About
Research Interests
Our laboratory specializes in DNA Large Language Models and their applications in plant science. We are at the intersection of AI and biology, developing foundation models that learn the fundamental grammar of DNA to enable:
- DNA Large Language Models — building and training foundation models for DNA sequence understanding
- Regulatory element prediction — using LLMs to identify cis-regulatory elements with unprecedented accuracy
- Genome engineering — applying AI to optimize CRISPR-based genome editing
- Open-source tool development — making our models and tools freely available via PDLLMs
Featured Work: PDLLMs
Our Plant DNA Large Language Models (PDLLMs) represent a new paradigm for plant genome analysis. Published in Molecular Plant 2025, PDLLMs provide a suite of tailored foundation models for analyzing plant genomes, predicting regulatory elements, and accelerating crop improvement. Get PDLLMs on GitHub
Grants & Funding
- National Natural Science Foundation of China (NSFC)
- Chengdu Institute of Biology, Chinese Academy of Sciences Start-up Fund