Raevsky, O.A. (1999) Molecular structure descriptors in the computer-aided design of biologically active compounds. Russ. Chem. Rev., 68, 505-524. [Pg.1147]

Generation and storage of molecular structure descriptors from the topological or geometrical representations of the structures. [Pg.110]

X. Li and 1. Gutman, Mathematical aspects of Randi6-type molecular structure descriptor. University of Kragujevac, Kragujevac, Serbia, 2006. [Pg.153]

Mdosavljevic, S. and Radenkovic, S. (2003a) Graph energy a useful molecular structure-descriptor. Indian J. Chem., 42, 1309—1311. [Pg.1057]

I. Gutman, Preface to a special issue entitled Graph-based molecular structure-descriptors— theory and applications, Ind. J. Chem. 42A (2003) 1197-1198. [Pg.170]

Flora, S. de, Koch, R. Strobel, K. and Nagel, M. (1985) A model based on molecular structure descriptors for predicting mutagenicity of organic compounds. Toxicol Environ. Chem., 10, 157-70. [Pg.235]

Toropoy A.A., Gutman, I. and Furtula, B. (2005) Graph of atomic orbitals and molecular structure descriptors based on it. J. Serb. Chem. Soc., 70, 669-674. [Pg.1184]

Descriptor Generation. The most Important part of SAR studies is the development of molecular structure descriptors. [Pg.150]

Pattern Recognition Analysis. Once each compound in a data set has been represented by a set of molecular structure descriptors, then the analysis phase of the SAR study begins. [Pg.152]

B. Lucid, S. Nikolid, N. Trinajstid, B. Zhou, and S. Ivanis Turk, Sum-connectivity index, in Novel molecular structure descriptors—Theory and application I, ed. I. Gutman and B. Furtula, University of Kragujevac, Kragujevac, Serbia, 2010, pp. 101-136. [Pg.47]

Last but not least, we may mention considerable activity in some mathematical circles interested in mathematical properties of molecular descriptors. Mathematical Aspects of Randic-Type Molecular Structure Descriptors is the title of one of two books on the mathematical properties of the connectivity index X, in which selected papers on these topics were presented [21,22]. Clearly, the connectivity index represents one successfully solved problem in the search for useful mathematical molecular descriptors. But a question can be raised Is there anything unsolved relating to the topic of the connectivity index Is there something that can still be improved We will come up with some answers to these questions later. [Pg.156]

These results show that pattern recognition can be used as an effective tool to characterize polycyclic aromatic hydrocarbon carcinogens. Using a set of only 28 molecular structure descriptors, linear discriminants can be found to correctly dichotomize 191 out of 200 randomly selected PAH s. This same set of 28 descriptors supports a linear discriminant function that has an average predictive ability of over ninety percent when subjected to randomized predictive ability tests. [Pg.122]

Clearly, the constant can be included into threshold value B, so that the function /o(C) = 1 is not necessary. We must stress that in such form the probabilistic approach has no tuned parameters at all. Some tuning of naive Bayes classifier can be performed by selection of the molecular structure descriptors [or /(C)] set. This is a wonderful feature in contrast to QSAR methods, especially to Artificial Neural Networks. [Pg.194]

© 2019 chempedia.info