Nowadays, the massive amount of data that needs to be processed is increased. High-performance computing (HPC) and big data analytics are required. In the identical context, research on drug discovery has reached an area where it has no preference, but the use of HPC and huge data processing systems to perform its targets at a reasonable time. Virtual screen (VS) is one of the costliest tasks in terms of computation requirements. It is considered as an intensive and heavy task. At the same time, it plays an essential role in new drug design. This research investigates machine learning and big data analytics in VS. It tries to use a ligand base and a structural base and rank molecular databases as active against a specific target protein. The machine learning algorithms, including random forests, naive Bayesian classifiers, nerve networks, decision trees, support vector machines, and deep-learning strategies have been developed for both Ligand-based and structure-based docking. Also, this paper introduces a review of previous research conducted on the utilization of machine learning as well as big data analytics framework in VS. The paper outlines the current progress in the use of traditional methods for machine learning and massive data analytic applications in a multi-node dataset. This article compares the estimation of machine learning approaches and broad ligand-base theoretical system. It also explores how machine learning approaches can improve the performance of various problems of virtual screening classification in broad repositories. Finally, various challenges and solutions of the virtual screening dataset in the machine learning and big data analytics are discussed.