Within our lab, we aim to formulate a range of biomedical challenges into AI-driven problems by designing powerful deep learning architectures and developing efficient computational frameworks. Our work is mostly problem-driven and methodology focused, and we benefit greatly from close collaborations with experimental labs.
1. Computational methods for regulatory analysis of transcription process.
Computational methods for regulatory analysis of the transcription process are among the core tools in understanding gene expression regulation. In recent years, the explosion of single cell and spatial multiomics data spanning genomics, transcriptomics, and epigenomics allows us to recognize more complex patterns and regulatory mechanisms in transcription processing. For example, prevalent heterogeneity of features such as splicing efficiency across cell types and contexts, the dynamic interplay between RNA-binding proteins and cis-regulatory elements. Based on available high-throughput sequencing data, we are interested in finding the biological mechanisms and driving factors of such patterns, and how to combine these factors into transcriptional regulatory analyses.
2. Artificial intelligence-driven transcript isoform analysis.
Single-cell and spatial transcriptomics provide powerful paradigms for resolving transcriptomic heterogeneity across cell types, states, and tissue microenvironments. However, accurately identifying full-length transcript isoforms remains challenging because of sparse sequencing coverage and the complex regulation of RNA processing. We aim to develop computational and artificial intelligence-based tools for detecting and quantifying alternative splicing, alternative transcription start sites, and alternative polyadenylation and termination sites at single-cell and spatial resolution. Furthermore, we seek to characterize how these transcript-level regulatory events vary across cell populations and spatial niches, bridging isoform discovery with a mechanistic understanding of gene regulation in development, immunity, and disease.
3. Clinical tumor single-cell and spatial transcriptomics.
Single-cell and spatial transcriptomics provide powerful approaches for
dissecting tumor heterogeneity and the complex organization of the
tumor microenvironment. We collaborate closely with clinicians to
analyze single-cell and spatial transcriptomic data from patient-derived
tumor samples, integrating molecular profiles with pathological and clinical
information. We aim to characterize malignant cell states, immune and stromal
populations, cell–cell interactions, and spatial niches associated with tumor
progression, metastasis, treatment response, and drug resistance.
Through these interdisciplinary collaborations, we seek to identify clinically
relevant biomarkers and therapeutic targets, translating multi-omics data into
mechanistic insights and potential strategies for precision oncology.