Abstract: Versions of the invention are directed to computer-based methods, apparatus and software (programs) for fast, dynamic programming and recursive partitioning techniques to segment data, especially real-world data, into data structures for display as nodal trees. These techniques and displayed data in segmented form have numerous applications, especially for the analysis and understanding of real-world data. Some particular applications are in the area of computational high throughput screening of molecular drug (or pharmaceutical) candidates using a quantitative structure activity relationship (QSAR) approach. Another particular application is in the areas of pharmacogenomics and pharmacogenetics.

Abstract: Versions of the invention are directed to computer-based methods, apparatus and software (programs) for fast, dynamic programming and recursive partitioning techniques to segment data, especially real-world data, into data structures for display as nodal trees. These techniques and displayed data in segmented form have numerous applications, especially for the analysis and understanding of real-world data. Some particular applications are in the area of computational high throughput screening of molecular drug (or pharmaceutical) candidates using a quantitative structure activity relationship (QSAR) approach. Another particular application is in the areas of pharmacogenomics and pharmacogenetics.

Abstract: Statistical classification of activities of molecules is a computer implemented methodology of QSAR employing visualization of molecular features and statistical techniques for correlating features of molecules with their observed biological properties. Each molecule is described by noting the presence (1) or absence (0) of a feature of interest. The identification of specific features coded by 1's or 0's is accomplished by recursive partitioning. The data sets are planned or unplanned. The method is also applicable to classification of individuals in biological populations on the basis of their genetic makeup.

Abstract: Statistical classification of activities of molecules is a computer implemented methodology of QSAR employing visualization of molecular features and statistical techniques for correlating features of molecules with their observed biological properties. Each molecule is described by noting the presence (1) or absence (0) of a feature of interest. The identification of specific features coded by 1's or 0's is accomplished by recursive partitioning. The data sets are planned or unplanned. The method is also applicable to classification of individuals in biological populations on the basis of their genetic makeup.