Machine Learning, Modeling, and Discovery
Introduction
In the era of data-driven science, our lab integrates machine learning (ML) and computational modeling to accelerate discovery in tissue engineering, drug delivery, diagnostics, and regenerative medicine. By combining biological data, experimental results, and advanced algorithms, we unlock patterns and predictive insights that are often hidden from traditional analysis.
Our work focuses on:
Predictive Modeling of Biological Systems
Apply supervised and unsupervised learning to model cell behavior, tissue regeneration, drug response, and disease progression—guiding the development of smarter biomaterials and therapies.Optimization of Biomaterial Formulations
Use machine learning to fine-tune scaffold designs, hydrogel compositions, and drug release profiles—reducing trial-and-error and enhancing functional performance.High-Throughput Data from Microfluidics
Combine AI with microfluidic systems to generate real-time, large-scale data on cellular responses, drug screening, and microscale fluid dynamics—enabling efficient, low-volume experimentation.Data-Driven Discovery
Build analytical pipelines for imaging, gene expression, and biomechanical datasets—fueling hypothesis generation and supporting precision medicine.Human-in-the-Loop Systems
Design ML systems that incorporate expert feedback, ensuring interpretability, iterative improvement, and scientific validity in predictions.
By fusing experimental biology, AI, and microfluidic technologies, we aim to push the boundaries of biomedical innovation and support the translation of lab findings into clinical solutions.
