Biomaterials-based technology can be speedily produced at the rate of hundreds (if not thousands) of unique samples daily due to extraordinary technological advances in miniaturisation, automation and robot assembly.
The ability of biomaterials to effectively generate biological tissue is multifactorial and strongly influenced by the extent of cell-material interactions, which can be measured across a plethora of parameters (which can sometimes be in the hundreds) using high-throughput gene expression and imaging assays at relatively low cost. Consequently, the biomaterials engineering field is potentially drowning in data.
However, the fields of artificial intelligence (AI), machine learning (ML) and computational modelling have an enormous appetite to work with big data of multiscale complexity and therefore offer huge opportunities to enable efficient biomaterials development and accelerate clinical translation. Additionally, nowadays, high-performance cloud computing is relatively inexpensive and does not need hardware investment, which makes it easier for research labs to use these powerful computational tools.
Examples already exist where tools for managing big data are being used in biomaterials research.
High-throughput experimentation that produces thousands of measurements per sample is powerful tools for quantifying cell–material interaction that will add power to the analysis of biological effect induced by materials properties. With advances in miniaturisation and automation and material fabrication, thousands of biomaterial samples can be produced rapidly, which can then be characterised using these assays. However, the resulting amount of data can be crushing and computational methods are now being used to make sense of the data. Machine learning techniques offer a considerable collection of tools to enable predictions about optimal biomaterials design and cell-material interactions to discover patterns in desirable cellular responses. Computational simulations allow researchers to set and test hypotheses and perform experiments in silico.
Groen et al.  reported recently in a highly impressive review paper published in Acta Biomaterialia that “combining multiple computational methods to deal with both the biological and the material complexity simultaneously would facilitate the development of innovative, new tissue regeneration applications. New insights in biology and full cellular response assessments are necessary to adequately address the effect of material properties on the organism.” Additionally, they highlighted that to adopt a multidisciplinary team approach is paramount in order to be successful in converging integrating the multiscale approaches of AI, ML and computational modelling with “the different omics fields“ , i.e. technologies that measure some characteristic of a large family of cellular molecules, such as genes, proteins, or small metabolites.
So the future is bright for Biomaterials by leveraging the research power at the intersection of Science, Biology and Computing.
Please share your views and opinions on the opportunities and challenges in bringing these very different worlds together.
 Groen N, Guvendiren M, Rabitz H, Welsh WJ, Kohn J, De Boer J. Stepping into the omics era: Opportunities and challenges for biomaterials science and engineering. Acta Biomaterialia. 2016 Apr 1;34:133-42.