Cargando…

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

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 meth...

Descripción completa

Detalles Bibliográficos
Autores principales: Yoo, Sunyong, Yang, Hyung Chae, Lee, Seongyeong, Shin, Jaewook, Min, Seyoung, Lee, Eunjoo, Song, Minkeun, Lee, Doheon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7845697/
https://www.ncbi.nlm.nih.gov/pubmed/33519445
http://dx.doi.org/10.3389/fphar.2020.584875
_version_ 1783644604148482048
author Yoo, Sunyong
Yang, Hyung Chae
Lee, Seongyeong
Shin, Jaewook
Min, Seyoung
Lee, Eunjoo
Song, Minkeun
Lee, Doheon
author_facet Yoo, Sunyong
Yang, Hyung Chae
Lee, Seongyeong
Shin, Jaewook
Min, Seyoung
Lee, Eunjoo
Song, Minkeun
Lee, Doheon
author_sort Yoo, Sunyong
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7845697
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78456972021-01-30 A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds Yoo, Sunyong Yang, Hyung Chae Lee, Seongyeong Shin, Jaewook Min, Seyoung Lee, Eunjoo Song, Minkeun Lee, Doheon Front Pharmacol Pharmacology 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. Frontiers Media S.A. 2020-11-30 /pmc/articles/PMC7845697/ /pubmed/33519445 http://dx.doi.org/10.3389/fphar.2020.584875 Text en Copyright © 2020 Yoo, Yang, Lee, Shin, Min, Lee, Song and Lee. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Pharmacology
Yoo, Sunyong
Yang, Hyung Chae
Lee, Seongyeong
Shin, Jaewook
Min, Seyoung
Lee, Eunjoo
Song, Minkeun
Lee, Doheon
A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title_full A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title_fullStr A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title_full_unstemmed A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title_short A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds
title_sort deep learning-based approach for identifying the medicinal uses of plant-derived natural compounds
topic Pharmacology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7845697/
https://www.ncbi.nlm.nih.gov/pubmed/33519445
http://dx.doi.org/10.3389/fphar.2020.584875
work_keys_str_mv AT yoosunyong adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT yanghyungchae adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leeseongyeong adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT shinjaewook adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT minseyoung adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leeeunjoo adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT songminkeun adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leedoheon adeeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT yoosunyong deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT yanghyungchae deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leeseongyeong deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT shinjaewook deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT minseyoung deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leeeunjoo deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT songminkeun deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds
AT leedoheon deeplearningbasedapproachforidentifyingthemedicinalusesofplantderivednaturalcompounds