Research Papers:

MLACP: machine-learning-based prediction of anticancer peptides

Balachandran Manavalan, Shaherin Basith, Tae Hwan Shin, Sun Choi, Myeong Ok Kim and Gwang Lee _

PDF  |  HTML  |  Supplementary Files  |  How to cite

Oncotarget. 2017; 8:77121-77136. https://doi.org/10.18632/oncotarget.20365

Metrics: PDF 2149 views  |   HTML 4958 views  |   ?  


Balachandran Manavalan1, Shaherin Basith2, Tae Hwan Shin1,3, Sun Choi2, Myeong Ok Kim4 and Gwang Lee1,3

1Department of Physiology, Ajou University School of Medicine, Suwon, Republic of Korea

2College of Pharmacy, Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul, Republic of Korea

3Institute of Molecular Science and Technology, Ajou University, Suwon, Republic of Korea

4Division of Life Science and Applied Life Science (BK21 Plus), College of Natural Sciences, Gyeongsang National University, Jinju, Republic of Korea

Correspondence to:

Gwang Lee, email: [email protected]

Keywords: anticancer peptides, hybrid model, machine-learning parameters, random forest, support vector machine

Received: May 16, 2017     Accepted: July 13, 2017     Published: August 19, 2017


Cancer is the second leading cause of death globally, and use of therapeutic peptides to target and kill cancer cells has received considerable attention in recent years. Identification of anticancer peptides (ACPs) through wet-lab experimentation is expensive and often time consuming; therefore, development of an efficient computational method is essential to identify potential ACP candidates prior to in vitro experimentation. In this study, we developed support vector machine- and random forest-based machine-learning methods for the prediction of ACPs using the features calculated from the amino acid sequence, including amino acid composition, dipeptide composition, atomic composition, and physicochemical properties. We trained our methods using the Tyagi-B dataset and determined the machine parameters by 10-fold cross-validation. Furthermore, we evaluated the performance of our methods on two benchmarking datasets, with our results showing that the random forest-based method outperformed the existing methods with an average accuracy and Matthews correlation coefficient value of 88.7% and 0.78, respectively. To assist the scientific community, we also developed a publicly accessible web server at www.thegleelab.org/MLACP.html.

Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 20365