A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds

Sunyong Yoo; Hyung Chae Yang; Seongyeong Lee; Jaewook Shin; Seyoung Min; Eunjoo Lee; Minkeun Song; Doheon Lee

doi:10.3389/fphar.2020.584875

A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds

Front Pharmacol. 2020 Nov 30:11:584875. doi: 10.3389/fphar.2020.584875. eCollection 2020.

Authors

Sunyong Yoo¹, Hyung Chae Yang², Seongyeong Lee¹, Jaewook Shin¹, Seyoung Min¹, Eunjoo Lee³, Minkeun Song⁴, Doheon Lee^{5

6}

Affiliations

¹ School of Electronics and Computer Engineering, Chonnam National University, Gwangju, South Korea.
² Department of Otorhinolaryngology-Head and Neck Surgery, Chonnam National University Medical School and Chonnam National University Hospital, Gwangju, South Korea.
³ Big Data Steering Department, National Health Insurance Service, Wonju, South Korea.
⁴ Department of Physical and Rehabilitation Medicine, Research Institute of Medical Science, Cardiovascular Research Institute, Chonnam National University Medical School and Hospital, Gwangju, South Korea.
⁵ Bio-Synergy Research Center, Daejeon, South Korea.
⁶ Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.

Abstract

Medicinal plants and their extracts have been used as important sources for drug discovery. In particular, plant-derived natural compounds, including phytochemicals, antioxidants, vitamins, and minerals, are gaining attention as they promote health and prevent disease. Although several in vitro methods have been developed to confirm the biological activities of natural compounds, there is still considerable room to reduce time and cost. To overcome these limitations, several in silico methods have been proposed for conducting large-scale analysis, but they are still limited in terms of dealing with incomplete and heterogeneous natural compound data. Here, we propose a deep learning-based approach to identify the medicinal uses of natural compounds by exploiting massive and heterogeneous drug and natural compound data. The rationale behind this approach is that deep learning can effectively utilize heterogeneous features to alleviate incomplete information. Based on latent knowledge, molecular interactions, and chemical property features, we generated 686 dimensional features for 4,507 natural compounds and 2,882 approved and investigational drugs. The deep learning model was trained using the generated features and verified drug indication information. When the features of natural compounds were applied as input to the trained model, potential efficacies were successfully predicted with high accuracy, sensitivity, and specificity.

Keywords: chemical property; deep learning; medicinal use; molecular interaction; natural compound; natural product; network analysis; text mining.