The amount of biological bigdata is increasing day by day making it a challenge for the data scientist to analyse the data. Various machine learning approaches have been introduced to perform different biological problems. Here the application of such tools designed based on machine learning algorithms to make a comprehensive pharmacophoric analysis of ‘APOBEC3B gene responsiveness’ towards breast cancer and to find a potential molecule to down-regulate the mutation have been demonstrated. Gene enrichment of APOBEC3B (A3B) mutations have been studied. Biomolecular Networking has been used to identify protein and drug molecules interacting with APOBEC3B. Ligand library has been created by generating evolutionary molecules. The ligand molecules were screened for interaction study. The ligand-target complex was evaluated through molecular dynamic simulation. Cytarabine has been identified as the control drug. The evolutionary molecule of cytarabine, C8H14O4 showed good interaction with APOBEC3B. The application of machine learning algorithms in drug designing have been demonstrated by identifying the potential ligand molecule for down-regulating APOBEC3B mutation.