SUMMARY
As a cancer researcher in the field of artificial intelligence (AI) and informatics, Tae Hyun Hwang, Ph.D., is building an internationally recognized AI in Oncology Program for Mayo Clinic. He leads translational machine learning and AI research for precision oncology, immuno-oncology, and cellular therapy in cancer.
He works with a team of other researchers to develop and implement novel machine learning and AI algorithms to help solve clinically relevant gastric cancer challenges. This includes learning if there are biological mechanisms that computational approaches can solve.
Dr. Hwang and his team also are working to develop new assays based on the expression level of a single gene, or several genes, to make biomarkers more accessible and easily deployed in the clinical setting. They also are studying the molecular mechanisms of immunotherapy resistance made available by machine learning and AI approaches.
Dr. Hwang develops machine learning, data mining, and bioinformatics methodology to identify prognostic and predictive biomarkers and build predictive models for clinical outcome prediction and treatment stratification. Using genomic sequencing and AI algorithms that use diagnostic histopathology images, his team is building a model to predict the likelihood that patients with gastric cancer will benefit from chemotherapy or immunotherapy.
To build this model, Dr. Hwang and his team developed and implemented a machine learning algorithm that integrated genetic data from more than 5,000 patients. Then the team developed a molecular signature consisting of 32 genes that could be used to guide patient care decisions.
Focus areas
- AI and 3D molecular tumor modeling driven by machine learning. Dr. Hwang advances AI-driven 3D molecular tumor models to study precancer stages and their progression. He maps the multidimensional evolution of tumors, providing critical insights into cancer development and treatment response.
- Subcellular-resolution 3D and 4D atlas models. Dr. Hwang develops subcellular-resolution 3D and 4D atlas models powered by AI and machine learning with a combination of holotomography and light sheet microscopy technologies. He uses these models to investigate how individual cells, their suborganelles, and even full 3D models of organs and organisms contribute to disease processes. Dr. Hwang uses live 3D and 4D holotomography, combined with molecular data, to track cellular dynamics in real time — uncovering novel insights into disease initiation, progression, metastasis, and therapeutic response.
- Spatial microbiome in the tumor immune microenvironment. Using spatial sorting technology, Dr. Hwang isolates individual microorganisms along with their surrounding cellular and noncellular components from a tumor. He studies how these microorganisms impact tumor progression, immune modulation, and treatment response. This approach also could be applied to investigate how fungi, viruses, and other pathogens influence the tumor immune microenvironment.
- 3D spatial multimodal approaches. Dr. Hwang combines spatial sorting and holotomography to isolate individual cells and suborganelles at the tissue level and generate multimodal data, such as DNA, RNA, protein, and methylation, simultaneously. Using this integrated 3D spatial multimodal approach enables Dr. Hwang to comprehensively profile the tumor microenvironment to uncover complex molecular interactions that drive disease progression and treatment response.
- Real-time drug delivery and response using organotypic models. Dr. Hwang employs organotypic models to study drug delivery and therapeutic response in real time, focusing on antibody-drug conjugates, chimeric antigen receptor (CAR)-T cell therapy, and messenger RNA therapeutics. He uses hybrid holotomography and light sheet microscopy to track drug interactions within the tumor immune microenvironment to optimize precision treatment strategies.
Significance to patient care
By combining cutting-edge AI, machine learning, and experimental methodologies, Dr. Hwang aims to uncover the mechanisms driving health and disease, particularly the complex ecosystem surrounding a tumor. Since this environment can either promote or stop the progression of cancer, learning more can help find ways to alter cancer, slow it down, or prevent it from spreading.
The AI models Dr. Hwang creates bring more precise care to patients. These models can predict how patients will respond to treatment. They also can create patient subgroups based on disease characteristics and better guide healthcare professionals as they care for patients with gastric cancer.
Professional highlights
- Florida Department of Health Cancer Chair, Mayo Clinic Comprehensive Cancer Center, 2022-present.
- Member, Molecular Oncology Program, Case Western Reserve University Comprehensive Cancer Center, 2016-present.
- Award, Eric & Wendy Schmidt Fund for AI Research & Innovation, 2024.
- Founder and chair, Artificial Intelligence, Systems and Spatial Biology in Human Disease Conference, Mayo Clinic, 2023-2024.
- American Association for Cancer Research:
- Member, 2013-2022.
- Artificial Intelligence in Oncology Advancements and Policy, 2019-2020.
- Co-director, Data Analysis Core, University of Texas Southwestern Kidney Cancer Specialized Programs of Research Excellence, 2016-2021.
- Global winner, Cancer Transcriptome Atlas Grant, GeoMx Spatial Transcriptome, 2020.
- Member, Program Committee, 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Artificial Intelligence for COVID-19, 2020.
- Director, Bioinformatics Core, NASA Specialized Centers of Research, 2015-2020.