Machine Learning Prediction for 50 Anti-Cancer Food Molecules from 968 Anti-Cancer Drugs

Abstract

Cancer-beating molecules (CBMs) are abundant in many types of food and potentially anti-cancer therapeutic agents. In the previous work, researchers introduced a network-based machine learning platform to identify the cancer-beating molecules, for example, comparing the similarities in the molecular network between approved anticancer drug and food molecules. Herein, we aim to build on this work to enhance the accuracy of predicting food molecules. In this project, we improve supervised learning approaches by applying Soft Voting algorithm to seven machine learning algorithms: Support Vector Machine with Radial Basis Function (SVM with RBF kernel), multilayer perceptron neural network (MLP), Random forest, Decision trees, Gaussian Naive Bayes, Adaboosting, and Bagging. As a result, the accuracy in the dataset of 50 food molecules utilized increased from 82% to 87%, achieving a significant improvement in the precision of predicting anti-cancer molecules.