The current rapid expansion of biomedical data is often referred to as a data tsunami and represents both a challenge and an opportunity for quality healthcare. The rise of 'Big Data' comes from a variety of sources including the increase in large volume data sets such as genomics, the expanded use of high-dimensional data sets including electronic health records, and the increased use of mobile applications and wireless devices to monitor a variety of data types. The volume, variety, and velocity of data generation all contribute to the ‘Big Data’ problem. Specifically, the explosion of data creates challenges ranging from acquisition and processing, to storage and transfer, to analysis and visualization. The overarching challenge of the ‘Big Data’ paradigm in the biomedical sciences is how to convert data to increased understanding and ultimately improve the detection and treatment of diseases. This session focuses on how bringing together perspectives from the physical sciences, life sciences, and engineering can lead from ‘Big Data’ to knowledge, and ultimately drive discovery and innovation. Applications of 'Big Data' to a variety of aspects of science and medicine will be discussed. Presentations cover topics in crowdsourcing scientific problems, the use of large scale and high-dimensional data sets to address complex problems, applications of 'Big Data' in healthcare and education, and the use of integrated computational models to derive knowledge from data.