# AI for Bioinformatics
Developing intelligent algorithms using AI and deep learning to analyze large-scale biological data, enabling efficient omics interpretation, biomarker discovery, and biological problem solving.
Back to top ↑Research
We develop intelligent algorithms at the interface of AI and computational biology—spanning sequence-to-structure modeling, large-scale omics analysis, single-cell multi-omics integration, and AI-guided therapeutics design.
# Genomic and Transcriptomic Data Analysis
Designing scalable algorithms and pipelines for genome alignment, variant calling, haplotype phasing, isoform identification & quantification, and fusion detection, supporting accurate and robust interpretation of large-scale sequencing datasets.
Back to top ↑# Cancer Genomics and Precision Medicine
Uncovering somatic mutations, tumor subclones, lineage construction and evolutionary dynamics to identify biomarkers and therapeutic targets, driving precision oncology and personalized treatment strategies.
Back to top ↑# Single-cell Multi-omics Data Imputation
Developing machine learning methods for integrating and imputing single-cell multi-omics data in gene and isoform resolution, resolving sparsity and heterogeneity to reveal cellular states and regulatory mechanisms.
Back to top ↑# AI-Driven Drug Design and Ligand Docking
Applying AI and structural modeling to predict protein–ligand interactions, optimize binding affinity, and design novel compounds, accelerating therapeutic discovery and reducing development costs.
Back to top ↑# AI-Driven TCR Generation and Immunotherapy
Leveraging generative models and binding prediction frameworks to design high-affinity TCRs, advancing personalized immunotherapy and TCR‑T cell engineering for cancer treatment.
Back to top ↑