AI-driven biomaterial screening to accelerate medical device development

我们的多学科团队将利用人工智能，计算机模拟和高通量筛选方法的力量，在可持续，快速和合理的框架内为再生医学创造生物材料。生物材料的传统工程方法是昂贵和费力的，这显著阻碍了从实验室到床边的转化。为了缓解这一未满足的挑战，我们将使用组合数值模拟和机器学习模型来生成和分析细胞-生物材料相互作用的大规模和多模态合成数据。这样的应用将有效地缩小材料的选择，并导致假设驱动的实证实验模型验证。含有3D细胞负载水凝胶的新型高通量阵列将用于进行数千项细胞生物材料实验。我们将进一步扩大AI知情材料设计并应用于声带组织工程。最后，我们将对这种新的人工智能驱动的生物材料设计和筛选进行成本分析，并与传统的假设驱动方法进行比较。我们预计，人工智能在生物材料治疗学中的应用将大大减少资金、时间和劳动力，同时加速个性化和精确的生物材料在医疗应用中的发展。

Our multi-disciplinary team will leverage the power of artificial intelligence, computer simulation and high-throughput screening approaches to create biomaterials for regenerative medicine in a sustainable, rapid and rational framework. Conventional engineering processes of biomaterials are expensive and laborious that has significantly impeded the translation from bench to bedside. To mitigate this unmet challenge, we will use combinatorial numerical simulations and machine learning models to generate and analyze large-scale and multi-modality synthetic data of cell-biomaterial interactions. Such application will effectively narrow down material choices and lead to hypothesis-driven empirical experiments for model verification. Novel high-throughput arrays containing 3D cell-laden hydrogels will be used to conduct thousands of cell-biomaterial experiments. We will further scale up the AI-informed material design and apply to vocal fold tissue engineering. Lastly, we will perform a cost analysis of this new AI-driven biomaterial design and screening with that of the conventional hypothesis-driven approach. We anticipate that the implementation of AI in biomaterial therapeutics will dramatically reduce the finance, time and labor while accelerate the development of personalized and precise biomaterials for medical applications.