This research, employing computational methodologies, aimed to discover potential inhibitors for the nucleotide-binding oligomerization domain-like receptor protein 3 (NLRP3), an intracellular sensor pivotal in in ammation and various disease processes. Despite NLRP3's critical role, there remains a research gap in the identi cation of novel inhibitors, making this study's objective signi cant. Through statistical techniques such as principal component analysis (PCA) and K-means clustering, data re nement and division was conducted in this research, leading to a more targeted set of potential inhibitors. By employing stepwise and subset multiple linear regression, a two-dimensional quantitative structureactivity relationship (2D-QSAR) model was developed, revealing six essential molecular descriptors for inhibitory activity. The interpretation of these descriptors led to the proposition of ve potential compounds. One of these proposed compounds demonstrated remarkable binding a nity through molecular docking studies, marking it as a promising inhibitor of NLRP3. Further veri cation of this compound's potential was conducted via molecular dynamics simulations, a rming its stability and interactions within the protein-ligand system. Compliance with lipinski's rule of ve indicated the drug-like properties of the proposed compounds and their potential for oral bioavailability. Consequently, these ndings present a comprehensive methodology for the discovery and evaluation of novel NLRP3 inhibitors, signi cantly contributing to potential therapeutic advancements.