From mathematical models and machine learning to clinical reality

Mathematical models are routinely used in the physical and engineering sciences to help understand complex systems and optimize industrial processes. There are numerous examples of the fruitful application of mathematical principles to problems in cell and molecular biology, and recent years have seen increasing interest in applying quantitative techniques to problems in biotechnology. This chapter reviews some ways, in which mathematical models and machine learning may be used to advance our understanding of the complex biological processes involved in cellular differentiation and tissue growth and development, for applications in tissue engineering and regenerative medicine. We will discuss how mathematical models can advance our understanding of stem cell differentiation; growth and development of stem and progenitor cell colonies; and the mechanisms that underpin spatial organization of structure in three-dimensional developing tissues. We will also discuss how recent developments in machine leaning are able to extract biological knowledge from the most complex experimental datasets. We will conclude by considering how computational techniques can be further applied to the design and optimization of effective tissue engineering strategies for clinical application. Although this field is in its infancy, the appropriate use of mathematical methods has considerable potential to transform tissue engineering from experimental concept to clinical reality