EXPLORATORY DATA ANALYSIS ON ANTICANCER OF BREAST AND LUNG CANCER CELLS

Abstract

Membranolytic anticancer peptides (ACPs) are drawing increasing attention as potential future therapeutics against cancer, due to their ability to hinder the development of cellular resistance and their potential to overcome common hurdles of chemotherapy, e.g., side effects and cytotoxicity. In this research work focuses on the classifications of the peptides with experimental annotations on their anticancer action on breast and lung cancer cells by using machine learning. The K-Nearest Neighbors (KNN) produces the high level of accuracy i.e., 82.18% accuracy level. This is the highest precision value compare with other models. Rest of the algorithms namely Linear Discriminant Analysis, Linear Regression, Logistic Regression and Naïve Bayes have produce the accuracy values from 68.3 to 79.2%.The K-Nearest Neighbors (KNN) classifier has 82.46% of precision value. This is the highest precision value compare with other models. Rest of the algorithms namely Linear Discriminant Analysis, Linear Regression, and Naïve Bayes have produce the precision values from 69.23% to 80.01%. The Linear Regression, K-Nearest Neighbors (KNN) have produces the same recall value which is 82.32%. The K-Nearest Neighbors (KNN) approach takes the low time consumption i.e., 0.09 seconds to build the model, the Naïve Bayes  approach takes 0.13 seconds to build the model, the Logistic approach takes the 0.19 seconds , the Linear Discriminant Analysis approach takes the 0.3 seconds and finally Linear Regression approach takes more time around 0.22 seconds to build the model.