Abstract
•Drug discovery has been advanced to a big data era with a large amount of public data sources available.•Ten V features (volume, velocity, variety, veracity, validity, vocabulary, venue, visualization, volatility, and value) bring new challenges to machine learning modeling.•Recent progress of machine learning to deep learning and the development of new algorithms answers the big data challenges.
Advancing a new drug to market requires substantial investments in time as well as financial resources. Crucial bioactivities for drug candidates, including their efficacy, pharmacokinetics (PK), and adverse effects, need to be investigated during drug development. With advancements in chemical synthesis and biological screening technologies over the past decade, a large amount of biological data points for millions of small molecules have been generated and are stored in various databases. These accumulated data, combined with new machine learning (ML) approaches, such as deep learning, have shown great potential to provide insights into relevant chemical structures to predict in vitro, in vivo, and clinical outcomes, thereby advancing drug discovery and development in the big data era.