Machine-Learning-Driven Molecular Design and Structure–Property–Performance Relationships in Pharmaceutical Chemistry
Molecules · 19.06.2026 · 31 (12) · 2162
DOI: 10.3390/molecules31122162 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Molecules, online erschienen am 19.06.2026. Verfasst von Aisulu Zh Kabdraisova und 12 weiteren Autor:innen. Beteiligte Einrichtung: Scientific Research Institute for New Chemical Technologies and Materials, Farabi University, 96a Tole Bi Str., 050012 Almaty, Kazakhstan. Hauptthemen laut MEDLINE: Machine Learning, Chemistry, Pharmaceutical, Drug Design. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 101 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan, Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan.
Abstract (Originalsprache)
This review examines the emerging role of machine learning (ML) in pharmaceutical chemistry, with emphasis on molecular design, synthetic feasibility, and structure–property–performance (SPP) relationships. By enabling pre-synthesis prediction of physicochemical properties, reaction pathways, and pharmaceutical performance, ML can reduce empirical trial-and-error experimentation and support more efficient exploration of chemical space. A structured narrative review design with PRISMA-aligned systematic search elements was used to evaluate 101 studies, enabling transparent literature identification, eligibility screening, and thematic synthesis across heterogeneous ML applications in pharmaceutical chemistry. This review examines structure–property relationships (SPRs) and property–performance relationships (PPRs), with emphasis on key pharmaceutical endpoints such as solubility, permeability, stability, dissolution, and bioavailability. An integrated SPP framework is proposed to connect molecular structure, intermediate properties, and final performance outcomes while incorporating retrosynthetic analysis and experimental feedback and closed-loop optimization. Recent frontier developments are also discussed, including molecular foundation models, multimodal language–graph models, diffusion-based molecular generation, E(3)-equivariant models, and MolMIM-like latent-space optimization. This review also covers co-folding and joint ligand–protein modeling, Boltz-2-like affinity prediction, AlphaFold 3-related biomolecular interaction modeling, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction. Key limitations include dataset leakage, benchmark inconsistency, assay variability, conformational and protonation-state effects, reproducibility challenges, regulatory constraints, and the gap between computational prediction and prospective experimental validation. Future progress is expected to depend on hybrid physics–ML models, uncertainty-aware prospective validation, autonomous experimentation, explainable artificial intelligence, and sustainability-aware molecular design. Overall, ML is evolving from a predictive tool into a chemically informed decision-support framework for rational, synthesis-aware, and experimentally validated pharmaceutical development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Scientific Research Institute for New Chemical Technologies and Materials, Farabi University, 96a Tole Bi Str., 050012 Almaty, Kazakhstan.
- Branch Office of the Republican State Enterprise "Infracos", Abay Ave. 191, 050046 Almaty, Kazakhstan.
- Department of Chemistry and Technology of Organic Substances, Chemistry of Natural Compounds and Polymers, Faculty of Chemistry and Chemical Technology, Farabi University, Al-Farabi Ave. 71, 050040 Almaty, Kazakhstan.
- Department of Physical Chemistry, Catalysis and Petrochemistry, Faculty of Chemistry and Chemical Technology, Farabi University, Al-Farabi Ave. 71, 050040 Almaty, Kazakhstan.
- JSC Scientific Center for Anti-Infectious Drugs, Al-Farabi Ave. 75B, 050060 Almaty, Kazakhstan.
ORCID-Profile: Aisulu Zh Kabdraisova, Almagul K Umbetova, Yuliya A Litvinenko, Larissa R Sassykova, Nazym S Yelibayeva, Gauhar Sh Burasheva, Aliya E Berganayeva, Zhanibek S Assylkhanov, Meruyert D Dauletova, Dmitriy Yu Korulkin, Marzhan A Baiburkutova, Aigerim M Sadvakas
Förderung
- the Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan
- Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan
Zitieren
APA
Kabdraisova, A. Z., Umbetova, A. K., Kairalapova, G. Z., Litvinenko, Y. A., Sassykova, L. R., Yelibayeva, N. S., Burasheva, G. S., Berganayeva, A. E., Assylkhanov, Z. S., Dauletova, M. D., Korulkin, D. Y., Baiburkutova, M. A., & Sadvakas, A. M. (2026). Machine-Learning-Driven Molecular Design and Structure–Property–Performance Relationships in Pharmaceutical Chemistry. Molecules, 31(12), 2162. https://doi.org/10.3390/molecules31122162
Vancouver
Kabdraisova AZ, Umbetova AK, Kairalapova GZ, Litvinenko YA, Sassykova LR, Yelibayeva NS, et al. Machine-Learning-Driven Molecular Design and Structure–Property–Performance Relationships in Pharmaceutical Chemistry. Molecules. 2026;31(12):2162. doi:10.3390/molecules31122162
BibTeX
@article{Kabdraisova2026,
author = {Kabdraisova, Aisulu Zh and Umbetova, Almagul K and Kairalapova, Gulfairuz Zh and Litvinenko, Yuliya A and Sassykova, Larissa R and Yelibayeva, Nazym S and Burasheva, Gauhar Sh and Berganayeva, Aliya E and Assylkhanov, Zhanibek S and Dauletova, Meruyert D and Korulkin, Dmitriy Yu and Baiburkutova, Marzhan A and Sadvakas, Aigerim M},
title = {Machine-Learning-Driven Molecular Design and Structure–Property–Performance Relationships in Pharmaceutical Chemistry},
journal = {Molecules},
year = {2026},
volume = {31},
number = {12},
pages = {2162},
doi = {10.3390/molecules31122162}
}
EUVIMED