Abstract
<title>Abstract</title> <p> <bold>Introduction:</bold> Metabolic dysfunction-associated steatotic liver disease (MASLD) is the leading cause of chronic liver disease worldwide and is characterized by complex interactions among metabolic, inflammatory, and fibrogenic pathways. Current pharmacological strategies predominantly target single molecular mechanisms, limiting their ability to address the multifactorial nature of the disease. <bold>Objective</bold> : To develop an integrative computational framework for rational multi-target drug discovery in MASLD and evaluate its feasibility through the de novo design of a candidate small molecule. <bold>Methods</bold> : An end-to-end computational pipeline integrating systems biology, network pharmacology, machine learning, generative artificial intelligence, molecular docking, molecular dynamics, quantitative systems pharmacology, and virtual-patient simulation was developed to identify key regulatory networks, prioritize therapeutic targets, design a novel multi-target compound, and predict its pharmacological profile. <bold>Results:</bold> The framework identified a complementary therapeutic network involving SREBP1, AMPKα1, PPARδ, NLRP3, and FXR. The de novo generated molecule, Hepatocyte Precision Metabolic Modulator-001 (HPM-001), demonstrated consistent predicted binding across all prioritized targets, stable protein-ligand interactions during molecular dynamics simulations, and favorable in silico pharmacokinetic and safety profiles. Systems pharmacology and digital-twin simulations predicted coordinated modulation of lipid metabolism and inflammatory pathways, supporting the biological plausibility of the proposed multi-target strategy. <bold>Conclusions</bold> : This study establishes a reproducible computational framework for AI-guided multi-target drug discovery in MASLD and identifies HPM-001 as a proof-of-concept candidate for further experimental validation. These findings support the use of integrated computational approaches to accelerate the prioritization of polypharmacological therapies for complex metabolic diseases. </p>