prikaz prve stranice dokumenta Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development
  Download
PDF 561.81 KB
Scientific paper - Original scientific paper
Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development
International Journal of Computer Aided Engineering and Technology, 19 (2006), 12; 835-855. https://doi.org/10.1007/s10822-005-9022-2
Debeljak, Željko; Marohnić, Viktor; Srečnik, Goran; Medić-Šarić, Marica

Cite this document

Debeljak, Ž., Marohnić, V., Srečnik, G. & Medić Šarić, M. (2006). Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development. International Journal of Computer Aided Engineering and Technology, 19. (12), 835-855. doi: 10.1007/s10822-005-9022-2

Debeljak, Željko, et al. "Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development." International Journal of Computer Aided Engineering and Technology, vol. 19, no. 12, 2006, pp. 835-855. https://doi.org/10.1007/s10822-005-9022-2

Debeljak, Željko, Viktor Marohnić, Goran Srečnik and Marica Medić Šarić. "Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development." International Journal of Computer Aided Engineering and Technology 19, no. 12 (2006): 835-855. https://doi.org/10.1007/s10822-005-9022-2

Debeljak, Ž., et al. (2006) 'Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development', International Journal of Computer Aided Engineering and Technology, 19(12), pp. 835-855. doi: 10.1007/s10822-005-9022-2

Debeljak Ž, Marohnić V, Srečnik G, Medić Šarić M. Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development. International Journal of Computer Aided Engineering and Technology [Internet]. 2006 [cited 2024 October 26];19(12):835-855. doi: 10.1007/s10822-005-9022-2

Ž. Debeljak, V. Marohnić, G. Srečnik and M. Medić Šarić, "Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development", International Journal of Computer Aided Engineering and Technology, vol. 19, no. 12, pp. 835-855, 2006. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:239:165922. [Accessed: 26 October 2024]

Please login to the repository to save this object to your list.
Metadata
Title (english)Novel Approach to Evolutionary Neural Network Based Descriptor Selection and QSAR Model Development
AuthorŽeljko Debeljak
MBZ: 296571
AuthorViktor Marohnić
AuthorGoran Srečnik
AuthorMarica Medić-Šarić
MBZ: 74265
Author's institution(Clinical hospital center Osijek)
Author's institutionUniversity of Zagreb
Faculty of Pharmacy and Biochemistry
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Clinical Medical Sciences
Neurology
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Pharmacy
Medical Biochemistry
Abstract (english)
Capability of evolutionary neural network (ENN) based QSAR approach to direct the descriptor selection process towards stable descriptor subset (DS) composition characterized by acceptable generalization, as well as the influence of description stability on QSAR model interpretation have been examined. In order to analyze the DS stability and QSAR model generalization properties multiple random dataset partitions into training and test set were made. Acceptability criteria proposed by Golbraikh et al. [J. Comput.-Aided Mol. Des., 17 (2003) 241] have been chosen for selection of highly predictive QSAR models from a set of all models produced by ENN for each dataset splitting. All QSAR models that pass Golbraikh's filter generated by ENN for each dataset partition were collected. Two final DS forming principles were compared. Standard principle is based on selection of descriptors characterized by highest frequencies among all descriptors that appear in the pool [J. Chem. Inf. Comput. Sci., 43 (2003) 949]. Search across the model pool for DS that are stable against multiple dataset subsampling i.e. universal DS solutions is the basis of novel approach. Based on described principles benzodiazepine QSAR has been proposed and evaluated against results reported by others in terms of final DS composition and model predictive performance.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleInternational Journal of Computer Aided Engineering and Technology
Numberingvol. 19, no. 12, pp. 835-855
p-ISSN1757-2657
e-ISSN1757-2665
DOIhttps://doi.org/10.1007/s10822-005-9022-2
URN:NBNurn:nbn:hr:239:165922
Publication2006
Document URLhttps://link.springer.com/article/10.1007/s10822-005-9022-2
Type of resourceText
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-05-14 08:57:07