Classification of Dopamine Antagonists Using TFS-Based Artificial Neural Network

Abstract

In the former work, the authors proposed the Topological Fragment Spectral (TFS) method as a tool for the description of the topological structure profile of a molecule. This paper describes the TFS-based artificial neural network (TFS/ANN) approach for the classification and the prediction of pharmacological active classes of chemicals. Dopamine antagonists of 1227 that interact with different types of receptors (D1, D2, D3, and D4) were used for the training. The TFS/ANN successfully classified 89% of the drugs into their own active classes. Then, the trained model was used for predicting the class of unknown compounds. For the prediction set of 137 drugs that were not included in the training set, the TFS/ANN model predicted 111 (81%) drugs of them into their own active classes correctly.

Chemical data mining based on non-terminal vertex graph

“…The method doesn't require any kind of a priori substructure definition like a dictionary file for substructures to be searched for. The TFS representation method is also useful for the similar structure searching on chemical structure databases [5], the visualization of similar structure data space [6] and prediction of active classes of drugs by machine learning [7]. The TFS is based on the enumeration of all the possible substructures and the characterization of them.…”