Convergence Research and Training in Computational Bioengineering: A Case Study on AI/ML-Driven Biofilm–Material Interaction Discovery

Abstract

Historically, research disciplines have successfully operated independently. However, the emergence of transdisciplinary research has led to convergence methodologies, resulting in groundbreaking discoveries. Despite the benefits, graduate programs face challenges in implementing transdisciplinary research and preparing students for real-world collaboration across diverse disciplines and experience levels. We propose a convergence training framework integrating project-based learning, training modules, and collaborative teaming to address this. This approach, tested in a multi-institutional workshop, proved effective in bridging expertise gaps and fostering successful convergence learning experiences in computational biointerface (material–biology interface) research. Here, biointerface research focuses on control of biomolecular interactions with technologically relevant material surfaces, which is a critical component of biotechnology and engineering applications. Positive outcomes, including conference presentations and published models, endorse the framework's application in graduate curricula, particularly for students engaging in transdisciplinary collaboration.