The choice of docking algorithm is critical in computational biology since it has a substantial impact on the accuracy of predicting molecular interactions. Docking algorithms mimic chemical binding, assisting in drug development and understanding biological processes. The presence of decoys, molecules that imitate real binders but provide deceptive outcomes, creates a problem. Decoys can mislead researchers by providing false positives, therefore retrieval of trustworthy decoy datasets and metrics for evaluating algorithm performance is critical. Computational biologists could enhance the precision and dependability of their predictions by carefully selecting and fine-tuning docking methods, thus improving our knowledge of complicated biological systems in drug development. In this work, data mining was used to identify key biological targets against a disease model, as well as beneficial small molecular decoy compounds for specific protein targets based on their reported bioactivity using an in-house script. Enrichment analysis was used to pick the best potential molecular interaction setup.