The field of computational chemistry has transformed the process of discovering new drugs by offering sophisticated techniques for designing and improving therapeutic treatments. This has resulted in a major increase in the speed of drug development and a reduction in expenses. These approaches include a range of methods such as molecular modelling, quantum chemistry, molecular dynamics simulations, and machine learning algorithms. Molecular docking and virtual screening enable researchers to anticipate the interactions between possible therapeutic candidates and biological targets, hence improving the identification of promising molecules. Quantum chemistry techniques offer in depth understanding of electronic configurations and reaction processes, enabling the systematic creation of molecules with specific characteristics. Molecular dynamics simulations provide a dynamic perspective on the interactions between molecules and the changes in their shape and structure over time. This enhances our comprehension of the binding of drugs to receptors and the stability of these interactions. Moreover, machine learning algorithms have the capability to analyse extensive information in order to identify trends and forecast biological activities, thereby facilitating th e streamlining of lead chemical optimization. By incorporating these computational techniques, scientists may systematically investigate the range of chemical compounds, enhance the features related to the absorption, distribution, metabolism, and excretio n of drugs, and anticipate any unintended effects on non target molecules. This eventually accelerates the process of creating safer and more efficient treatments.