Texas A&M University

3D brain MRI synthesis from separate hemisphere and cerebellum-brainstem diffusion priors, assembled and refined into one volume with editable parts.

Protein language model for variant effect prediction and de novo sequence design, conditioned on Gene Ontology embeddings of molecular function.

Protein sequence-structure co-design model conditioned on Gene Ontology function embeddings, sampling residues and backbone angles together.

De novo protein design model that co-generates sidechains, backbone, and sequence in one flow-matching process instead of backbone only.

Controllable DNA sequence design conditioned on cell type, transcription factor, or activity signal, in GPT- and BERT-style transformer variants.

Multi-LLM consensus framework for automated cell type annotation in scRNA-seq data, outperforming prior methods by ~15% in mean accuracy.

Chemical language model that tokenizes each atom by its functional group, giving transferable embeddings for molecular property prediction.