Dehmer, M., Varmuza, K., Bonchev, D. (Eds.) Statistical Modelling of Molecular Descriptors in QSAR/QSPR

Wiley-VCH, 2012. — 447 p. — (Quantitative and Network Biology. Volume 2). — ISBN: 9783527324347.Molecular descriptors have been applied extensively in, for example, bioinformatics, network biology structure-oriented drug design, medicinal chemistry, chemometrics, chemical graph theory, and mathematical chemistry. Also, their positive impact in quantitative structure–activity relationship/quantitative structure–property relationship(QSAR/QSPR) has been demonstrated and important subgroups of
descriptors such as topological indices have been explored. The book Statistical Modeling of Molecular Descriptors in QSAR/QSPR presents theoretical and practical results toward the statistical analysis and modeling of molecular descriptors. An intriguing and important field of activity for applying the results discussed in this book is QSAR and QSPR. Particularly the contributors put the emphasis on employing statistical methods for modeling data generated by using molecular descriptors. In this sense, the major goal of the book is to advocate and promote a combination of statistical, information-theoretic, and data analysis techniques to meet the challenge
of designing empirical models by using molecular descriptors. Importantly, some of these contributions demonstrate the ability of molecular descriptors for predicting physicochemical or even toxic properties of chemicals successfully. Also, mathematical properties of molecular and topological descriptors are investigated.Current Modeling Methods Used in QSAR/QSPR
Developing Best Practices for Descriptor-Based Property Prediction: Appropriate Matching of Datasets, Descriptors, Methods, and Expectations
Mold 2 Molecular Descriptors for QSAR
Multivariate Analysis of Molecular Descriptors
Partial-Order Ranking and Linear Modeling: Their Use in Predictive QSAR/QSPR Studies
Graph-Theoretical Descriptors for Branched Polymers
Structural-Similarity-Based Approaches for the Development of Clustering and QSPR/QSAR Models in Chemical Databases
Statistical Methods for Predicting Compound Recovery Rates for Ligand-Based Virtual Screening and Assessing the Probability of Activity
Molecular Descriptors and the Electronic Structure
New Types of Descriptors and Models in QSAR/QSPR
Consensus Models of Activity Landscapes
Reverse Engineering Chemical Reaction Networks from Time Series Data
Reduction of Dimensionality, Order, and Classification in Spaces of Theoretical Descriptions of Molecules: An Approach Based on Metrics, Pattern Recognition Techniques, and Graph Theoretic Considerations
The Analysis of Organic Reaction Pathways by Brownian Processing
Generation of Chemical Transformations: Reaction Pathways Prediction and Synthesis Design