Prediction of Complement-Inhibitory Activity of Benzamidines Using Topological and Geometric Parameters

Basak, Subhash C.; Gute, Brian D.; Ghatak, Shibnath

doi:10.1021/ci9800716

Cited by 24 publications

(14 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently used topological descriptors are capable of representing molecular shape, connectivity, and some level of molecular flexibility (23,(60)(61)(62). However, because of the limited coverage of the number of bond links in a heteroatom loop, these descriptors are not yet capable of describing the special features of a complex multiring structure that contains multiple heteroatoms.…”

Section: Relevance Of Selected Features To Genotoxicty Studymentioning

confidence: 99%

Prediction of Genotoxicity of Chemical Compounds by Statistical Learning Methods

Ung

Yap

et al. 2005

Chem. Res. Toxicol.

View full text Add to dashboard Cite

Various toxicological profiles, such as genotoxic potential, need to be studied in drug discovery processes and submitted to the drug regulatory authorities for drug safety evaluation. As part of the effort for developing low cost and efficient adverse drug reaction testing tools, several statistical learning methods have been used for developing genotoxicity prediction systems with an accuracy of up to 73.8% for genotoxic (GT+) and 92.8% for nongenotoxic (GT-) agents. These systems have been developed and tested by using less than 400 known GT+ and GTagents, which is significantly less in number and diversity than the 860 GT+ and GT-agents known at present. There is a need to examine if a similar level of accuracy can be achieved for the more diverse set of molecules and to evaluate other statistical learning methods not yet applied to genotoxicity prediction. This work is intended for testing several statistical learning methods by using 860 GT+ and GT-agents, which include support vector machines (SVM), probabilistic neural network (PNN), k-nearest neighbor (k-NN), and C4.5 decision tree (DT). A feature selection method, recursive feature elimination, is used for selecting molecular descriptors relevant to genotoxicity study. The overall accuracies of SVM, k-NN, and PNN are comparable to and those of DT lower than the results from earlier studies, with SVM giving the highest accuracies of 77.8% for GT+ and 92.7% for GT-agents. Our study suggests that statistical learning methods, particularly SVM, k-NN, and PNN, are useful for facilitating the prediction of genotoxic potential of a diverse set of molecules.

show abstract

Section: Relevance Of Selected Features To Genotoxicty Studymentioning

confidence: 99%

Prediction of Genotoxicity of Chemical Compounds by Statistical Learning Methods

Ung

Yap

et al. 2005

Chem. Res. Toxicol.

View full text Add to dashboard Cite

show abstract

“…In fact, one of the present author made numerous studies on the large set of compounds using diverse types of molecular descriptors. [40][41][42][43][44][45] Concerning "overfitting", which is clearly undesirable, we would like to point out that this is out of the question when one uses a single descriptor. Overfitting is a danger in multiple regression analysis when one uses too many descriptors and has too few data.…”

Section: Discussionmentioning

confidence: 99%

Construction of High-Quality Structure−Property−Activity Regressions: The Boiling Points of Sulfides

Randić

Basak

2000

J. Chem. Inf. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

Instead of using the standard molecular descriptors (topological indices) for regression analysis, which are numerically fully determined once a molecule is selected, we outline the use of variable molecular descriptors that are modified during the search for the best regression. The approach is illustrated using boiling points of sulfides. We have transformed the connectivity index 1chi into a function of two variables (x, y) which differentiate carbon and sulfur atoms. The optimal values of the variables (x, y) were determined by minimizing the standard error of the regression. With the values x = +0.25 and y = -0.95 for carbon and sulfur, respectively, we have obtained a regression based on a single descriptor and a standard error of 1.8 degrees C. With elimination of two outliers (having a deviation of about 4 degrees C) the standard error is reduced to a remarkable 1.3 degrees C.

show abstract

“…We have recently formulated a hierarchical QSAR (HiQSAR) approach where parameters of increasing chemical or computational complexity are used in a graduated manner. In particular, we have used topostructural (TS), topochemical (TC), geometrical (3-D), and quantum chemical (semiempirical as well as ab initio) parameters in QSAR model development for various properties including the complement inhibitory properties of benzamidines (Basak et al, 1999), the mutagenicity of a set of 95 aromatic amines (Basak et al, 1998), the skin penetration profiles for 60 polycyclic aromatic hydrocarbons (Gute et al, 1999), and the toxicity of a group of 55 halocarbons to aspergillus niger (Basak et al, 2003). In this paper we have used a variant of the HiQSAR approach to develop predictive models for the toxicity of a group of 20 halocarbons to primary hepatocytes.…”

Section: Introductionmentioning

confidence: 99%

Prediction of halocarbon toxicity from structure: a hierarchical QSAR approach

Gute¹,

Balasubramanian²,

Geiss³

et al. 2004

Environmental Toxicology and Pharmacology

View full text Add to dashboard Cite

Mathematical structural invariants and quantum theoretical descriptors have been used extensively in quantitative structure-activity relationships (QSARs) for the estimation of pharmaceutical activities, biological properties, physicochemical properties, and the toxicities of chemicals. Recently our research team has explored the relative importance of various levels of chemodescriptors, i.e. topostructural (TS), topochemical (TC), geometrical (3D), and quantum theoretical descriptors, in property estimation. This study examines the contribution of chemodescriptors ranging from topostructural to quantum theoretic calculations, up to the Gaussian STO-3G level, in predicting the results of six indicators of oxidative stress for a set of 20 halocarbons. Using quantum theoretical calculations in this study is of particular interest as molecular energetics is related to the likelihood of electron attachment and free radical formation, the mechanism of toxicity for these chemicals and should aid in modeling their potential for oxidative stress.

show abstract

Prediction of Complement-Inhibitory Activity of Benzamidines Using Topological and Geometric Parameters

Cited by 24 publications

References 42 publications

Prediction of Genotoxicity of Chemical Compounds by Statistical Learning Methods

Prediction of Genotoxicity of Chemical Compounds by Statistical Learning Methods

Construction of High-Quality Structure−Property−Activity Regressions: The Boiling Points of Sulfides

Prediction of halocarbon toxicity from structure: a hierarchical QSAR approach

Contact Info

Product

Resources

About