Hwang, Tae-Hyun

Background: Tumor immune microenvironment (TIME) organization fundamentally shapes cancer progression and immunotherapy outcomes. Traditional 2D spatial molecular approaches inadequately capture the complex three-dimensional architecture and cellular interactions within TIME. We developed an AI-driven platform integrating multiple spatial molecular datasets, enabling comprehensive 3D visualization for therapeutic discovery and patient selection. Methods: Our platform combines holotomography imaging, providing 3D refractive index maps, with diverse spatial molecular data: in situ molecular imaging, spatial proteomics, multiplex immunohistochemistry, and spatial transcriptomics. AI algorithms align datasets within a unified 3D coordinate system, while Poisson implicit surface reconstruction generates subcellular-resolution models. Platform validation used clinical samples from immunotherapy-treated patients. Results: The platform integrated multimodal spatial data into high-resolution 3D TIME representations, revealing novel relationships between protein expression, transcriptional patterns, and cellular architecture. 3D surface protein analysis with subcellular morphology identified patients with target protein expression outside tight junctions, indicating higher risk for adverse effects from antibody-drug conjugates and cellular therapies. This insight, unavailable through 2D analysis, enabled precise patient selection. Conclusions: This platform provides detailed subcellular-resolution TIME architecture analysis, offering actionable insights for therapeutic targeting, biomarker discovery, and patient selection. AI-driven 3D spatial multimodal TIME analysis advances precision medicine across multiple therapeutic approaches, including immunotherapy, targeted therapy, and drug delivery optimization. AI Disclosure: Original abstract content was written by the authors. Claude was used for editorial assistance and formatting without altering the scientific content or context of the work. Citation Format: Inyeop Jang, Yoonho Choi, Minji Kim, Jeonghwan Park, Jiyeon Sung, Byungsoo Ann, Clemenceau R. Jean, TaeHyun Hwang. AI-enabled 3D multimodal integration platform reveals subcellular architecture of tumor immune microenvironment for therapeutic target and biomarker discovery and patient selection [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 3648.

AbstractMotivation: A central problem in biomarker discovery from large-scale gene expression or single nucleotide polymorphism (SNP) data is the computational challenge of taking into account the dependence among all the features. Methods that ignore the dependence usually identify non-reproducible biomarkers across independent datasets. We introduce a new graph-based semi-supervised feature classification algorithm to identify discriminative disease markers by learning on bipartite graphs. Our algorithm directly classifies the feature nodes in a bipartite graph as positive, negative or neutral with network propagation to capture the dependence among both samples and features (clinical and genetic variables) by exploring bi-cluster structures in a graph. Two features of our algorithm are: (1) our algorithm can find a global optimal labeling to capture the dependence among all the features and thus, generates highly reproducible results across independent microarray or other high-thoughput datasets, (2) our algorithm is capable of handling hundreds of thousands of features and thus, is particularly useful for biomarker identification from high-throughput gene expression and SNP data. In addition, although designed for classifying features, our algorithm can also simultaneously classify test samples for disease prognosis/diagnosis.Results: We applied the network propagation algorithm to study three large-scale breast cancer datasets. Our algorithm achieved competitive classification performance compared with SVMs and other baseline methods, and identified several markers with clinical or biological relevance with the disease. More importantly, our algorithm also identified highly reproducible marker genes and enriched functions from the independent datasets.Availability: Supplementary results and source code are available at http://compbio.cs.umn.edu/Feature_Class.Contact: kuang@cs.umn.eduSupplementary information: Supplementary data are available at Bioinformatics online.