Multi‐Omics and Machine Learning‐Driven Discovery of <scp>ABCC8</scp> ( <scp>SUR1</scp> ) for Diabetes Mellitus: Integrating Molecular Insights on <i>Nigella sativa</i> Bioactives and Sulfonylurea

Diabetes mellitus is a chronic metabolic disorder characterized by hyperglycemia and pancreatic β-cell dysfunction. The ATP-sensitive potassium KATP channel, regulated by ATP-binding cassette subfamily C member 8 (ABCC8/SUR1), plays a pivotal role in insulin secretion, and its dysregulation is associated with neonatal and type 2 diabetes. In this study, we employed an integrated computational framework to explore the structural, regulatory, and ligand-interaction landscape of ABCC8. Transcriptomic analysis of publicly available datasets (GSE41762, GSE25724) indicated significant upregulation of ABCC8 in diabetic samples (q-values: 0.09597 and 0.04781), suggesting a potential compensatory response to hyperglycemia. Structural analyses identified conserved ATP-binding motifs and a predicted disordered region (residues 621-676), which may influence channel gating and interaction dynamics. In silico virtual screening of FDA-approved sulfonylureas and Nigella sativa derived bioactive compounds revealed favorable predicted binding affinities toward ABCC8. Selected N. sativa compounds exhibited docking scores ranging from -4.1 to -9.7 kcal/mol, comparable to those of sulfonylureas (-8.2 to -3.6 kcal/mol). Molecular dynamics simulations further suggested stable protein-ligand complexes based on RMSD, radius of gyration, and solvent-accessible surface area profiles. Pathway enrichment and predictive miRNA analyses implicated ABCC8 in insulin secretion, K ATPchannel regulation, and metabolic signaling pathways, with miR-375 and miR-29 predicted to be involved in ABCC8 regulation. Overall, this study provides computational and predictive insights into ABCC8 structure, regulation, and ligand interactions, highlighting candidate molecules for further investigation. Experimental validation is required to confirm these findings and to evaluate their translational relevance for diabetes management.