. Teknol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1021\/ci0500839","article-title":"Supervised Self-Organizing Maps in Drug Discovery. 1. Robust Behavior with Overdetermined Data Sets","volume":"45","author":"Xiao","year":"2005","journal-title":"J. Chem. Inf. Model."},{"key":"ref_4","first-page":"X1-56","article-title":"Data exploration using self-organizing maps","volume":"82","author":"Kaski","year":"1997","journal-title":"Acta Polytech. Scand. Math. Comput. Manag. Eng. Ser."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.chemolab.2006.02.003","article-title":"Supervised Kohonen networks for classification problems","volume":"83","author":"Melssen","year":"2006","journal-title":"Chemom. Intell. Lab."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"13213","DOI":"10.1007\/s00521-018-3576-0","article-title":"AMSOM: Artificial metaplasticity in SOM neural networks\u2014Application to MIT-BIH arrhythmias database","volume":"32","author":"Fombellida","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_7","first-page":"683","article-title":"Artificial Metaplasticity can Improve Artificial Neural Networks Learning","volume":"15","author":"Andina","year":"2009","journal-title":"Intell. Autom. Soft. Comput."},{"key":"ref_8","unstructured":"Lajiness, M. (1991). QSAR: Rational Approaches to the Design of Bioactive Compounds, Elsevier Science."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.1021\/ci060117s","article-title":"On Outliers and Activity Cliffs\u2014Why QSAR Often Disappoints","volume":"46","author":"Maggiora","year":"1997","journal-title":"J. Chem. Inf. Model."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"14360","DOI":"10.1021\/acsomega.9b02221","article-title":"Evolving Concept of Activity Cliffs","volume":"4","author":"Stumpfe","year":"2019","journal-title":"ACS Omega"},{"key":"ref_11","unstructured":"(2020, January 15). LiverTox: Clinical and Research Information on Drug-Induced Liver Injury [Internet]. Bethesda (MD): National Institute of Diabetes and Digestive and Kidney Diseases, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK547852\/."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1093\/nar\/gkaa971","article-title":"PubChem in 2021: New data content and improved web interfaces","volume":"49","author":"Kim","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"ref_13","unstructured":"Kode Srl (2021, April 21). Dragon (Software for Molecular Descriptor Calculation) Version 7.0.8. Available online: https:\/\/chm.kode-solutions.net."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Todeschini, R., and Consonni, V. (2000). Handbook of Molecular Descriptors, Wiley-VCH. [1st ed.].","DOI":"10.1002\/9783527613106"},{"key":"ref_15","first-page":"30","article-title":"CPANNatNIC software for counter\u2011propagation neural network to assist in read\u2011across","volume":"9","author":"Drgan","year":"2017","journal-title":"J. Chem. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0169-7439(97)00030-0","article-title":"Kohonen and counterpropagation artificial neural networks in analytical chemistry","volume":"38","author":"Zupan","year":"1997","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0169-7439(95)80022-2","article-title":"Neural networks with counter-propagation learning strategy used for modelling","volume":"27","author":"Zupan","year":"1995","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Baj\u017eelj, B., and Drgan, V. (2020). Hepatotoxicity Modeling Using Counter-Propagation Artificial Neural Networks: Handling an Imbalanced Classification Problem. Molecules, 25.","DOI":"10.3390\/molecules25030481"},{"key":"ref_19","unstructured":"Leardi, R. (2003). Nature-Inspired Methods in Chemometrics: Genetic Algorithms and Artificial Neural Networks, Elsevier."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5541","DOI":"10.1021\/jm0497141","article-title":"A comparison of methods for modeling quantitative structure-activity relationships","volume":"47","author":"Sutherland","year":"2004","journal-title":"J. Med. Chem."},{"key":"ref_21","first-page":"10","article-title":"Examining the predictive accuracy of the novel 3D N-linear algebraic molecular codifications on benchmark datasets","volume":"8","author":"Barigye","year":"2016","journal-title":"J. Chem. Inform."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/22\/9\/4443\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:52:14Z","timestamp":1760161934000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/22\/9\/4443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,24]]},"references-count":21,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["ijms22094443"],"URL":"https:\/\/doi.org\/10.3390\/ijms22094443","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,24]]}}}