Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/31255
Title: | How to rank and discriminate artificial neural networks? Case study: Prediction of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives | Authors: | Kovačević Strahinja Podunavac-Kuzmanović Sanja Jevrić Lidija Đurendić Evgenija Ajduković (Daljev) Jovana Gadžurić Slobodan Vraneš Milan |
Issue Date: | 2016 | Journal: | Journal of the Iranian Chemical Society | Abstract: | © 2015 Iranian Chemical Society. Model discrimination is still not a resolved task. The classical statistical approaches lead to different results (for the same models) and at the same time a lot of models seem to be statistically equivalent. The authors deliberately select such conditions when their algorithm is superior. Hence, it is better to apply different approaches to compare and rank the models fairly. This paper presents the application of methodology called sum of ranking differences (SRD) to rank the artificial neural network models [quantitative structure-activity relationship (QSAR) models] designed for prediction of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives toward androgen receptor negative prostate cancer cells (AR-, PC-3). The SRD method suggests the consistent models, in terms of compounds order and proximity to the golden standard, which should preferably be used in the prediction of anticancer activity of studied androstane derivatives. | URI: | https://open.uns.ac.rs/handle/123456789/31255 | ISSN: | 1735-207X | DOI: | 10.1007/s13738-015-0759-9 |
Appears in Collections: | PMF Publikacije/Publications TF Publikacije/Publications |
Show full item record
SCOPUSTM
Citations
13
checked on May 10, 2024
Page view(s)
24
Last Week
1
1
Last month
0
0
checked on May 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.