Machine Learning-Based Analysis Reveals Triterpene Saponins and Their Aglycones in Cimicifuga racemosa - as Critical Mediators of AMPK Activation

Aug 3, 2026

Upload by Aurora

Cimicifuga racemosa (CR) extracts contain diverse saponins that defend against herbivores and pathogens and may support treatment of human disorders including heart failure, pain, hypercholesterolemia, cancer, and inflammation. Because multiple effects are mediated by activation of AMP-dependent protein kinase (AMPK), the study performs comprehensive in silico screening of activating constituents. Machine learning models using MACCS molecular fingerprints classify 95 CR constituents, with calibration using 50 positive and negative controls, showing screening suitability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages35

Reading Time1 h 28 min

AccessFree to download

Abstract

Keywords

Introduction

source: [https://doi.org/10.48350/196304 | downloaded:](https://doi.org/10.48350/196304 | downloaded:) 4.6.2024 pharmaceutics Article Machine Learning-Based Analysis Reveals Triterpene Saponinsand Their Aglycones in Cimicifuga racemosa as Critical Mediators of AMPK Activation Jürgen Drewe 1, *, Verena Schöning 2, Ombeline Danton 1, Alexander Schenk 1 and Georg Boonen 1 Citation: Drewe, J.; Schöning, V.; Danton, O.; Schenk, A.; Boonen, G. Machine Learning-Based Analysis Reveals Triterpene Saponins and Their Aglycones in Cimicifuga racemosaas Critical Mediators of AMPK Activation. Pharmaceutics 2024, 16, 511 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)pharmaceutics16040511 Academic Editors: Robert Ancuceanu and Mihaela Dinu Received: 28 February 2024 Revised: 14 March 2024 Accepted: 5 April 2024 Published: 7 April 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Medical Department, Max Zeller Söhne AG, 8590 Romanshorn, Switzerland; [ombelined@gmail.com](ombelined@gmail.com) (O.D.); alexander.schenk@zellerag.ch (A.S.); [georg.boonen@zellerag.ch](georg.boonen@zellerag.ch) (G.B.) 2 Clinical Pharmacology and Toxicology, Department of General Internal Medicine, Inselspital—University Hospital, 3010 Bern, Switzerland * Correspondence: juergen.drewe@zellerag.ch or juergen.drewe@unibas.ch Abstract: Cimicifuga racemosa (CR) extracts contain diverse constituents such as saponins. These saponins, which act as a defense against herbivores and pathogens also show promise in treating human conditions such as heart failure, pain, hypercholesterolemia, cancer, and inflammation. Some of these effects are mediated by activating AMP-dependent protein kinase (AMPK) . Therefore, comprehensive screening for activating constituents in a CR extract is highly desirable. Employing machine learning (ML) techniques such as Deep Neural Networks (DNN), Logistic Regression Classification (LRC), and Random Forest Classification (RFC) with molecular fingerprint MACCS descriptors, 95 CR constituents were classified. Calibration involved 50 randomly chosen positive and negative controls. LRC achieved the highest overall test accuracy (90.2%), but DNN and RFC surpassed it in precision, sensitivity, specificity, and ROC AUC. All CR constituents were predicted as activators, except for three non-triterpene compounds. The validity of these classifications was supported by good calibration, with misclassifications ranging from 3% to 17% across the various models. High sensitivity (84.5–87.2%) and specificity (84.1–91.4%) suggest suitability for screening. The results demonstrate the potential of triterpene saponins and aglycones in activating AMPdependent protein kinase (AMPK), providing the rationale for further clinical exploration of CR extracts in metabolic pathway-related conditions. Keywords: AMPK activator; logistic regression classification; deep neural networks; machine learning; Cimicifuga racemosa; triterpene saponins; polyphenols 1. Introduction Extracts of Cimicifuga racemosa L., NUTT. (also known as Actaea racemosa L. or black cohosh) are widely accepted [1–4] and have been granted “well-established use” status in the treatment of postmenopausal (i.e., climacteric) complaints by the European Medicines Agency [5] . This monograph predominantly includes vasomotor symptoms such as hot flushes and sweating, as well as nervousness, irritability, and metabolic changes. Although characteristic postmenopausal complaints have been known for a very long time and the beneficial effects of Cimicifuga extracts on climacteric symptoms are well accepted [3,4], the mechanism of actions

FAQs

What motivated screening for AMPK-activating constituents in Cimicifuga racemosa extracts?

AMP-dependent protein kinase (AMPK) is implicated in mediating several beneficial effects of CR extracts, so identifying potential AMPK activators is important for targeted exploration of the extract’s therapeutic potential.

Which machine learning techniques were used to classify CR constituents as AMPK activators?

Deep Neural Networks, Logistic Regression Classification, and Random Forest Classification were used with MACCS molecular fingerprint descriptors.

How accurate were the model predictions for AMPK activation screening?

Logistic regression achieved the highest overall test accuracy (90.2%), while deep neural networks and random forest showed stronger precision, sensitivity, specificity, and ROC AUC; misclassification rates ranged from 3% to 17% across models.

Aug 3, 2026

Upload by Aurora