A machine learning-integrated stepwise method to discover novel anti-obesity phytochemicals that antagonize the glucocorticoid receptor

Shin, Seo Hyun; Hur, Gihyun; Kim, Na Ra; Park, Jung Han Yoon; Lee, Ki Won; Yang, Hee Young

doi:10.1039/d2fo03466b

Cited by 8 publications

(6 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, "Normalization" was used to analyze the data and the polarization values were represented by the percent inhibition. [24] The fluorescence polarization value without a competitor was set to 0 % inhibition and the value for the high control was set to 100 % inhibition. Furthermore, the limit of detection (LOD), the 50 % inhibitory concentration (IC 50 value), and the detectable concentration range were identified as the standard concentration at 10 %, 50 %, and 20 %-80 % of the tracer binding, respectively.…”

Section: Fluorescence Polarization Assaymentioning

confidence: 99%

Comparison of the Glucocorticoid Receptor Binding and Agonist Activities of Typical Glucocorticoids: Insights into Their Endocrine Disrupting Effects

Liang,

Li,

Zhang

et al. 2024

Chemistry & Biodiversity

View full text Add to dashboard Cite

Over the past decades, the synthetic glucocorticoids (GCs) have been widely used in clinical practice and animal husbandry. Given the health hazard of these toxic residues in food, it is necessary to explore the detailed interaction mechanisms of typical GCs and their main target glucocorticoid receptor (GR). Hence, this work compared the GR binding and agonist activities of typical GCs. Fluorescence polarization assay showed that these GCs were potent ligands of GR. Their GR binding affinities were in the order of methylprednisolone > betamethasone ≈ prednisolone > dexamethasone, with IC50 values of 1.67, 2.94, 2.95, and 5.58 nM. Additionally, the limits of detection of dexamethasone, betamethasone, prednisolone, and methylprednisolone were 0.32, 0.14, 0.19, and 0.09 μg/kg in fluorescence polarization assay. Reporter gene assay showed that these GCs induced GR transactivation in a dose‐dependent manner, confirming their GR agonist activities. Among which, dexamethasone at the concentration of 100 nM produced a maximal induction of more than 11‐fold over the blank control. Molecular docking and molecular dynamics simulations suggested that hydrogen‐bonding and hydrophobic interactions played an important role in stabilizing the GC‐GR‐LBD complexes. In summary, this work might help to understand the GR‐mediated endocrine disrupting effects of typical GCs.

show abstract

Section: Fluorescence Polarization Assaymentioning

confidence: 99%

Comparison of the Glucocorticoid Receptor Binding and Agonist Activities of Typical Glucocorticoids: Insights into Their Endocrine Disrupting Effects

Liang,

Li,

Zhang

et al. 2024

Chemistry & Biodiversity

View full text Add to dashboard Cite

show abstract

“…The two models identified 65 phytochemicals that antagonised GR. They found demethylzeylasteral (22) (Figure 12), a phytochemical of the Tripterygium wilfordii Radix, exhibited potent anti-obesity activity in vitro [128]. (22) Figure 12.…”

Section: Machine Learning and Artificial Intelligencementioning

confidence: 99%

Phytochemicals in Drug Discovery - A Confluence of Tradition and Innovation

Chihomvu,

Ganesan,

Gibbons

et al. 2024

Preprint

View full text Add to dashboard Cite

Phytochemicals have a long and successful history in drug discovery. With recent advancements in analytical techniques and methodologies, discovering bioactive leads from natural compounds has become easier. Computational techniques like molecular docking, QSAR modelling and machine learning, and network pharmacology are among the most promising new tools that allow researchers to make predictions concerning natural products' potential targets, thereby guiding experimental validation efforts. Additionally, approaches like LC-MS or LC-NMR speed up compound identification by streamlining analytical processes. Integrating structural and computational biology aids in lead identification, thus providing invaluable information to understand how phytochemicals interact with potential targets in the body. Emerging computational approach is machine learning involving QSAR modelling and deep neural networks that interrelate phytochemical properties with diverse physiological activities such as antimicrobial or anticancer effects.

show abstract

“…The workflow includes contributions of some R packages. 56 R-based QSAR analysis was performed on selected phytochemicals to explore their therapeutic potential for COVID-19 treatment.…”

Section: Example Of Qsar With Specific Phytochemicalsmentioning

confidence: 99%

“…A QSAR‐based machine learning‐integrated stepwise method was used to discover novel anti‐obesity phytochemicals that antagonize the glucocorticoid receptor. The workflow includes contributions of some R packages 56 …”

Section: Example Of Qsar With Specific Phytochemicalsmentioning

confidence: 99%

R software for QSAR analysis in phytopharmacological studies

Ningthoujam¹,

Nath

Kityania

et al. 2023

Phytochemical Analysis

View full text Add to dashboard Cite

IntroductionIn recent decades, quantitative structure–activity relationship (QSAR) analysis has become an important method for drug design and natural product research. With the availability of bioinformatic and cheminformatic tools, a vast number of descriptors have been generated, making it challenging to select potential independent variables that are accurately related to the dependent response variable.ObjectiveThe objective of this study is to demonstrate various descriptor selection procedures, such as the Boruta approach, all subsets regression, the ANOVA approach, the AIC method, stepwise regression, and genetic algorithm, that can be used in QSAR studies. Additionally, we performed regression diagnostics using R software to test parameters such as normality, linearity, residual histograms, PP plots, multicollinearity, and homoscedasticity.ResultsThe workflow designed in this study highlights the different descriptor selection procedures and regression diagnostics that can be used in QSAR studies. The results showed that the Boruta approach and genetic algorithm performed better than other methods in selecting potential independent variables. The regression diagnostics parameters tested using R software, such as normality, linearity, residual histograms, PP plots, multicollinearity, and homoscedasticity, helped in identifying and diagnosing model errors, ensuring the reliability of the QSAR model.ConclusionQSAR analysis is vital in drug design and natural product research. To develop a reliable QSAR model, it is essential to choose suitable descriptors and perform regression diagnostics. This study offers an accessible, customizable approach for researchers to select appropriate descriptors and diagnose errors in QSAR studies.

show abstract

A machine learning-integrated stepwise method to discover novel anti-obesity phytochemicals that antagonize the glucocorticoid receptor

Abstract: This study developed and validated a machine learning-integrated stepwise method to discover novel anti-obesity phytochemicals through GR antagonism.

Cited by 8 publications

References 82 publications

Comparison of the Glucocorticoid Receptor Binding and Agonist Activities of Typical Glucocorticoids: Insights into Their Endocrine Disrupting Effects

Comparison of the Glucocorticoid Receptor Binding and Agonist Activities of Typical Glucocorticoids: Insights into Their Endocrine Disrupting Effects

Phytochemicals in Drug Discovery - A Confluence of Tradition and Innovation

R software for QSAR analysis in phytopharmacological studies

Contact Info

Product

Resources

About