Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs

The accumulation of senescent cells is a major contributor to aging and various age-related diseases, making developing senolytic compounds that are capable of clearing these cells an important area of research. However, progress has been hampered by the limited number of known senolytics and the in...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinjun Li, Kai Zhao, Guotai Yang, Haohao Lv, Renxin Zhang, Shuhan Li, Zhiyuan Chen, Min Xu, Naixue Yang, Shaoxing Dai
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Molecules
Subjects:
Online Access:https://www.mdpi.com/1420-3049/30/12/2653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425846944661504
author Jinjun Li
Kai Zhao
Guotai Yang
Haohao Lv
Renxin Zhang
Shuhan Li
Zhiyuan Chen
Min Xu
Naixue Yang
Shaoxing Dai
author_facet Jinjun Li
Kai Zhao
Guotai Yang
Haohao Lv
Renxin Zhang
Shuhan Li
Zhiyuan Chen
Min Xu
Naixue Yang
Shaoxing Dai
author_sort Jinjun Li
collection DOAJ
description The accumulation of senescent cells is a major contributor to aging and various age-related diseases, making developing senolytic compounds that are capable of clearing these cells an important area of research. However, progress has been hampered by the limited number of known senolytics and the incomplete understanding of their mechanisms. This study presents a powerful senolytic predictor built using phenotypic data and machine learning techniques to identify compounds with potential senolytic activity. A comprehensive training dataset consisting of 111 positive and 3951 negative compounds was curated from the literature. The dataset was used to train machine learning models, incorporating traditional molecular fingerprints, molecular descriptors, and MoLFormer molecular embeddings. By applying MoLFormer-based oversampling and testing different algorithms, it was found that the Support Vector Machine (SVM) and Multilayer Perceptron (MLP) models with MoLFormer embeddings exhibited the best performance, achieving Area Under the Curve (AUC) scores of 0.998 and 0.997, and F1 scores of 0.948 and 0.941, respectively. This senolytic predictor was then used to perform virtual screening of compounds from the DrugBank and TCMbank databases. In the DrugBank database, 98 structurally novel candidate compounds with potential senolytic activity were identified. For TCMbank, 714 potential senolytic compounds were predicted and 81 medicinal herbs with possible senolytic properties were identified. Moreover, pathway enrichment analysis revealed key targets and potential mechanisms underlying senolytic activity. In an experimental screening of predicted compounds, panaxatriol was found to exhibit senolytic activity on the etoposide-induced senescence of the IMR-90 cell line. Additionally, voclosporin was found to extend the lifespan of <i>C. elegans</i> more effectively than metformin, demonstrating the value of our model for drug repurposing. This study not only provides an efficient framework for discovering novel senolytic agents, but also highlights the predicted novel senolytic compounds and herbs as valuable starting points for future research into senolytic drug development.
format Article
id doaj-art-3c74fa0e4cb147919b7f3cb4bc4a896b
institution Kabale University
issn 1420-3049
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Molecules
spelling doaj-art-3c74fa0e4cb147919b7f3cb4bc4a896b2025-08-20T03:29:39ZengMDPI AGMolecules1420-30492025-06-013012265310.3390/molecules30122653Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and HerbsJinjun Li0Kai Zhao1Guotai Yang2Haohao Lv3Renxin Zhang4Shuhan Li5Zhiyuan Chen6Min Xu7Naixue Yang8Shaoxing Dai9State Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaCenter for Pharmaceutical Sciences, Faculty of Life Science and Technology, Kunming University of Science and Technology, Kunming 650500, ChinaCenter for Pharmaceutical Sciences, Faculty of Life Science and Technology, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaCenter for Pharmaceutical Sciences, Faculty of Life Science and Technology, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaState Key Laboratory of Primate Biomedical Research, Institute of Primate Translational Medicine, Kunming University of Science and Technology, Kunming 650500, ChinaThe accumulation of senescent cells is a major contributor to aging and various age-related diseases, making developing senolytic compounds that are capable of clearing these cells an important area of research. However, progress has been hampered by the limited number of known senolytics and the incomplete understanding of their mechanisms. This study presents a powerful senolytic predictor built using phenotypic data and machine learning techniques to identify compounds with potential senolytic activity. A comprehensive training dataset consisting of 111 positive and 3951 negative compounds was curated from the literature. The dataset was used to train machine learning models, incorporating traditional molecular fingerprints, molecular descriptors, and MoLFormer molecular embeddings. By applying MoLFormer-based oversampling and testing different algorithms, it was found that the Support Vector Machine (SVM) and Multilayer Perceptron (MLP) models with MoLFormer embeddings exhibited the best performance, achieving Area Under the Curve (AUC) scores of 0.998 and 0.997, and F1 scores of 0.948 and 0.941, respectively. This senolytic predictor was then used to perform virtual screening of compounds from the DrugBank and TCMbank databases. In the DrugBank database, 98 structurally novel candidate compounds with potential senolytic activity were identified. For TCMbank, 714 potential senolytic compounds were predicted and 81 medicinal herbs with possible senolytic properties were identified. Moreover, pathway enrichment analysis revealed key targets and potential mechanisms underlying senolytic activity. In an experimental screening of predicted compounds, panaxatriol was found to exhibit senolytic activity on the etoposide-induced senescence of the IMR-90 cell line. Additionally, voclosporin was found to extend the lifespan of <i>C. elegans</i> more effectively than metformin, demonstrating the value of our model for drug repurposing. This study not only provides an efficient framework for discovering novel senolytic agents, but also highlights the predicted novel senolytic compounds and herbs as valuable starting points for future research into senolytic drug development.https://www.mdpi.com/1420-3049/30/12/2653senolytic compoundsmachine learningvirtual screeningMoLFormerDrugBankTCMbank
spellingShingle Jinjun Li
Kai Zhao
Guotai Yang
Haohao Lv
Renxin Zhang
Shuhan Li
Zhiyuan Chen
Min Xu
Naixue Yang
Shaoxing Dai
Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
Molecules
senolytic compounds
machine learning
virtual screening
MoLFormer
DrugBank
TCMbank
title Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
title_full Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
title_fullStr Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
title_full_unstemmed Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
title_short Development and Application of a Senolytic Predictor for Discovery of Novel Senolytic Compounds and Herbs
title_sort development and application of a senolytic predictor for discovery of novel senolytic compounds and herbs
topic senolytic compounds
machine learning
virtual screening
MoLFormer
DrugBank
TCMbank
url https://www.mdpi.com/1420-3049/30/12/2653
work_keys_str_mv AT jinjunli developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT kaizhao developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT guotaiyang developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT haohaolv developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT renxinzhang developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT shuhanli developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT zhiyuanchen developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT minxu developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT naixueyang developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs
AT shaoxingdai developmentandapplicationofasenolyticpredictorfordiscoveryofnovelsenolyticcompoundsandherbs