Active compound is a substance (medicine) capable of providing kind effect when the human bodies are in bad shape. Active compound often used for preventing or curing a disease. Active compound takes an important role in medical world. Simplified Molecular Input Line System notation, in short SMILES notation is representation of compound (carbon bond) created by David Weininger in 1980. SMILES notation composed of ASCII (American Standard Code for Information Interchange) characters so that it can be stored in string variable and easily processed by the computer. Currently, there are numbers of compounds (SMILES notation) and it makes the classification for tested compound that can be made into a medicine (active compound) becomes necessary. The purpose of this research is to classify the active compound function utilizing SMILES notation with Learning Vector Quantization (LVQ) method by using 2 active compound function classes, one for metabolic disease, and another for cancer disease. There are 467 datasets with each 11 features. On testing process, the obtained value for learning rate is 0.1, decrement alpha is 0.3, minimum alpha is , and maximum epoch is 15 by using a percentage of 80% training data and 20% testing data which produce accuracy of 76.34%.
Copyrights © 2018