EUVIMEDEUVIMED entdecken
Crossref

AI-Assisted Optimization of Polyherbal Formulations for Diabetes Mellitus Therapy

Veerabathiran Balasubramanian, Neelambari S, Komal Verma, Rajesh KS, Shikha Saxena, Ramanpreet Walia, Shoheb Shakil Shaikh, Swati Madan

International Journal of Drug Delivery Technology · 05.06.2026 · 16 (49s)

DOI: 10.25258/ijddt.16.49s.124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 05.06.2026. Verfasst von Veerabathiran Balasubramanian und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetes mellitus (DM) represents a major global non-communicable disease characterized by persistent hyperglycemia and multifactorial metabolic dysfunction. Although synthetic antidiabetic drugs remain clinically effective, long-term therapy is often associated with adverse effects, limited target specificity, and poor patient adherence. Polyherbal formulations derived from medicinal plants offer synergistic and multitargeted therapeutic potential; however, optimization of such complex combinations remains scientifically challenging. The present study employed artificial intelligence (AI)-assisted computational approaches, including machine learning, network pharmacology, molecular docking, and ADMET prediction, to identify and optimize polyherbal combinations for diabetes management. Eight ethnopharmacologically validated medicinal plants were selected, and phytochemical data were retrieved from PubChem, ChEMBL, IMPPAT, and TCMSP databases. Random forest and artificial neural network models were trained using curated bioactivity datasets to predict antidiabetic efficacy. Molecular docking against key diabetic targets, including DPP-4, PPARγ, α-glucosidase, AMPK, and IRS-1, demonstrated strong binding affinities ranging from −7.4 to −9.8 kcal/mol. Among 347 screened phytoconstituents, 68 satisfied drug-likeness criteria, while the optimized combination of berberine, gymnemic acid, charantin, and curcumin exhibited superior predicted therapeutic potential. Network pharmacology identified multiple enriched pathways associated with insulin signaling and glucose homeostasis. ADMET analysis confirmed favorable pharmacokinetic and toxicity profiles. Overall, this study establishes an evidence-based, non-animal computational framework for precision polyherbal formulation development in diabetes therapy.

Zitieren

APA

Balasubramanian, V., S, N., Verma, K., KS, R., Saxena, S., Walia, R., Shaikh, S. S., & Madan, S. (2026). AI-Assisted Optimization of Polyherbal Formulations for Diabetes Mellitus Therapy. International Journal of Drug Delivery Technology, 16(49s). https://doi.org/10.25258/ijddt.16.49s.124

Vancouver

Balasubramanian V, S N, Verma K, KS R, Saxena S, Walia R, et al. AI-Assisted Optimization of Polyherbal Formulations for Diabetes Mellitus Therapy. International Journal of Drug Delivery Technology. 2026;16(49s). doi:10.25258/ijddt.16.49s.124

BibTeX
@article{Balasubramanian2026,
  author = {Balasubramanian, Veerabathiran and S, Neelambari and Verma, Komal and KS, Rajesh and Saxena, Shikha and Walia, Ramanpreet and Shaikh, Shoheb Shakil and Madan, Swati},
  title = {AI-Assisted Optimization of Polyherbal Formulations for Diabetes Mellitus Therapy},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {49s},
  doi = {10.25258/ijddt.16.49s.124}
}
Kostenlos starten →