A Novel Customized Big Data Analytics Framework for Drug Discovery

Abstract

Drug discovery is related to analytics as the method requires a technique to handle the extremely large volume of structured and unstructured biomedical data of multi-dimensional and complexity from pharmaceutical companies. To tackle the complexity of data and to get better insight into the data, big data analytics can be used to integrate the massive amount of pharmaceutical data and computational tools in an analytic framework. This paper presents an overview of big data analytics in the field of drug discovery and outlines an analytic framework which can be applied to computational drug discovery process and briefly discuss the challenges. Hence, big data analytics may contribute to better drug discovery.

Big data analytics in single‐cell transcriptomics: Five grand opportunities

“…In the era of big data in drug development, high-throughput screening techniques have driven an explosion of the data generated in biomedical research and healthcare systems. Drug discovery methods require methods to handle the enormous volume of structured and unstructured biomedical data (Jainul Fathima & Murugaboopathi, 2018). Effective data analysis and interpretation lead to a better understanding of diseases and the development of more personalized diagnostics and therapeutics (Merelli, Pérez-S anchez, Gesing, & D'Agostino, 2014).…”

Traditional machine learning and big data analytics in virtual screening: a comparative study

“…However, there are still many problems: 1) Large volume of data: Chemical libraries contain up to 10 10 records and this value continues to rise. A large volume of data renders traditional machine learning algorithms insufficient [55], but these algorithms can be used appropriately for these datasets in default scan. Apache Hadoop, MapReduce and Apache Spark are used as tools for big data.…”