Downloads: 1
Research Paper | Pharmaceutical Science | Volume 15 Issue 2, February 2026 | Pages: 532 - 536 | Sri Lanka
AI-Assisted Virtual Screening Combined with Dual-Target Molecular Docking for Identification of ACE2 and TMPRSS2 Inhibitors in SARS-CoV-2 Therapeutic Development
Abstract: Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) initiates infection through binding of its spike glycoprotein to angiotensin-converting enzyme 2 (ACE2), followed by proteolytic activation mediated by transmembrane serine protease 2 (TMPRSS2). Simultaneous inhibition of ACE2 and TMPRSS2 offers a promising strategy to block viral entry and limit disease progression. However, conventional drug discovery approaches are time-consuming and inefficient during global health emergencies. This doctoral study integrated artificial intelligence (AI) assisted virtual screening with structure-based molecular docking to identify potential dual ACE2/TMPRSS2 inhibitors from large chemical libraries. Machine learning models were employed to prioritize compounds according to predicted bioactivity and suitability for drug development. Selected candidates were docked against ACE2 and TMPRSS2 using AutoDock Vina. Protein?ligand interactions were analyzed using Discovery Studio Visualizer. Pharmacokinetic properties and toxicity profiles were evaluated using SwissADME and pkCSM. Ensemble docking, advanced ADMET filtering, and network pharmacology were incorporated to strengthen lead selection. Several lead compounds demonstrated strong binding affinities to both ACE2 and TMPRSS2 (-8.7 to -10.8 kcal/mol), forming stable hydrogen bonds and hydrophobic interactions with critical residues involved in viral entry. ADMET profiling revealed favorable oral bioavailability, acceptable metabolic stability, and low predicted cardiotoxicity. AI-based prioritization significantly reduced screening time while improving hit identification efficiency. Network pharmacology suggested modulation of inflammatory and viral-entry pathways. The integrated AI-docking framework successfully identified dual-target inhibitors with promising pharmacological characteristics. These findings support further experimental validation and highlight the potential of artificial intelligence-driven computational pharmacology in accelerating antiviral drug discovery.
Keywords: AI drug discovery, ACE2, TMPRSS2, molecular docking, ADMET, COVID-19 therapeutics
How to Cite?: Rathnayaka Mudiyanselage Isuru Gayashan Wijiesinghe, "AI-Assisted Virtual Screening Combined with Dual-Target Molecular Docking for Identification of ACE2 and TMPRSS2 Inhibitors in SARS-CoV-2 Therapeutic Development", Volume 15 Issue 2, February 2026, International Journal of Science and Research (IJSR), Pages: 532-536, https://www.ijsr.net/getabstract.php?paperid=SR26202235746, DOI: https://dx.dx.doi.org/10.21275/SR26202235746