projects

The Qin AIM Lab builds computational methods at the interface of AI and multi-omics, with a focus on spatial transcriptomics, long-read sequencing, cancer and clinical genomics, and regulatory genomics. Below are the lab’s main research directions and the open-source software we develop and maintain. Each card links to a short overview and the related publications.

research

Single cell and Spatial Multi-Omics

AI-driven methods for single-cell and spatial transcriptomics, with a focus on Xenium and tissue architecture.

Long-Read Sequencing Methodology

Algorithms for transcript isoforms, structural variation, and regulatory disruption from PacBio and ONT long reads.

Cancer Genomics and Evolution

Fusion transcripts, tumor structural variation, somatic mosaicism, and developmental origins of cancer cell states.

Epigenomics and Gene Regulation

Integrative modeling of transcription factor binding, chromatin accessibility, and cis-regulation across human and mouse.

AI for Biomedical Data

Deep learning, probabilistic models, and generative methods for multi-omics, regulatory genomics, and clinical genomics.

software

CTAT-LR-Fusion

Accurate fusion transcript identification from long- and short-read isoform sequencing at bulk or single-cell resolution.

minisv

Improving long-read somatic structural variant calling with pangenome and de novo personal genome assembly.

Lisa

Inferring transcriptional regulators through integrative modeling of public chromatin accessibility and ChIP-seq data.

Cistrome Data Browser

A data portal for ChIP-seq and chromatin accessibility data in human and mouse, with integrative gene regulation tools.