Hunan University

Infrared spectroscopy foundation model pretrained on 60 million simulated spectra, then adapted to real FTIR measurements of molecules and mixtures.

Single-cell foundation model adding a gated cell-level contrastive objective to masked expression pretraining for transferable frozen cell embeddings.

NMR foundation model trained on 158 million simulated 1H and 13C spectra, transferring simulation-learned representations to real experimental data.

Protein representation learning from cryo-EM density maps, transferring to flexibility, active-site, binding-affinity, and stability tasks.

Vision-language DNA model that renders genomic sequence as visual layouts, reading regions up to 450,000 bases with about 20x better token efficiency.

Protein binder design model post-trained from a multimodal protein language model to bind proteins, peptides, small molecules, and nucleic acids.

Multimodal single-cell foundation model pretrained on 4M+ co-assayed cells, predicting 382 surface proteins from transcriptomes alone, zero-shot.

Retrosynthesis and reaction prediction LLM that jointly learns molecular fragmentation and recombination from a 4.4M-instruction chemistry corpus.

All-atom generative model for protein complexes that designs multi-chain binders from scratch and performs multimer folding and inverse folding.

Genomic language model for scRNA-seq cell-type annotation, reweighting rare classes so diseased cell types are not swamped by common ones.

Universal ultrasound segmentation foundation model adapting the Segment Anything Model to eight anatomical regions in a single promptable network.

DNA- and RNA-binding residue prediction from a nucleic-acid-adapted protein language model and an equivariant graph network over protein structure.

Lung cancer histopathology model that predicts spread through air spaces from whole-slide images using a feature-interactive Siamese graph encoder.

De novo peptide sequencing model that retrieves a similar peptide-spectrum match from a database and fuses it into transformer decoding.

Conditional GAN that generates small molecules against a protein-protein interaction interface, encoding the complex with graph attention networks.