Institute of Computing Technology, Chinese Academy of Sciences

Multimodal molecular large language model grounding molecule understanding and generation in fine-grained, multi-level chemical knowledge.

Proteomics foundation model for peptide-spectrum scoring and open de novo sequencing, reading over 1,300 modifications from tandem mass spectra.

De novo peptide sequencing from mirror-protease mass spectra, reading paired complementary spectra to recover near-complete fragment ion coverage.

Immune protein structure prediction for TCRs, antibodies, and nanobodies. Adapts ESMFold with LoRA, reaching 1.31 Å RMSD on the CDR3-beta loop.

Chemical perturbation model generating post-treatment transcriptomes for compounds and cell lines never screened, from SMILES structure and dose.

3D CT vision-language model that drafts radiology reports, answers questions about volumes, and screens for disease from a masked-autoencoder encoder.