Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs

IntroductionTricyclic anti-depressant (TCA) drugs are widely used to treat depression, but traditional methods for evaluating their physicochemical properties can be time-consuming and costly. This study examines how topological indices can help to predict the properties of TCA drugs, with a special...

Full description

Saved in:
Bibliographic Details
Main Authors: Simran Kour, J. Ravi Sankar
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Chemistry
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fchem.2025.1603948/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736237221412864
author Simran Kour
J. Ravi Sankar
author_facet Simran Kour
J. Ravi Sankar
author_sort Simran Kour
collection DOAJ
description IntroductionTricyclic anti-depressant (TCA) drugs are widely used to treat depression, but traditional methods for evaluating their physicochemical properties can be time-consuming and costly. This study examines how topological indices can help to predict the properties of TCA drugs, with a special focus on the role of the hydrogen representation.MethodsTwo molecular configurations were analyzed: one with only explicit hydrogen and the other including all hydrogen atoms. To assess predictive performance, linear regression (LR) and support vector regression (SVR) models were employed.ResultsThe results showed that adding all hydrogen atoms showed strong correlations, especially for polarizability, molar refractivity, and molar volume. Among the models employed, SVR provided more accurate results. Additionally, hydrogen representation had a stronger impact on SVR's predictions.DiscussionThese findings highlight the potential of using machine learning techniques in quantitative structure-property relationship (QSPR) models for more efficient and reliable predictions of drug properties.
format Article
id doaj-art-72a650bb0fe645e782a43aa3ad840e98
institution DOAJ
issn 2296-2646
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Chemistry
spelling doaj-art-72a650bb0fe645e782a43aa3ad840e982025-08-20T03:07:20ZengFrontiers Media S.A.Frontiers in Chemistry2296-26462025-06-011310.3389/fchem.2025.16039481603948Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugsSimran KourJ. Ravi SankarIntroductionTricyclic anti-depressant (TCA) drugs are widely used to treat depression, but traditional methods for evaluating their physicochemical properties can be time-consuming and costly. This study examines how topological indices can help to predict the properties of TCA drugs, with a special focus on the role of the hydrogen representation.MethodsTwo molecular configurations were analyzed: one with only explicit hydrogen and the other including all hydrogen atoms. To assess predictive performance, linear regression (LR) and support vector regression (SVR) models were employed.ResultsThe results showed that adding all hydrogen atoms showed strong correlations, especially for polarizability, molar refractivity, and molar volume. Among the models employed, SVR provided more accurate results. Additionally, hydrogen representation had a stronger impact on SVR's predictions.DiscussionThese findings highlight the potential of using machine learning techniques in quantitative structure-property relationship (QSPR) models for more efficient and reliable predictions of drug properties.https://www.frontiersin.org/articles/10.3389/fchem.2025.1603948/fulltricyclic anti-depressant drugstopological indicesQSPRlinear regressionsupport vector regression
spellingShingle Simran Kour
J. Ravi Sankar
Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
Frontiers in Chemistry
tricyclic anti-depressant drugs
topological indices
QSPR
linear regression
support vector regression
title Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
title_full Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
title_fullStr Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
title_full_unstemmed Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
title_short Hydrogen-centric machine learning approach for analyzing properties of tricyclic anti-depressant drugs
title_sort hydrogen centric machine learning approach for analyzing properties of tricyclic anti depressant drugs
topic tricyclic anti-depressant drugs
topological indices
QSPR
linear regression
support vector regression
url https://www.frontiersin.org/articles/10.3389/fchem.2025.1603948/full
work_keys_str_mv AT simrankour hydrogencentricmachinelearningapproachforanalyzingpropertiesoftricyclicantidepressantdrugs
AT jravisankar hydrogencentricmachinelearningapproachforanalyzingpropertiesoftricyclicantidepressantdrugs