TY  - JOUR
TI  - Network pharmacology and machine learning reveal multi-target mechanisms of poly herbal formulation against atherosclerosis
AU  - Shafique, Muhammad
AU  - Ghori, Muhammad Umer
AU  - Hassan, Mubashir
AU  - Ashfaq, Usman Ali
AU  - Masoud, Muhammad Shareef
JO  - Pakistan Journal of Pharmaceutical Sciences
JA  - Pak. J. Pharm. Sci.
VL  - 39
IS  - 5
SP  - 1578
EP  - 1589
PY  - 2026
DA  - 2026/05
KW  - Atherosclerosis
KW  - Allium sativum
KW  - Bioinformatics
KW  - Ginkgo biloba
KW  - Network pharmacology
KW  - Nerium oleander
DO  - 10.36721/PJPS.2026.39.5.REG.13645.1
AB  - Background: Medicinal herbs such as Allium sativum, Ginkgo biloba and Nerium oleander have traditionally been used for the treatment of atherosclerosis and cardiovascular diseases. This study investigates how network pharmacology and machine learning approaches can be utilized to identify potential therapeutic compounds from these plants against atherosclerosis. Methods: Network pharmacology analysis was applied to identify active compounds and their potential gene targets using databases and tools including IMPPAT, PubChem, KNAPSACK, SwissADME, SwissTargetPrediction, DisGeNET and GeneCards. Cytoscape 3.10.2 was used to visualize compound–target networks. Functional enrichment analysis was performed using the DAVID database, and candidate targets were validated through molecular docking using PyRx and Discovery Studio. Results: Bioinformatics and computational analyses identified several key compounds, including quercetin, naringenin, luteolin, kaempferol, apigenin, daidzein, luteolin-7-olate, pinocembrin, pregnenolone and fisetin, as potential therapeutic agents against atherosclerosis. Pathway analysis indicated that atherosclerosis progression is closely associated with cholesterol metabolism, cellular senescence and signaling pathways such as Ras, NF-κB and PI3K-Akt. Conclusion: Network pharmacology and molecular docking results suggest that these phytochemicals may inhibit atherosclerosis progression by modulating multiple biological pathways. This machine learning-assisted network pharmacology study provides a theoretical basis for understanding the therapeutic potential of these medicinal plants in atherosclerosis management.
ER  -