Review of “Statistical Modelling of Molecular Descriptors in QSAR/QSPR” by Matthias Dehmer, Kurt Varmuza, and Danail Bonchev
نویسنده
چکیده
Book details Statistical Modelling of Molecular Descriptors in QSAR/ QSPR. Edited by Matthias Dehmer, Kurt Varmuza, and Danail Bonchev. Wiley-Blackwell, Weinheim, Germany, 2012. Print ISBN: 978-3-527-32434-7; ePDF ISBN: 9783-527-64502-2. The book is Volume 2 of the series Quantitative and Network Biology, Series Editors: M. Dehmer and F. Emmert-Streib. Hard copy US$ 159.95, Euros 129.99; E-book US$ 126.00, Euros 114.00 The editors have selected 40 authors from 12 countries to contribute in producing a coherent account for the topics related to the book title. The 15 chapters of this book describe the current theoretical and practical results of statistical analysis and modeling of molecular descriptors. Zero-dimensional, 1-, 2-, and 3-dimensional descriptors are briefly mentioned. The most common 2D molecular descriptors are topological indices, and the use of any descriptor needs always a valid statistical confirmation that correlations are not due to chance. The first two chapters present, with some unavoidable overlap, introductory generalities about descriptors, various methods for modeling (multiple linear regression, partial least squares, neural networks, etc.) and for classification (linear discriminant analysis, k-nearest neighbor, support vector machine, etc.). Various software types are presented (e. g. Dragon, CODESSA, etc.). The following chapters deal with more restricted aspects. In the 3 chapter, after once again the software packages for descriptor calculation are reviewed, the Mold freeware is presented in detail, with a long list of all 777 descriptors. A few examples are described: in comparison with results obtained for classification (by Cerius, Dragon, and Molconn_Z) and regression models (by CODESSA), Mold is seen to provide equal or better QSAR results. The 4 chapter is authored by V.
منابع مشابه
Multivariate linear QSPR/QSAR models: Rigorous evaluation of variable selection for PLS
Basic chemometric methods for making empirical regression models for QSPR/QSAR are briefly described from a user's point of view. Emphasis is given to PLS regression, simple variable selection and a careful and cautious evaluation of the performance of PLS models by repeated double cross validation (rdCV). A demonstration example is worked out for QSPR models that predict gas chromatographic re...
متن کاملOn Entropy-Based Molecular Descriptors: Statistical Analysis of Real and Synthetic Chemical Structures
This paper presents an analysis of entropy-based molecular descriptors. Specifically, we use real chemical structures, as well as synthetic isomeric structures, and investigate properties of and among descriptors with respect to the used data set by a statistical analysis. Our numerical results provide evidence that synthetic chemical structures are notably different to real chemical structures...
متن کاملMolecular Topology. 14. Molord Algorithm and Real Number Subgraph Invariants
An algorithm, MOLORD, is proposed for defining real number invariants for subgraphs of various sizes in molecular graphs. The algorithm is based on iterative line derivati ves and accounts for heteroatoms by means of their electronegativities. It can be used in topological equivalence perception as well as to provide local and global descriptors for QSPR or QSAR studies. The algorithm is implem...
متن کاملNovel ZE-Isomerism Descriptors Derived from Molecular Topology and Their Application to QSAR Analysis
We introduce several series of novel ZE-isomerism descriptors derived directly from two-dimensional molecular topology. These descriptors make use of a quantity named ZE-isomerism correction, which is added to the vertex degrees of atoms connected by double bonds in Z and E configurations. This approach is similar to the one described previously for topological chirality descriptors (Golbraikh,...
متن کاملQSAR and QSPR based solely on surface properties?
The use of descriptors based on local properties calculated at the molecular surface for QSPR models is discussed. It is suggested that descriptors should be related to the physical theory of intermolecular interactions and the relationship between established surface-based descriptors and the fundamental types of intermolecular interaction is discussed. Descriptors based on local properties th...
متن کامل