SIRT2i_Predictor - A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors

Sep 17, 2026

Uploaded by Eden

Selective sirtuin 2 (SIRT2) inhibitors have shown promise for age-related diseases, yet no SIRT2 inhibitors have reached clinical trials. Machine learning has transformed early drug discovery, but robust large-scale ML models for novel SIRT2 inhibitors remain limited. To support virtual screening and lead optimization, the machine-learning tool SIRT2i_Predictor was built using multiple high-quality regression and classification models trained on 1797 compounds. Benchmarking indicates comparable chemical-space coverage with improved speed, and application to an in-house database aids prioritization for costly experimental testing via an easy-to-use web interface.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Background on SIRT2 and therapeutic rationale

Current challenges in SIRT2 inhibitor discovery

Development of SIRT2i_Predictor

Model types and training dataset

Benchmarking vs structure-based virtual screening

Web-based interface and practical application

In-house database screening and experimental prioritization

Availability of source code

pharmaceuticals Article SIRT2i_Predictor: A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors Nemanja Djokovic 1, *, Minna Rahnasto-Rilla 2, Nikolaos Lougiakis 3, Maija Lahtela-Kakkonen 2 and Katarina Nikolic 1, * Citation: Djokovic, N.; Rahnasto-Rilla, M.; Lougiakis, N.; Lahtela-Kakkonen, M.; Nikolic, K. SIRT2i_Predictor: A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors. Pharmaceuticals 2023, 16, 127 . [https://doi.org/10.3390/ph16010127](https://doi.org/10.3390/ph16010127) [Academic Editors: And](Academic Editors: And)¯elija M. Malenovi´c and Ana Proti´c Received: 13 December 2022 Revised: 10 January 2023 Accepted: 11 January 2023 Published: 14 January 2023 Copyright: © 2023 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 Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade, Vojvode Stepe 450, 11221 Belgrade, Serbia 2 School of Pharmacy, University of Eastern Finland, P.O. Box 1627, 70210 Kuopio, Finland 3 Laboratory of Medicinal Chemistry, Section of Pharmaceutical Chemistry, Department of Pharmacy, School of Health Sciences, National and Kapodistrian University of Athens, Panepistimiopolis-Zografou, 15771 Athens, Greece * [Correspondence: nemanja.djokovic@pharmacy.bg.ac.rs](Correspondence: nemanja.djokovic@pharmacy.bg.ac.rs) (N.D.); [katarina.nikolic@pharmacy.bg.ac.rs](katarina.nikolic@pharmacy.bg.ac.rs) (K.N.) Abstract: A growing body of preclinical evidence recognized selective sirtuin 2 (SIRT2) inhibitors as novel therapeutics for treatment of age-related diseases. However, none of the SIRT2 inhibitors have reached clinical trials yet. Transformative potential of machine learning (ML) in early stages of drug discovery has been witnessed by widespread adoption of these techniques in recent years. Despite great potential, there is a lack of robust and large-scale ML models for discovery of novel SIRT2 inhibitors. In order to support virtual screening (VS), lead optimization, or facilitate the selection of SIRT2 inhibitors for experimental evaluation, a machine-learning-based tool titled SIRT2i_Predictor was developed. The tool was built on a panel of high-quality ML regression and classiﬁcation-based models for prediction of inhibitor potency and SIRT1-3 isoform selectivity. State-of-the-art ML algorithms were used to train the models on a large and diverse dataset containing 1797 compounds. Benchmarking against structure-based VS protocol indicated comparable coverage of chemical space with great gain in speed. The tool was applied to screen the in-house database of compounds, corroborating the utility in the prioritization of compounds for costly in vitro screening campaigns. The easy-to-use web-based interface makes SIRT2i_Predictor a convenient tool for the wider community. The SIRT2i_Predictor's source code is made available online. Keywords: virtual screening; Python GUI application; QSAR; machine learning; SIRT2 inhibitors; regression; classiﬁcation 1. Introduction SIRT2 is a NAD+-dependent protein deacetylase involved in the regulation of many important biological functions, including the maintenance of genome stability, metabolism, aging, tumorigenesis, and cell-cycle regulation [1–5] . Studies on cellular and animal models of disease revealed the promising potential of SIRT2 inhibition in the treatment of agerelated diseases, including neurodegenerative disease and carcinoma [6,7] . Preclinical evidence generated during the last decade has resulted in growing interest in the development of small-molecule SIRT2 inhibitors, particularly as novel anticancer therapeutics [7] . The inhibition

FAQs

Why are SIRT2 inhibitors important for age-related diseases?

SIRT2 inhibition has shown promising preclinical potential in targeting age-related conditions such as neurodegenerative disease and cancer-related processes like proliferation and invasion.

What problem does the paper address in machine learning for SIRT2 inhibitor discovery?

It highlights the lack of robust, large-scale ML models specifically designed to discover novel SIRT2 inhibitors, despite ML’s growing role in early drug discovery.

What is SIRT2i_Predictor and how does it support discovery workflows?

SIRT2i_Predictor is a machine-learning-based tool with a web interface that predicts inhibitor potency and SIRT1-3 isoform selectivity, supporting virtual screening and lead optimization and helping prioritize compounds for experimental testing.

Sep 17, 2026

Uploaded by Eden