Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics

Abstract This work introduces a hybrid computational approach in which degree-based topological descriptors are harnessed with the aid of advanced regression models and artificial neural networks (ANNs) to predict the crucial physicochemical properties of 17 drugs for the treatment of bladder cancer...

Full description

Saved in:
Bibliographic Details
Main Authors: Huiling Qin, Atef F. Hashem, Muhammad Farhan Hanif, Osman Abubakar Fiidow
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-14175-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343942295814144
author Huiling Qin
Atef F. Hashem
Muhammad Farhan Hanif
Osman Abubakar Fiidow
author_facet Huiling Qin
Atef F. Hashem
Muhammad Farhan Hanif
Osman Abubakar Fiidow
author_sort Huiling Qin
collection DOAJ
description Abstract This work introduces a hybrid computational approach in which degree-based topological descriptors are harnessed with the aid of advanced regression models and artificial neural networks (ANNs) to predict the crucial physicochemical properties of 17 drugs for the treatment of bladder cancer. Each molecule is assigned a molecular graph, from which a series of topological descriptors such as Zagreb indices, Randic index, Atom Bond Connectivity (ABC), and Symmetric Division Degree (SSD)are computed. These indices are used as input features by various regression models along with linear, cubic, and feedforward ANNs. The performance of the models is analyzed using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination $$(R^2)$$ . ANNs showed the best predictive performance with the $$R^2$$ value achieving 0.99. Moreover, SHAP (SHapley Additive exPlanations) analysis was used to explain the contribution of each descriptor toward the models’ predictions. The findings validate the promise of the combination of graph-theoretic descriptors with the tools of machine learning to achieve solid and interpretable models of molecular property prediction, which hold the potential for drug discovery and optimization in oncologic applications.
format Article
id doaj-art-af782e8a1eb146be9387242c9c3cd1d8
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-af782e8a1eb146be9387242c9c3cd1d82025-08-20T03:42:48ZengNature PortfolioScientific Reports2045-23222025-07-0115113210.1038/s41598-025-14175-wGraph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeuticsHuiling Qin0Atef F. Hashem1Muhammad Farhan Hanif2Osman Abubakar Fiidow3Department of Rehabilitation, The Affiliated Hospital of Youjiang Medical University for NationalitiesDepartment of Mathematics and Statistics, College of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU)Department of Mathematics and Statistics, The University of LahoreDepartment of Public Health, Faculty of Health Science, Salaam UniversityAbstract This work introduces a hybrid computational approach in which degree-based topological descriptors are harnessed with the aid of advanced regression models and artificial neural networks (ANNs) to predict the crucial physicochemical properties of 17 drugs for the treatment of bladder cancer. Each molecule is assigned a molecular graph, from which a series of topological descriptors such as Zagreb indices, Randic index, Atom Bond Connectivity (ABC), and Symmetric Division Degree (SSD)are computed. These indices are used as input features by various regression models along with linear, cubic, and feedforward ANNs. The performance of the models is analyzed using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination $$(R^2)$$ . ANNs showed the best predictive performance with the $$R^2$$ value achieving 0.99. Moreover, SHAP (SHapley Additive exPlanations) analysis was used to explain the contribution of each descriptor toward the models’ predictions. The findings validate the promise of the combination of graph-theoretic descriptors with the tools of machine learning to achieve solid and interpretable models of molecular property prediction, which hold the potential for drug discovery and optimization in oncologic applications.https://doi.org/10.1038/s41598-025-14175-wArtificial Neural Networks (ANN)Topological IndicesDegree-Based DescriptorsCubic RegressionLinear RegressionQSPR
spellingShingle Huiling Qin
Atef F. Hashem
Muhammad Farhan Hanif
Osman Abubakar Fiidow
Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
Scientific Reports
Artificial Neural Networks (ANN)
Topological Indices
Degree-Based Descriptors
Cubic Regression
Linear Regression
QSPR
title Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
title_full Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
title_fullStr Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
title_full_unstemmed Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
title_short Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
title_sort graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
topic Artificial Neural Networks (ANN)
Topological Indices
Degree-Based Descriptors
Cubic Regression
Linear Regression
QSPR
url https://doi.org/10.1038/s41598-025-14175-w
work_keys_str_mv AT huilingqin graphtheoreticandmachinelearningapproachesinmolecularpropertypredictionofbladdercancertherapeutics
AT ateffhashem graphtheoreticandmachinelearningapproachesinmolecularpropertypredictionofbladdercancertherapeutics
AT muhammadfarhanhanif graphtheoreticandmachinelearningapproachesinmolecularpropertypredictionofbladdercancertherapeutics
AT osmanabubakarfiidow graphtheoreticandmachinelearningapproachesinmolecularpropertypredictionofbladdercancertherapeutics