QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition

Background/Objectives: HMG-CoA reductase is an enzyme that regulates the initial stage of cholesterol synthesis, and its inhibitors are widely used in the treatment of cardiovascular diseases. Methods: We have created a set of quantitative structure-activity relationship (QSAR) models for human HMG-...

Full description

Saved in:
Bibliographic Details
Main Authors: Robert Ancuceanu, Patriciu Constantin Popovici, Doina Drăgănescu, Ștefan Busnatu, Beatrice Elena Lascu, Mihaela Dinu
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Pharmaceuticals
Subjects:
Online Access:https://www.mdpi.com/1424-8247/17/11/1448
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152739117072384
author Robert Ancuceanu
Patriciu Constantin Popovici
Doina Drăgănescu
Ștefan Busnatu
Beatrice Elena Lascu
Mihaela Dinu
author_facet Robert Ancuceanu
Patriciu Constantin Popovici
Doina Drăgănescu
Ștefan Busnatu
Beatrice Elena Lascu
Mihaela Dinu
author_sort Robert Ancuceanu
collection DOAJ
description Background/Objectives: HMG-CoA reductase is an enzyme that regulates the initial stage of cholesterol synthesis, and its inhibitors are widely used in the treatment of cardiovascular diseases. Methods: We have created a set of quantitative structure-activity relationship (QSAR) models for human HMG-CoA reductase inhibitors using nested cross-validation as the primary validation method. To develop the QSAR models, we employed various machine learning regression algorithms, feature selection methods, and fingerprints or descriptor datasets. Results: We built and evaluated a total of 300 models, selecting 21 that demonstrated good performance (coefficient of determination, R<sup>2</sup> ≥ 0.70 or concordance correlation coefficient, CCC ≥ 0.85). Six of these top-performing models met both performance criteria and were used to construct five ensemble models. We identified the descriptors most important in explaining HMG-CoA inhibition for each of the six best-performing models. We used the top models to search through over 220,000 chemical compounds from a large database (ZINC 15) for potential new inhibitors. Only a small fraction (237 out of approximately 220,000 compounds) had reliable predictions with mean pIC<sub>50</sub> values ≥ 8 (IC<sub>50</sub> values ≤ 10 nM). Our svm-based ensemble model predicted IC<sub>50</sub> values < 10 nM for roughly 0.08% of the screened compounds. We have also illustrated the potential applications of these QSAR models in understanding the cholesterol-lowering activities of herbal extracts, such as those reported for an extract prepared from the <i>Iris × germanica</i> rhizome. Conclusions: Our QSAR models can accurately predict human HMG-CoA reductase inhibitors, having the potential to accelerate the discovery of novel cholesterol-lowering agents and may also be applied to understand the mechanisms underlying the reported cholesterol-lowering activities of herbal extracts.
format Article
id doaj-art-c54eb208f5214379afebf74fe3318633
institution Kabale University
issn 1424-8247
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Pharmaceuticals
spelling doaj-art-c54eb208f5214379afebf74fe33186332024-11-26T18:17:12ZengMDPI AGPharmaceuticals1424-82472024-10-011711144810.3390/ph17111448QSAR Regression Models for Predicting HMG-CoA Reductase InhibitionRobert Ancuceanu0Patriciu Constantin Popovici1Doina Drăgănescu2Ștefan Busnatu3Beatrice Elena Lascu4Mihaela Dinu5Department of Pharmaceutical Botany and Cell Biology, Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaDepartment of Pharmaceutical Botany and Cell Biology, Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaDepartment of Pharmaceutical Physics, Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaDepartment of Cardiology, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaDepartment of Pharmaceutical Botany and Cell Biology, Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaDepartment of Pharmaceutical Botany and Cell Biology, Faculty of Pharmacy, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, RomaniaBackground/Objectives: HMG-CoA reductase is an enzyme that regulates the initial stage of cholesterol synthesis, and its inhibitors are widely used in the treatment of cardiovascular diseases. Methods: We have created a set of quantitative structure-activity relationship (QSAR) models for human HMG-CoA reductase inhibitors using nested cross-validation as the primary validation method. To develop the QSAR models, we employed various machine learning regression algorithms, feature selection methods, and fingerprints or descriptor datasets. Results: We built and evaluated a total of 300 models, selecting 21 that demonstrated good performance (coefficient of determination, R<sup>2</sup> ≥ 0.70 or concordance correlation coefficient, CCC ≥ 0.85). Six of these top-performing models met both performance criteria and were used to construct five ensemble models. We identified the descriptors most important in explaining HMG-CoA inhibition for each of the six best-performing models. We used the top models to search through over 220,000 chemical compounds from a large database (ZINC 15) for potential new inhibitors. Only a small fraction (237 out of approximately 220,000 compounds) had reliable predictions with mean pIC<sub>50</sub> values ≥ 8 (IC<sub>50</sub> values ≤ 10 nM). Our svm-based ensemble model predicted IC<sub>50</sub> values < 10 nM for roughly 0.08% of the screened compounds. We have also illustrated the potential applications of these QSAR models in understanding the cholesterol-lowering activities of herbal extracts, such as those reported for an extract prepared from the <i>Iris × germanica</i> rhizome. Conclusions: Our QSAR models can accurately predict human HMG-CoA reductase inhibitors, having the potential to accelerate the discovery of novel cholesterol-lowering agents and may also be applied to understand the mechanisms underlying the reported cholesterol-lowering activities of herbal extracts.https://www.mdpi.com/1424-8247/17/11/1448HMG-CoA reductaseQSARstatinsnested cross-validationvirtual screening<i>Iris germanica</i>
spellingShingle Robert Ancuceanu
Patriciu Constantin Popovici
Doina Drăgănescu
Ștefan Busnatu
Beatrice Elena Lascu
Mihaela Dinu
QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
Pharmaceuticals
HMG-CoA reductase
QSAR
statins
nested cross-validation
virtual screening
<i>Iris germanica</i>
title QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
title_full QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
title_fullStr QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
title_full_unstemmed QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
title_short QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
title_sort qsar regression models for predicting hmg coa reductase inhibition
topic HMG-CoA reductase
QSAR
statins
nested cross-validation
virtual screening
<i>Iris germanica</i>
url https://www.mdpi.com/1424-8247/17/11/1448
work_keys_str_mv AT robertancuceanu qsarregressionmodelsforpredictinghmgcoareductaseinhibition
AT patriciuconstantinpopovici qsarregressionmodelsforpredictinghmgcoareductaseinhibition
AT doinadraganescu qsarregressionmodelsforpredictinghmgcoareductaseinhibition
AT stefanbusnatu qsarregressionmodelsforpredictinghmgcoareductaseinhibition
AT beatriceelenalascu qsarregressionmodelsforpredictinghmgcoareductaseinhibition
AT mihaeladinu qsarregressionmodelsforpredictinghmgcoareductaseinhibition