Prediction of cancer cell sensitivity to natural products based on genomic and chemical properties.

Zhenyu Yue,Wenna Zhang,Qiuying Ding,Qiaoyue Yang,Junfeng Xia,Yongming Lu,Yan Chen

doi:10.7717/peerj.1425

Abstract

Natural products play a significant role in cancer chemotherapy. They are likely to provide many lead structures, which can be used as templates for the construction of novel drugs with enhanced antitumor activity. Traditional research approaches studied structure-activity relationship of natural products and obtained key structural properties, such as chemical bond or group, with the purpose of ascertaining their effect on a single cell line or a single tissue type. Here, for the first time, we develop a machine learning method to comprehensively predict natural products responses against a panel of cancer cell lines based on both the gene expression and the chemical properties of natural products. The results on two datasets, training set and independent test set, show that this proposed method yields significantly better prediction accuracy. In addition, we also demonstrate the predictive power of our proposed method by modeling the cancer cell sensitivity to two natural products, Curcumin and Resveratrol, which indicate that our method can effectively predict the response of cancer cell lines to these two natural products. Taken together, the method will facilitate the identification of natural products as cancer therapies and the development of precision medicine by linking the features of patient genomes to natural product sensitivity.

Highlights

In recent years, many natural products were purified and shown to have cancer chemopreventive activity in laboratory, as exemplified by Camptothecin, Vinblastine, Embelin and Paclitaxel (Dai et al, 2011; Goldwasser et al, 1995; Lynch et al, 2012; Of Trialists, 2011)
Strategy for prediction of cancer cell sensitivity to natural products Our goal was to use gene expression and in vitro drug sensitivity data derived from cell lines, with the addition of chemical properties, to predict cell lines’ response to natural products
Comparison of different machine learning methods In this study, in order to identify the best machine learning technique suitable for predicting cancer cell sensitivity to natural products, we comprehensively evaluated the performances of SVM (LibSVM), Decision Tree (J48), Random Forest, and Rotation Forest classifiers

Summary

Introduction

Many natural products were purified and shown to have cancer chemopreventive activity in laboratory, as exemplified by Camptothecin, Vinblastine, Embelin and Paclitaxel (Dai et al, 2011; Goldwasser et al, 1995; Lynch et al, 2012; Of Trialists, 2011). These agents from natural source have contributed significantly to the successful treatment of melanoma, leukemia, breast cancer and many other carcinomas.

Objectives

Methods

Results

Conclusion