AI & ML interests

None defined yet.

Recent Activity

Organization Card

FishCaduceus

FishCaduceus is a family of single-nucleotide DNA language models developed for cyprinid and comparative fish genomics.

The project provides:

  • pretrained FishCaduceus models with 512-bp and 1,024-bp context lengths
  • pretraining datasets from seven major cyprinid aquaculture fishes and zebrafish
  • cross-species benchmarks for translation initiation, translation termination, splice donor and splice acceptor prediction
  • evolutionary constraint benchmarks derived from a 26-fish whole-genome alignment

FishCaduceus is designed for fish genome annotation, cross-species transfer, evolutionary constraint analysis and zero-shot variant prioritization.

Resources

Manuscript

FishCaduceus: A DNA Language Model for Cyprinid Genomics at Single-Nucleotide Resolution

The manuscript is in preparation.

Contact

Xiao-Qin Xia
Institute of Hydrobiology, Chinese Academy of Sciences
Email: xqxia@ihb.ac.cn