Genentech

Guided discrete diffusion model for antibody lead optimization, conditioning sequence design on the seed binder's CDR canonical backbone conformation.

Genomics foundation model that unifies sequence-to-function prediction, DNA language modeling, and generative regulatory design in one backbone.

Multimodal tokenizer for antibody CDR loops, encoding backbone dihedrals and sequence as discrete tokens that plug into antibody language models.

Antibody, nanobody, and T-cell receptor structure prediction that resolves bound and unbound conformations separately in under a second per domain.

Raman spectroscopy foundation model that denoises biological spectra and learns embeddings transferable across cell, tissue, and tumor studies.

Protein-protein interface embedding model built on Delaunay graphs, reused frozen for antibody-antigen affinity and antibody viscosity prediction.

TCR-pMHC specificity prediction that folds frozen ESM-2 and AlphaFold2 representations into a three-body peptide-MHC-CDR3 energy tensor.

Drug-conditional adapter inside a frozen single-cell foundation model, predicting transcriptional responses to unseen drugs and cell lines.

Spatial gene expression prediction from H&E tumor histology, aligning a pathology foundation model with a single-cell RNA-seq foundation model.

Latent diffusion model for controllable all-atom protein generation that co-designs sequence and structure while training on sequences alone.

Single-cell foundation model trained by metric learning to embed scRNA-seq profiles for cell type annotation and similarity search in cell atlases.

Patient-level foundation model that pools every cell in an scRNA-seq sample into one disease representation, trained on 24.3 million cells.

Generative masked protein language model with an interpretable concept layer, letting designers set 718 biophysical and annotation concepts directly.

Walk-jump sampler that runs molecular dynamics in a smoothed, noised space of all-atom coordinates to generate peptide conformational ensembles.

Peptide-MHC presentation model for class I and II that maps peptide, flanking residues, source protein and MHC allele into separate readable vectors.

Sequence-to-function model predicting cell-type- and disease-specific gene expression from DNA, trained on pseudobulk profiles from 22 million cells.

Efficient protein language model library from Prescient Design enabling high-quality sequence representations and fitness prediction in 24 GPU hours.

Discrete generative model for antibody protein sequences combining MCMC walks on a smoothed energy landscape with one-step denoising jumps.

Cryo-electron tomography membrane analysis pipeline pairing generalizable U-Net membrane segmentation with mesh-based particle localization.

Protein structure prediction model pairing SE(3)-equivariant networks with a coarse-grained representation to fold sequences fast, without MSA inputs.