A Data-Driven Approach for Identifying Medicinal Combinations of Natural Products

Yoo, Sunyong; Ha, Suhyun; Shin, Moonshik; Noh, Kyungrin; Nam, Hojung; Lee, Doheon

doi:10.1109/access.2018.2874089

Cited by 16 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various network analysis platforms have been developed with bioinformatics, which are frequently utilized in pharmacology. These include platforms such as the Korean Traditional Knowledge Portal (http://www.koreantk.com/ (accessed on 30 November 2023), the Traditional Chinese Medicine Integrated Database [16], and KAMPO (https://kampo.ca/ (accessed on 30 November 2023)) [17]. The CODA program, however, distinguishes itself as a unique network platform.…”

Section: Discussionmentioning

confidence: 99%

Diverse and Synergistic Actions of Phytochemicals in a Plant-Based Multivitamin/Mineral Supplement against Oxidative Stress and Inflammation in Healthy Individuals: A Systems Biology Approach Based on a Randomized Clinical Trial

Kang,

Kim,

Lee

et al. 2023

Antioxidants

View full text Add to dashboard Cite

Traditional clinical methodologies often fall short of revealing the complex interplay of multiple components and targets within the human body. This study was designed to explore the complex and synergistic effects of phytochemicals in a plant-based multivitamin/mineral supplement (PBS) on oxidative stress and inflammation in healthy individuals. Utilizing a systems biology framework, we integrated clinical with multi-omics analyses, including UPLC-Q-TOF-MS for 33 phytochemicals, qPCR for 42 differential transcripts, and GC-TOF-MS for 17 differential metabolites. A Gene Ontology analysis facilitated the identification of 367 biological processes linked to oxidative stress and inflammation. As a result, a comprehensive network was constructed consisting of 255 nodes and 1579 edges, featuring 10 phytochemicals, 26 targets, and 218 biological processes. Quercetin was identified as having the broadest target spectrum, succeeded by ellagic acid, hesperidin, chlorogenic acid, and quercitrin. Moreover, several phytochemicals were associated with key genes such as HMOX1, TNF, NFE2L2, CXCL8, and IL6, which play roles in the Toll-like receptor, NF-kappa B, adipocytokine, and C-type lectin receptor signaling pathways. This clinical data-driven network system approach has significantly advanced our comprehension of a PBS’s effects by pinpointing pivotal phytochemicals and delineating their synergistic actions, thus illuminating potential molecular mechanisms.

show abstract

Section: Discussionmentioning

confidence: 99%

Diverse and Synergistic Actions of Phytochemicals in a Plant-Based Multivitamin/Mineral Supplement against Oxidative Stress and Inflammation in Healthy Individuals: A Systems Biology Approach Based on a Randomized Clinical Trial

Kang,

Kim,

Lee

et al. 2023

Antioxidants

View full text Add to dashboard Cite

show abstract

“…Our previous studies have shown that natural compounds have relatively limited chemical and molecular information compared with drugs ( Noh et al, 2018 ; Yoo et al, 2018a ; Yoo et al, 2018b ; Yoo et al, 2018c ). Analyzing this incomplete information using conventional statistical methods can distort the results or limit the coverage.…”

Section: Discussionmentioning

confidence: 99%

“…Plant-derived natural compounds and their chemical structure information were collected from KTKP ( Portal, 2020 ), TCMID ( Xue et al, 2012 ), COCONUT ( Yoo et al, 2018a ), and FooDB ( FooDB, 2020 ). Drug information, including chemical structure and indication, was collected from DrugBank version 5.1.5 ( Wishart et al, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

“…In this paper, we propose a deep learning-based approach to predict the medicinal uses of natural compounds. Our previous studies have shown that the various properties of natural compounds, such as molecular and chemical properties, can be utilized to predict the medicinal uses of natural compounds ( Noh et al, 2018 ; Yoo et al, 2018a ; Yoo et al, 2018b ; Yoo et al, 2018c ). Therefore, we adapted our previous approaches to extract the molecular and chemical properties of natural compounds ( Supplementary Section S1 in Supplementary Data S1 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…The Compound Combination-Oriented Natural Product Database (which interestingly shares the abbreviation, COCONUT: we will refer it K-COCONUT) is a database that not only contains entities related to natural products, but also other biological information such as genes, proteins, and disorders (Yoo et al 2018). We acquired raw data from the previously available database website, which encompasses 8,642 'herbs': these include not only plants but also fungi, animals, and even non-biological entities (Supplementary data SD3).…”

Section: [2] Implementationmentioning

confidence: 99%

PhyloSophos: a high-throughput scientific name mapping algorithm augmented with explicit consideration of taxonomic science

Cho

2023

Preprint

View full text Add to dashboard Cite

The nature of taxonomic science and the scientific nomenclature system makes it difficult to use scientific names as identifiers without running into complications. To facilitate high-throughput analysis of biological data involving scientific names, we designed PhyloSophos, a Python package that takes into account the properties of scientific names and taxonomic systems to map name inputs to the entries within the reference database of choice. We would like to present three case-studies which demonstrates how our implementations, including rule-based pre-processing and recursive mapping could improve mapping performance and information availability. We expect PhyloSophos to help with the systematic processing of poorly digitized and curated biological data, such as biodiversity information and ethnopharmacological resources, thus enabling full-scale bioinformatics analysis using these data.

show abstract

A Data-Driven Approach for Identifying Medicinal Combinations of Natural Products

Cited by 16 publications

References 47 publications

Diverse and Synergistic Actions of Phytochemicals in a Plant-Based Multivitamin/Mineral Supplement against Oxidative Stress and Inflammation in Healthy Individuals: A Systems Biology Approach Based on a Randomized Clinical Trial

Diverse and Synergistic Actions of Phytochemicals in a Plant-Based Multivitamin/Mineral Supplement against Oxidative Stress and Inflammation in Healthy Individuals: A Systems Biology Approach Based on a Randomized Clinical Trial

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

PhyloSophos: a high-throughput scientific name mapping algorithm augmented with explicit consideration of taxonomic science

Contact Info

Product

Resources

About