Non-linear assessment of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives – Chemometric guidelines for further syntheses

Kоvаčеvić, Strаhinjа; Podunavac‐Kuzmanović, Sanja O.; Jevrić, Lidija R.; Djurendić, Evgenija A.; Ajduković, Jovana J.

doi:10.1016/j.ejps.2014.05.031

Cited by 21 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The partial least square regression (PLSR) with variable importance in projection (VIP) approach was applied in order to eliminate the variables with VIP values lower than a user-defined threshold (Mehmood, Hovde Liland, Snipen, & Saebø, 2012). In this paper, the threshold of 0.3 is used as an elimination criterion (Kovačević, Podunavac-Kumanović, Jevrić, Djurendić, & Ajduković, 2014).…”

Section: Chemometric Analysismentioning

confidence: 99%

Artificial neural network modeling of the antioxidant activity of lettuce submitted to different postharvest conditions

Banjac

Kоvаčеvić

Jevrić

et al. 2019

J Food Process Preserv

Self Cite

View full text Add to dashboard Cite

Using novel ebb and flow hydroponic system lettuce (Lactuca sativa L.) samples were grown and then stored under different postharvest conditions (greenhouse with a cube, refrigerator with a cube, and refrigerator without a cube). The effect of the postharvest conditions on bioactive compounds profile and antioxidant activity was studied. All samples were subjected to the bioactive compounds composition analysis as well as to the antioxidant activity determination in order to reveal how the postharvest conditions affect them. The experimental data were used for the antioxidant activity modeling by artificial neural network (ANN) approach. The antioxidant activity was determined by DPPH assay and expressed as IC50. According to the standard statistical parameters, comparison of the experimentally observed and predicted data, and residuals analysis, generated ANNs could be used for the prediction of the antioxidant activity. Practical applications Lettuce (Lactuca sativa L.) samples were grown using novel Ebb and Flow hydroponic system. Different postharvest conditions were used for samples storage. Generated models for the prediction of antioxidant activity were obtained using artificial neural network (ANN) modeling.

show abstract

Section: Chemometric Analysismentioning

confidence: 99%

Artificial neural network modeling of the antioxidant activity of lettuce submitted to different postharvest conditions

Banjac

Kоvаčеvić

Jevrić

et al. 2019

J Food Process Preserv

Self Cite

View full text Add to dashboard Cite

show abstract

“…ANNs are widely applied non-linear method in chemometric modeling of complex relationships between variables [69][70][71]. ANNs consist of artificial neurons which implement the essence of biological neurons.…”

Section: Chemometric Methods and Model Validationmentioning

confidence: 99%

Computational modeling of ionic liquids density by multivariate chemometrics

Kоvаčеvić

Podunavac‐Kuzmanović

Zec

et al. 2016

Journal of Molecular Liquids

View full text Add to dashboard Cite

“…[26] Selection of the number of hidden layers and the number of neurons is achieved based on trial-and-error approach, and these numbers are changing during training process until the satisfactory behavior of the ANN is obtained. [27] The processing of the information between the layers is conducted through an activation or transfer function. [28] This nonlinear function can be sigmoid or hyperbolic.…”

Section: Chemometric Toolsmentioning

confidence: 99%

Linear and Nonlinear Structure-Retention Relationship Analysis of Different Classes of Pesticides Isolated From Groundwater

Kоvаčеvić

Podunavac‐Kuzmanović

Jevrić

2015

Journal of Liquid Chromatography & Related Technologies

Self Cite

View full text Add to dashboard Cite

The present article gives an insight into the linear and nonlinear relationships between the retention behavior in reversed-phase high performance liquid chromatography (RP-HPLC) of several classes of pesticides isolated from groundwater, and their in silico physicochemical, topological and lipophilicity molecular descriptors. The quantitative structure-retention relationship (QSRR) chemometric approach was applied for this purpose on a large set of compounds (77 pesticides). The selection of the most appropriate molecular descriptors was achieved by stepwise selection procedure coupled with partial least squares method and the variance inflation in projection parameter (SS-PLS-VIP). QSRR included the linear regression (LR), multiple linear regession (MLR), and artificial neural networks regression (ANN-R). In order to select the optimal QSRR model, statistical validation parameters were used. Additionally, a relatively new chemometric method called sum of ranking differences (SRD) was applied in order to select the optimal regression model. The obtained results showed that certain models can successfully be used for precise prediction of the retention time of the studied compounds.

show abstract

Non-linear assessment of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives – Chemometric guidelines for further syntheses

Cited by 21 publications

References 33 publications

Artificial neural network modeling of the antioxidant activity of lettuce submitted to different postharvest conditions

Artificial neural network modeling of the antioxidant activity of lettuce submitted to different postharvest conditions

Computational modeling of ionic liquids density by multivariate chemometrics

Linear and Nonlinear Structure-Retention Relationship Analysis of Different Classes of Pesticides Isolated From Groundwater

Contact Info

Product

Resources

About