Institute za hemija

Skopje, Macedonia

Institute za hemija

Skopje, Macedonia
SEARCH FILTERS
Time filter
Source Type

Eric S.,University of Belgrade | Kalinic M.,University of Belgrade | Popovic A.,University of Belgrade | Zloh M.,University of London | Kuzmanovski I.,Institute Za Hemija
International Journal of Pharmaceutics | Year: 2012

In this work, we present a novel approach for the development of models for prediction of aqueous solubility, based on the implementation of an algorithm for the automatic adjustment of descriptor's relative importance (AARI) in counter-propagation artificial neural networks (CPANN). Using this approach, the interpretability of the models based on artificial neural networks, which are traditionally considered as "black box" models, was significantly improved. For the development of the model, a data set consisting of 374 diverse drug-like molecules, divided into training (n = 280) and test (n = 94) sets using self-organizing maps, was used. Heuristic method was applied in preselecting a small number of the most significant descriptors to serve as inputs for CPANN training. The performances of the final model based on 7 descriptors for prediction of solubility were satisfactory for both training (RMSEPtrain = 0.668) and test set (RMSEPtest = 0.679). The model was found to be a highly interpretable in terms of solubility, as well as rationalizing structural features that could have an impact on the solubility of the compounds investigated. Therefore, the proposed approach can significantly enhance model usability by giving guidance for structural modifications of compounds with the aim of improving solubility in the early phase of drug discovery. © 2012 Elsevier B.V. All rights reserved.


Le Roux A.,CNRS Laboratory of Design and Application of Bioactive Molecules | Le Roux A.,University of Strasbourg | Kuzmanovski I.,Slovenian National Institute of Chemistry | Kuzmanovski I.,Institute Za Hemija | And 8 more authors.
Journal of Chemical Information and Modeling | Year: 2011

Antioxidative activity expressed as protection of thymidine has been investigated for a set of 30 pulvinic acid derivatives. A combination of in vitro testing and in silico modeling was used for synthesis of new potential antioxidants. Experimental data obtained from a primary screening test based on oxidation under Fenton conditions and by an UV exposure followed by back-titration of the amount of thymidine remaining intact have been used to develop a computer model for prediction of antioxidant activity. Structural descriptors of 30 compounds tested for their thymidine protection activity were calculated in order to define the structure-property relationship and to construct predictive models. Due to the potential nonlinearity, the counter-propagation artificial neural networks were assessed for modeling of the antioxidant activity of these compounds. The optimized model was challenged with 80 new molecules not present in the initial training set. The compounds with the highest predicted antioxidant activity were considered for synthesis. Among the predicted structures, some coumarine derivatives appeared to be especially interesting. One of them was synthesized and tested on in vitro assays and showed some antioxidant and radioprotective activities, which turned out as a promising lead toward more potent antioxidants. © 2011 American Chemical Society.


Stojic N.,Institute za Hemija | Eric S.,University of Belgrade | Kuzmanovski I.,Institute za Hemija
Journal of Molecular Graphics and Modelling | Year: 2010

In this work, a novel algorithm for optimization of counter-propagation artificial neural networks has been used for development of quantitative structure-activity relationships model for prediction of the estrogenic activity of endocrine-disrupting chemicals. The search for the best model was performed using genetic algorithms. Genetic algorithms were used not only for selection of the most suitable descriptors for modeling, but also for automatic adjustment of their relative importance. Using our recently developed algorithm for automatic adjustment of the relative importance of the input variables, we have developed simple models with very good generalization performances using only few interpretable descriptors. One of the developed models is in details discussed in this article. The simplicity of the chosen descriptors and their relative importance for this model helped us in performing a detailed data exploratory analysis which gave us an insight in the structural features required for the activity of the estrogenic endocrine-disrupting chemicals. © 2010 Elsevier Inc.


Koleva V.,Bulgarian Academy of Science | Stefov V.,Institute Za Hemija | Najdoski M.,Institute Za Hemija | Cahil A.,Institute Za Hemija
Vibrational Spectroscopy | Year: 2012

The infrared and Raman spectra of protiated and deuterated crystalline Co(H 2PO 4) 2·2H 2O are presented and discussed with respect to the internal vibrations of the H 2PO 4 - ions, the OH stretching vibrations and the water librations. A detailed interpretation of the vibrational spectra is proposed on the basis of the isotopic and temperature shifts of the vibrational bands. The mutual exclusion rule is obeyed for all vibrations under consideration. Strong vibrational couplings are established between the PO 4 stretching modes and POH bending modes, as well as between the PO 4 bending modes and the water librations. The values of the correlation splittings A-B and g-u of the γ(OH) vibrations evidence the significant intra- and inter-chain interactions between the H 2PO 4 - ions. The four O⋯O hydrogen bonds are discussed with respect to their strengths and the multi band behaviour of the OH stretching modes of the respective POH groups. © 2012 Elsevier B.V.


Koleva V.,Bulgarian Academy of Science | Stefov V.,Institute za Hemija
Vibrational Spectroscopy | Year: 2013

The infrared, far-infrared and Raman spectra of acid phosphate salts of the type M(H2PO4)2·2H2O (M = Mg, Mn, Co, Ni, Zn, Cd) in both protiated and deuterated forms have been recorded at ambient and liquid nitrogen temperature. The vibrational spectra have been interpreted with respect to the vibrations of the H2PO4- ions. Strong vibrational couplings are established between the PO4 stretching modes and POH bending modes as well as between the PO4 bending modes and the water librations. The magnitude of the correlation field splittings A-B and g-u of the vibrational modes have been estimated. The influence of the metal ions on the frequencies of the stretching vibrations of the P - O bonds has been discussed and some trends regarding the frequency variation within the M(H2PO4)2·2H 2O series have been found. It has been established that the extent of the energetic distortions of H2PO4- with respect to the P - O bond lengths revealed by the spectroscopic data correlates with the extent of the geometric distortion shown by the structural data. © 2012 Elsevier B.V. All rights reserved.


Soptrajanov B.,Institute Za Hemija | Cahil A.,Institute Za Hemija | Najdoski M.,Institute Za Hemija | Koleva V.,Bulgarian Academy of Science | Stefov V.,Institute Za Hemija
Acta Chimica Slovenica | Year: 2011

The infrared and Raman spectra of magnesium rubidium phosphate hexahydrate MgRbPO4 6H2O and magnesium thallium phosphate hexahydrate, MgTlPO46H2O were recorded at room temperature (RT) and the boiling temperature of liquid nitrogen (LNT). To facilitate their analysis, also recorded were the spectra of partially deuterated analogues with varying content of deuterium. The effects of deuteration and those of lowering the temperature were the basis of the conclusions drawn regarding the origin of the observed bands which were assigned to vibrations which are predominantly localized in the water molecules (four crystallographically different types of such molecules exist in the structures) and those with PO43- character. It was concluded that in some cases coupling of phosphate and water vibrations is likely to take place. The appearance of the infrared spectra in the O-H stretching regions of the infrared spectra is explained as being the result of an extensive overlap of bands due to components of the fundamental stretching modes of the H2O units with a possible participation of bands due to second-order transitions. A broad band reminiscent of the B band of the well-known ABC trio characteristic of spectra of substances containing strong hydrogen bonds in their structure was found around 2400 cm-1 in the infrared spectra of the two studied compounds.


Stojkovic G.,Institute za hemija | Novic M.,Slovenian National Institute of Chemistry | Kuzmanovski I.,Institute za hemija
Chemometrics and Intelligent Laboratory Systems | Year: 2010

In this work counter-propagation artificial neural networks (CPANN) were used as a tool for development of interpretable quantitative structure-property relationship (QSPR) models for prediction of pKBH+ values of a series of amides. The methodology used here is based on our recently developed algorithm for automatic adjustment of the relative importance of the input variables for training of the CPANN. Using this novel algorithm we were able to develop several simple QSPR models.One of the best models, discussed in details in the article, has only three interpretable descriptors: number of halogen atoms in the structure, the energy of the lowest unoccupied molecular orbital (LUMO) which reflects the electronic properties of the molecules and the average molecular weight. The final analysis of this model shows that the most responsible for modeling of the pKBH+ values is the number of the present halogen atoms in the structures. Similar relative importance has LUMO. This descriptor helps in groping of the similar substances in different part of the CPANN. While the average molecular weight, with nearly seven times smaller relative importance compared to previous two descriptors, is related to the influence of the presence of, in most of the cases, more than one halogen atom in the structures on pKBH+. Finally, the developed models have excellent generalization performances which were checked using independent test set. © 2010 Elsevier B.V.


Svonson F.,Institute Za Hemija | Soptrajanov B.,Institute Za Hemija | Pejov L.,Institute Za Hemija | Stefov V.,Institute Za Hemija
Vibrational Spectroscopy | Year: 2011

The Fourier transform infrared spectra of Cs2CaCl 4·2H2O as well as those of a series of its partially deuterated analogues were recorded at room and at liquid-nitrogen temperature (RT and LNT, respectively). The RT Raman spectra of the protiated form and of its almost completely deuterated analogue were also studied. The combined results from the analysis of the spectra were used to assign the observed bands. The mechanical anharmonicity of the OH(D) stretching and bending motions were further analyzed by computing the corresponding anharmonicity constants by several algorithms. The obtained trends in the series of structurally similar compounds were discussed. © 2010 Elsevier B.V. All rights reserved.


PubMed | Institute za Hemija
Type: Journal Article | Journal: Journal of molecular graphics & modelling | Year: 2010

In this work, a novel algorithm for optimization of counter-propagation artificial neural networks has been used for development of quantitative structure-activity relationships model for prediction of the estrogenic activity of endocrine-disrupting chemicals. The search for the best model was performed using genetic algorithms. Genetic algorithms were used not only for selection of the most suitable descriptors for modeling, but also for automatic adjustment of their relative importance. Using our recently developed algorithm for automatic adjustment of the relative importance of the input variables, we have developed simple models with very good generalization performances using only few interpretable descriptors. One of the developed models is in details discussed in this article. The simplicity of the chosen descriptors and their relative importance for this model helped us in performing a detailed data exploratory analysis which gave us an insight in the structural features required for the activity of the estrogenic endocrine-disrupting chemicals.

Loading Institute za hemija collaborators
Loading Institute za hemija collaborators