Identification of protein-ligand interaction networks on a proteome scale is crucial to address a wide range of biological problems such as correlating molecular functions to physiological processes and designing safe and efficient therapeutics. In this study we have developed a novel computational strategy to identify ligand binding profiles of proteins across gene families and applied it to predicting protein functions, elucidating molecular mechanisms of drug adverse effects, and repositioning safe pharmaceuticals to treat different diseases The resultant network is then extrapolated to proteomics level to sort out the genes only expressed in the specific cancer types. The network is statistically analyzed and represented by the graphical interpretation to encounter the hub nodes. The objective of developing a biological networking is for the evaluation and validation of cancer drugs and their targets. In the field of cancer biology, the drug and their targets holds a role of paramount importance. With the work conducted here it shows the study of relation between drug target networks. Lung cancer is one of the main types of cancer in which the lung tissues are affected Genes belonging to the group of proto-oncogenes and tumor suppressors are best targeted for cancer studies. Biological networks like gene regulatory networks, protein interaction network is usually created to simplify the studies. The genes were collected from OMIM database for the lung cancer, respective targets were found using PDB and Gene Cards using the VisANT the biological networks has been drawn. From the literature study about 40 metalloproteinase inhibitors were collected and out of those 12 molecules show anticancer activity against lung cancer. The flexible docking has been performed for Target Protein Vs 12 compounds, Using the best docking score, the graphs obtained from the docking analysis is statistically validated with the help of VisANT. The compound with best docking score were subjected to ADMETOX through which it drawn out the potential candidate using ADME/TOX WEB. Thus out of 12 natural molecules one molecule was selected namely Eicosapentaenoic Acid where it showed the best docking score as well as average ADME property.