Hy Truong SonView profile
Assistant Professor
Dr. Hy Truong Son is an Assistant Professor in the Department of Computer Science at the University of Alabama at Birmingham (UAB), affiliated with the College of Arts and Sciences. He holds a Ph.D. in Computer Science from the University of Chicago and has prior experience as a Lecturer and Postdoctoral Fellow at the Halicioglu Data Science Institute, UC San Diego. His research focuses on AI-driven solutions for science and engineering, particularly deep learning applications in drug discovery, repurposing, and biomedical problem-solving through his HySonLab group. Dr. Son’s educational background includes a Ph.D. from the University of Chicago, emphasizing foundational training in computer science. His postdoctoral work at UC San Diego further solidified his expertise in data science and interdisciplinary AI applications. Research interests span AI for drug discovery, generative AI, multimodal learning, and healthcare technologies. His lab’s work integrates AI with molecular biology, medical imaging, and wearable sensor data to address challenges in precision medicine and environmental science. Notable projects include DrugPipe for drug repurposing and SilVar-Med for explainable medical imaging analysis. His recent publications highlight advancements in generative models, speech synthesis, protein design, and scalable graph neural networks. These works reflect a focus on bridging AI with real-world biomedical and engineering applications. While no awards are explicitly listed, his prolific publication record and active lab indicate significant contributions to the field. He advises students and engineers in his team, fostering collaborative research environments. Ongoing projects include wearable device datasets for mental health and multimodal biomedical knowledge graph development. Dr. Son’s HySonLab group emphasizes translational research, aiming to deploy AI solutions in clinical and scientific settings. Current efforts include optimizing molecular interactions via large language models and enhancing drug discovery pipelines through interdisciplinary computational methods.













