EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight

Mahesh Koirala iD, Lindy Yan, Zoser Mohamed, Mario DiPaola iD

International Journal of Molecular Sciences · 25.09.2025 · 26 (19) · 9384

DOI: 10.3390/ijms26199384 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 25.09.2025. Verfasst von Mahesh Koirala und 3 weiteren Autor:innen. Beteiligte Einrichtung: Therabene Inc., Norwood, MA 02062, USA. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Drug Discovery, Deep Learning, Artificial Intelligence. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 155 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrating artificial intelligence (AI) with the Quantitative Structure-Activity Relationship (QSAR) has transformed modern drug discovery by empowering faster, more accurate, and scalable identification of therapeutic compounds. This review outlines the evolution from classical QSAR methods, such as multiple linear regression and partial least squares, to advanced machine learning and deep learning approaches, including graph neural networks and SMILES-based transformers. Molecular docking and molecular dynamics simulations are presented as cooperative tools that boost the mechanistic consideration and structural insight into the ligand-target interactions. Discussions on using PROTACs and targeted protein degradation, ADMET prediction, and public databases and cloud-based platforms to democratize access to computational modeling are well presented with priority. Challenges related to authentication, interpretability, regulatory standards, and ethical concerns are examined, along with emerging patterns in AI-driven drug development. This review is a guideline for using computational models and databases in explainable, data-rich and profound drug discovery pipelines.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipDrug DiscoveryDeep LearningArtificial IntelligenceHumansMolecular Docking SimulationMolecular Dynamics Simulation

Stichwörter der Autor:innen

ADMET predictionPROTACsQSAR modelingartificial intelligencecheminformaticsdeep learningdrug discoverygraph neural networksmachine learningmolecular dockingmolecular dynamics

Autor:innen und Institutionen

  • Therabene Inc., Norwood, MA 02062, USA.

ORCID-Profile: Mahesh Koirala, Mario DiPaola

Zitieren

APA

Koirala, M., Yan, L., Mohamed, Z., & DiPaola, M. (2025). AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight. International Journal of Molecular Sciences, 26(19), 9384. https://doi.org/10.3390/ijms26199384

Vancouver

Koirala M, Yan L, Mohamed Z, DiPaola M. AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight. International Journal of Molecular Sciences. 2025;26(19):9384. doi:10.3390/ijms26199384

BibTeX
@article{Koirala2025,
  author = {Koirala, Mahesh and Yan, Lindy and Mohamed, Zoser and DiPaola, Mario},
  title = {AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  volume = {26},
  number = {19},
  pages = {9384},
  doi = {10.3390/ijms26199384}
}
Kostenlos starten →