Research Aim

Natural soft materials, such as muscle fibers, skin and mucous membranes, have evolved miraculous material properties. Engineering these properties in synthetic systems is extremely challenging

Data-driven engineering of soft materials can enable targeted design of biobased, biodegradable materials for many advanced applications in biomedicine and materials science, such as tissue regeneration, antifouling and drug delivery. The complexity of biomaterials and the environment in which they typically operate, require a solid understanding of properties of these materials. Although simulations of these materials can to some extend shed light on the behavior of complex chemical systems, the many non-linearities in multicomponent, biobased materials make generalization of simulation insights challenging.

For this reason, we believe that high-throughput experimentation and machine learning on experimental data can drive a new wave of biomaterial design. We are leveraging advances in automated synthesis, high-throughput analysis and machine learning for chemistry to guide the design of biobased soft materials and evolve their properties.