Hierarchical quantitative structure-activity

Hierarchical quantitative structure-activity relationship (HiQSAR) - Ridge regression ... 

HiQSAR Hierarchical quantitative structure-activity relationship... 

In this chapter, we have developed predictive models based on two well es-tabhshed methods (1) hierarchical quantitative structure-activity (HiQSAR) modeling, and (2) quantitative molecular similarity analysis (QMSA). We have reviewed published work in both of the above areas for important classes of heterocyclic compounds that have therapeutic and toxic effects. Predictive models can be developed based on experimental properties, substituent constants derived from such properties, and also theoretical descriptors which can be calculated directly from molecular structure, hi view of the fact that most potential therapeutic agents and the majority of known drugs and toxicants do not have experimental data available for their evaluation, theoretical descriptors are very useful in the initial screening of compound libraries. 

Zhu, H-, Ye, L., Richard, A., Golbraikh, A., Wright, R A., Rusyn, I., et al. (2009). A novel two-step hierarchical quantitative structure-activity relationship modeling work flow for predicting acute toxicity of chemicals in rodents. Environmental Health Perspect, 117,1257. 

A hierarchical approach. In Quantitative Structure-Activity Relationship (QSAR) Models of Mutagens and Carcinogens, Benigni, R., Ed., CRC Press, Boca Raton, FL, 2003, pp. 207-234. 

Extrapolations of the other significant components of risk assessment, measures of effects, are reviewed in Chapters 3 through 7, which present a hierarchical approach based on biological organization. Extrapolation of effect measures through (quantitative) structure-activity relationships (IQISARs) is often necessitated because... 

Figure 13.11 Overview diagram of the NCTR Four-Phase approach for priority setting. In Phase I, chemicals with molecular weight < 94 or > 1000 or containing no ring structure will be rejected. In Phase II, three approaches (structural alerts, pharmacophores, and classification methods) that include a total of 11 models are used to make a qualitative activity prediction. In Phase III, a 3D QSAR/CoMFA model is used to make a more accurate quantitative activity prediction. In Phase IV, an expert system is expected to make a decision on priority setting based on a set of rules. Different phases are hierarchical different methods within each phase are complementary.

---