Abstract: Models predict activity of chemical compounds by employing “transformed” descriptor values. The descriptors are transformed via transformation functions that convert the raw descriptor values to new values better representing the contribution of the descriptors to the activity in question. Typically, these transformation functions are non-linear parametric functions such as Gaussian functions or sigmoid functions. Typically, the model will employ at least two different descriptors, each transformed by its own non-linear parametric function.

Abstract: Models predict activity of chemical compounds by employing “transformed” descriptor values. The descriptors are transformed via transformation functions that convert the raw descriptor values to new values better representing the contribution of the descriptors to the activity in question. Typically, these transformation functions are non-linear parametric functions such as Gaussian functions or sigmoid functions. Typically, the model will employ at least two different descriptors, each transformed by its own non-linear parametric function.

Abstract: Accessibility correction factors may be used to modify values predicted by models of electronic component substrate reactivity. Most of the correction factors described herein pertain to either steric or orientation effects on substrate accessibility. The correction factors may be derived from one or more “descriptors” of the substrate structure. Each group of descriptors and associated correction factor pertain to a particular site on the substrate. Examples of such descriptors include site polarity, protrusion, partial surface area, partial charge, etc. Often the correction factor is a function of multiple descriptors. The function may be an expression comprising multiple terms, each representing the weighted contribution of a particular descriptor. In other embodiments, the correction factor is simply a descriptor or a descriptor multiplied by a coefficient or other function.

Abstract: Methods are disclosed for developing models used to rapidly predict metabolic stability and regioselectivity of drug molecules. Training sets, based on a sample of molecules with known reaction rates and/or activation energies, are used along with structural descriptors of the molecules in order to develop mathematical models of metabolism based on regression analysis of the activation energies and descriptors. The resulting models are then used to predict the metabolism of other molecules. The invention is particularly useful in developing simple models of cytochrome p450 enzyme metabolism.

Abstract: The present invention relates to a novel class of compounds that are potent inhibitors of HIV reverse transcriptase and HIV integrase. In addition to being multienzyme inhibitors, the inventive compounds of the present invention are remarkable in at least two other respects. First, they do not appear to be toxic to cells at typical therapeutic concentrations. Second, they appear to be equally effective against mutant strains of HIV reverse transcriptase commonly found in patients who have developed resistance to current reverse transcriptase inhibitors. Because the inventive compounds show promise in combatting viral resistance and are potent inhibitors of both HIV reverse transcriptase and integrase, they are ideal candidates for use in combination with existing therapies or alone in treating AIDS or HIV infection.