NSF CHE Workshop on Framing the Role of Big Data and Modern Data Science in Chemistry

PI: Dr. Johannes Hachmann (UB); co-PIs: Dr. John McLean (Vanderbilt University), Dr. Theresa Windus (Iowa State University)
NSF grant no. CHE-1733626

Executive Summary: The 2-day workshop Framing the Role of Big Data and Modern Data Science in Chemistry (funded under NSF grant no. CHE-1733626) was conducted in order to spearhead a broad discussion about the role of big data research and modern data science in chemistry. The workshop set out to articulate the tremendous potential of this emerging field, to address the needs that have to be met – both now and in the long term – in order to fully develop this potential, and to offer suggestions on how this development could be supported beyond existing funding mechanisms. While there is now broad agreement on the value of data-driven approaches and the closely related ideas of rational design, there is still a significant disconnect between its possibilities and the realities of every-day research in the chemical domain. Data science and the use of advanced data mining tools are not part of the regular training of chemists, and the community is thus oftentimes reluctant to engage them. Conversely, chemical applications are generally well beyond the scope of most data and computer scientists, who are the actual experts with respect to these powerful methods. This workshop attempts to chart a path that will allow us to bridge this disconnect, to support and guide the activities of researchers, to provide consensus community directions, and to ultimately advance and shape this emerging field as a focus area. Our long-term objective is to help pioneer a fundamental transformation of the discovery process in chemistry.

You can download the full workshop report here.


This material is based upon work supported by the National Science Foundation under grant no. CHE-1733626. Any opinions, findings, conclusions, and/or recommendations expressed in this material are those of the workshop participants and do not necessarily reflect the views of the National Science Foundation.

(Last update: 2019-04-02)