BAID RESEARCH BACKGROUND
The accelerating convergence of artificial intelligence with biomolecular science and biomedicine presents an urgent opportunity to generate meaningful, actionable insights at the molecular scale. At the Biomolecular Artificial Intelligence & Digital Biochemistry (BAID) team, we sit at the intersection of biochemistry, molecular biology, chemistry, pharmaceutical sciences, and computer science. We aim to develop computationally efficient and scalable frameworks for molecular deep learning, machine learning, and representation learning. In parallel, we apply modern computational and state-of-the-art techniques, including molecular docking and molecular dynamics simulation, to decode complex molecular phenomena. Our research tackles persistent challenges in biomedicine and biomolecular science, such as the inefficiencies of drug discovery pipelines (both low- and high-throughput), limited mechanistic understanding of molecular function, and data scarcity for therapeutic target identification.
Our work spans three interconnected research lines: (I) Molecular Representation Learning & Computations, (II) Molecular Discovery & Design, and (III) Molecular Modeling & Simulation. Together, these pillars enable us to build end-to-end pipelines that integrate data analysis, prediction, design, and simulation. Through this integrative and translational approach, we intend to conduct transformative research with real-world biomedical impact—pushing the frontiers of precision medicine, structural biology, and computational methodology.
We appreciate the funding and support from
