EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrative deep learning strategies to enhance early-stage drug discovery: optimizing computational structure–activity modeling for pharmacotherapeutic innovation

Sarah Rezazi, Cherif Si-Moussa, Salah Hanini

Journal of Pharmacy & Pharmaceutical Sciences · 11.03.2026 · 29

DOI: 10.3389/jpps.2026.16155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Pharmacy & Pharmaceutical Sciences, online erschienen am 11.03.2026. Verfasst von Sarah Rezazi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Sciences, Tipaza University, Tipaza, Algeria. Hauptthemen laut MEDLINE: Drug Discovery, Deep Learning. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of computational intelligence into therapeutic development is increasingly important for accelerating early-stage drug discovery and improving compound prioritization. In this study, we developed an optimized neural network–based predictive framework to support the identification of bioactive compounds with analgesic potential. A dataset of 532 structurally diverse molecules described by 227 molecular descriptors was analyzed, and a stepwise feature elimination procedure reduced the descriptor set to 105 informative variables, improving model robustness and reducing redundancy. The optimized artificial neural network, trained using the Levenberg–Marquardt algorithm, achieved a correlation coefficient of 95.9% with a prediction error of 0.433%, outperforming conventional statistical approaches reported for comparable QSAR tasks. Additional analysis links key descriptor groups, including connectivity and polarity parameters, to physicochemical properties relevant to analgesic activity, improving interpretability for medicinal chemistry applications. The framework is intended to support computational screening and candidate prioritization prior to experimental validation, thereby contributing to more efficient pharmacotherapeutic discovery workflows. This work highlights how data-driven modeling can complement translational strategies aimed at accelerating drug discovery pipelines.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryDeep LearningQuantitative Structure-Activity RelationshipNeural Networks, ComputerHumansPredictive Learning ModelsPrediction AlgorithmsStructure-Activity Relationship

Stichwörter der Autor:innen

computational drug discoverydeep learningneural networkspredictive modelingstructure–activity relationship

Autor:innen und Institutionen

  • Faculty of Sciences, Tipaza University, Tipaza, Algeria.
  • Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Medea, Médéa, Algeria.

Zitieren

APA

Rezazi, S., Si-Moussa, C., & Hanini, S. (2026). Integrative deep learning strategies to enhance early-stage drug discovery: optimizing computational structure–activity modeling for pharmacotherapeutic innovation. Journal of Pharmacy & Pharmaceutical Sciences, 29. https://doi.org/10.3389/jpps.2026.16155

Vancouver

Rezazi S, Si-Moussa C, Hanini S. Integrative deep learning strategies to enhance early-stage drug discovery: optimizing computational structure–activity modeling for pharmacotherapeutic innovation. Journal of Pharmacy & Pharmaceutical Sciences. 2026;29. doi:10.3389/jpps.2026.16155

BibTeX
@article{Rezazi2026,
  author = {Rezazi, Sarah and Si-Moussa, Cherif and Hanini, Salah},
  title = {Integrative deep learning strategies to enhance early-stage drug discovery: optimizing computational structure–activity modeling for pharmacotherapeutic innovation},
  journal = {Journal of Pharmacy & Pharmaceutical Sciences},
  year = {2026},
  volume = {29},
  doi = {10.3389/jpps.2026.16155}
}
Kostenlos starten →