PNNL

Bill Cannon, senior scientist and biophysicist in the Computational Mathematics Group, was a co-author of a recent article published in Nature Partner Journals-Digital Medicine.

The November 25 article, “Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences,” explores further expanding the frontiers of combining data-driven and theory-driven decisions to benefit human health. The authors suggest opportunities for advances in biological, biomedical, and behavioral sciences through a combination of machine learning and multiscale modeling.

“Over the past two decades,” the authors write, “multiscale modeling has emerged into a promising tool to build individual organ models by systematically integrating knowledge from the tissue, cellular, and molecular levels.”

And machine learning “allows us to systematically preprocess massive amounts of data, integrate and analyze it from different input modalities and different levels of fidelity, identify correlations, and infer the dynamics of the overall system.”

The authors suggest the integrated approach of using machine learning and multiscale modeling “would allow us to improve health, sports, and education by integrating population data with personalized data, all adjusted in real time, on the basis of continuously recorded health and lifestyle parameters from various sources.”

Cannon says “the integration of data-driven and theory-driven approaches will likely be much more powerful than pure data-driven approaches in biology and will change the way that we think about biological systems.”

Cannon is currently employing hybrid machine learning-multiscale modeling methods to elucidate regulation and control in complex biological systems