Experiments on Automatic Drug Activity Characterization using Support Vector Classification

F.J. Ferri, W. Díaz, and M.J. Castro (Spain)


Support Vector Machines, Pattern Classification, Multi layer Perceptron, Pharmacological drug selection.


The characterization of pharmacological properties from their chemical structure has become a challenging and promising technique in computer aided drug design. The idea consists of finding appropriate representations of can didate compounds in terms of their chemical formulae and try to apply a particular machine learning method able to appropriately characterize certain desired properties or kinds of pharmacological activity. In this particular work antibacterial activity has been considered. Several classic pattern classification methods have already been applied to this problem with promising results. In this work, the sup port vector machine model is considered and compared to multilayer perceptrons in this particular context. The natu ral and unpredictable imbalance and the fact that only rel atively small samples can be used for learning make this a challenging and interesting problem.

Important Links:

Go Back