Cancer Drug Classification using Artificial Neural Network with Feature Selection

Cancer is one of the life-threatening diseases that has become a common disease across the globe. It is a disease where the cells grow rapidly and irregularly. Cancer researchers have synthesized various compounds that have anticancer properties. With proliferating cheminformatic data, classification of the cancer drug becomes a challenge. Machine learning algorithms facilitate the classification of the drug type and hence reduces the lab expenses. This paper explores various supervised machine learning algorithms and their prediction of cancer drugs. Feature selection is applied to select the best and relevant feature which helps in higher prediction accuracy. Logistic Regression, Decision Tree, Artificial Neural Network and Random forest learning models are employed for the classification. Multi-Layer Perceptron achieved higher performance than the other machine learning models and the impact of feature selection on the prediction accuracy is investigated.