Abstract
scientific research are nowadays faced to very massive data processing, which consume relatively too much time and effort, that's why researchers have turned to high performance computational (HPC) techniques. In the same context, research on drug discovery has reached a place where it has no choice but using HPC and Big Data Processing Systems to accomplish its objectives in reasonable periods of time, Virtual Screening (VS) is considered as one of the most computationally intensive and heavy process, it plays an important role in designing new drugs and has to be done as fast as possible in order to effectively dock ligands in huge databases to a given protein receptor. On the other hand, breast cancer is one of the most dangerous diseases of world, in the last decade; more than 1.5 million new cases are diagnosed each year, with more than 400 thousands deaths. These statistics give very great importance to drug research for this disease. In this context, and in order to ameliorate the drug designing process for breast cancer, we propose in this work, to use Machine Learning Algorithms that are designed for Big Data analysis on top of MapReduce and Mahout in order to pre-filter the huge set of ligands to effectively do virtual screening for the breast cancer protein receptor.