Mapping Biomaterial Complexity by Machine Learning

Abstract

Biomaterials often have subtle properties that ultimately drive their bespoke performance. Given this nuanced structure-function behavior, the standard scientific approach of one experiment at a time or design of experiment methods is largely inefficient for the discovery of complex biomaterials. More recently, high-throughput experimentation coupled with machine learning methods has matured beyond expert users allowing scientists and engineers from diverse backgrounds to access these powerful data science tools. As a result, we now have the opportunity to strategically utilize all available data from high-throughput experiments to train efficacious models and map the structure-function behavior of biomaterials for their discovery. Herein, we discuss this necessary shift to data-driven determination of structure-function properties of biomaterials as we highlight how machine learning is leveraged in identifying physicochemical cues for biomaterials in tissue engineering, gene delivery, drug delivery, protein stabilization, and antifouling materials. We also discuss data-mining approaches that are coupled with machine learning to map biomaterial functions that reduce the load on experimental approaches for faster biomaterial discovery. Ultimately, harnessing the prowess of machine learning will lead to accelerated discovery and development of optimal biomaterial designs.

Keywords: biomaterials; data mining; high-throughput experimentation; machine learning; structure–property relationships; tissue engineering.

FIG. 1.

Curse of dimensionality exemplified in the process of wetting a scaffold. Arrows show complex interactions between the scaffold’s intrinsic structural properties (gray boxes), the scaffold’s environment (red boxes), and the unfolding physicochemical processes (blue boxes). Created with BioRender.com.

FIG. 2.

A design–build–test–learn closed-loop workflow for developing polymeric scaffolds. Starting at the top left, scaffold design features are determined, followed by building the scaffold using techniques such as 3D bioprinting and electrospinning. Next, the scaffold is tested in vitro and characterized. Testing and characterization data are used to train machine learning models. At the end of the cycle, the models make predictions using new and existing data for enhanced scaffold design features, and a new iteration begins. Created with BioRender.com.

FIG. 3.

Different aspects of tissue engineering scaffold development that can be empowered by machine learning. Created with BioRender.com.

FIG. 4.

A framework proposed by Sujeeun et. al., in which they hypothesized that in vitro cell data can be coupled with machine learning to predict scaffold performance in vivo. Figure adapted from Ref.