Abstract
We use 3D convex hull and conventional descriptors computed for 345 active HIV-1 protease inhibitors collected from literature and 437 inactive analogues searched from the MDL/ISIS database in the study. The number of descriptors used to represent each compound was from 4 to 8 randomly. These uncorrelated descriptors were divided to two groups by the principal component analysis and fuzzy c-means algorithm. The classification produced a clear-cut switch in membership functions computed for each uncorrelated descriptor at the group boundary. Compounds with non-switching membership functions computed were treated as outliers and they were counted for estimating the accuracy of the classification. The averaged accuracy of classification for the active inhibitor set was about 20 % which was better than that directly classified by a linear discriminant function on the original 3D convex hull descriptors. The whole classification scheme was also applied to several sets of some conventional descriptors computed for each compound but the averaged accuracy was around 42 % . Further classification using some 3D convex hull descriptors searched from comparing the distribution of these descriptors was performed on a new dataset composed of 289 outliers- deducted active inhibitors and 63 outliers identified from the inactive analogues through previous classification. This final classification identified 19 inactive analogues which were similar in structural and topological features to those of some highly active inhibitors classified together with them.