University of Texas at Austin

Unified all-atom generative model for biomolecular structure prediction, binder filtering, and controllable protein and nanobody design.

Cell world model pretrained on a 2.4M-cell mouse embryonic atlas, predicting one-step transcriptional state transitions and perturbation response.

Chemical language models pretrained on SMILES for therapeutic peptides, natively representing non-canonical residues, cyclization, and conjugation.

Antibody language model adapted on paired heavy and light chains, using CDR-focused masking to sharpen embeddings for binding affinity prediction.

Structure prediction backbone that swaps AlphaFold3-style triangle attention for triangle multiplication, cutting compute without losing accuracy.

Distilled few-step protein backbone generator that adapts Score Identity Distillation to Proteina for over 20x faster de novo structure sampling.

Multimodal diffusion transformer for de novo protein design, jointly generating sequence and structure conditioned on 465 Gene Ontology functions.

De novo protein backbone generator trained on low-confidence AlphaFold structures as corrupted data, reaching 86% designability at 700 residues.

Contrastive language-image model for fMRI functional decoding, predicting cognitive tasks, concepts, and domains from brain activation maps.

Protein language model that distills structure tokens into ESM2, yielding structurally enriched embeddings from sequence input alone.

Pathology vision-language model that adds lightweight adaptors and multi-granular prompt learning for few-shot whole-slide image classification.

Protein language model that generates paired heavy and light chain human antibodies from an antigen prompt, with binders validated in vitro.

Pocket-conditioned 3D ligand generator built on rectified flow, reaching -8.50 average Vina Dock and 75.0% diversity on CrossDocked2020.

Chemical language model reading modified and cyclic peptides as SMILES, fine-tuned to predict passive membrane diffusion of macrocycles.

Self-supervised vision foundation model pretrained on 1.3M medical images via second-order graph matching, for segmentation and classification.

Drug pair synergy prediction for rare cancer tissues, read from a language model's representation of a screening row written out as a sentence.