Designing cultured tissue moulds using evolutionary strategies

TL;DR

This paper presents an innovative approach combining evolutionary strategies, machine learning, and biophysical simulations to accelerate the design of tissue growth strategies for applications like cultivated meat and regenerative medicine.

Contribution

It introduces a novel method that leverages AI and simulations to efficiently identify effective tissue growth strategies, addressing a key challenge in tissue engineering.

Findings

Successfully designed tethering strategies for diverse tissue types

Achieved high cellular alignment and uniform density in simulated tissues

Demonstrated the method's potential to speed up tissue engineering processes

Abstract

There is an unmet need for artificial intelligence techniques that can speed up the design of growth strategies for cultured tissues. Cultured tissue is increasingly important for a range of applications such as cultivated meat, pharmaceutical assays and regenerative medicine. In this paper, we introduce a method based around evolutionary strategies, machine learning and biophysical simulations that can be used to speed up the process of identifying new tissue growth strategies for these diverse applications. We demonstrate the method by designing tethering strategies to grow tissues containing various cell types with desirable properties such as high cellular alignment and uniform density.