Predictive modeling of asthma drug properties using machine learning and topological indices in a MATLAB based QSPR study

Machine learning is a vital tool in advancing drug development by accurately predicting the physical, chemical, and biological properties of various compounds. This study utilizes MATLAB program-based algorithms to calculate topological indices and machine learning algorithms to explore their abilit...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 15; no. 1; pp. 30373 - 25
Main Authors: Bayati, Jalal Hatem Hussein, Mahboob, Abid, Amin, Laiba, Rasheed, Muhammad Waheed, Alameri, Abdu
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 19.08.2025
Nature Publishing Group
Nature Portfolio
Subjects:
639/166/898
639/166/985
639/638
639/705
Algorithms
Anti-Asthmatic Agents - chemistry
Anti-Asthmatic Agents - pharmacology
Anti-Asthmatic Agents - therapeutic use
Asthma
Asthma - drug therapy
Asthma drugs
Biological properties
Chemical properties
Drug development
Drug Discovery - methods
Extreme gradient boosting
Graphs
Humanities and Social Sciences
Humans
Inflammation
Learning algorithms
Machine Learning
MATLAB and Python algorithm
Molecular structure
multidisciplinary
Physical properties
Quantitative Structure-Activity Relationship
Random forest
Reducible topological descriptors
Science
Science (multidisciplinary)
Trends
MATLAB and Python algorithm
Reducible topological descriptors
Random forest
Extreme gradient boosting
Asthma drugs
Machine learning
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning is a vital tool in advancing drug development by accurately predicting the physical, chemical, and biological properties of various compounds. This study utilizes MATLAB program-based algorithms to calculate topological indices and machine learning algorithms to explore their ability to predict the physio-chemical properties of asthma drugs. By combining machine learning with topological indices, we can conduct faster and more precise analyses of drug structures. As we deepen our understanding of the relationship between molecular structure and performance, the integration of machine learning with QSPR research highlights the significant potential of computational strategies in pharmaceutical discovery. The use of machine learning algorithms such as random forest and extreme gradient boosting is essential in this process. These algorithms leverage labeled data to predict complex molecular processes, aiding in the discovery of new medication options and enhancing their properties. These methods enhance the accuracy of physical and chemical property predictions, streamline the drug discovery process, and efficiently evaluate large datasets through machine learning. Ultimately, these advancements facilitate the development of innovative and effective treatments.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-07022-5