Howard Hughes Medical Institute

Prime editing efficiency prediction from pegRNA sequence, with every biochemical step of the editing mechanism modeled as its own learned rate.

Protein deimmunization framework that aligns a protein language model with GRPO to design sequences carrying fewer MHC Class I T-cell epitopes.

All-atom structure prediction for arbitrary biomolecular complexes of proteins, nucleic acids, and ligands, with code and weights under a BSD license.

Functional ultrasound reconstruction with neural operators, rebuilding power Doppler brain images from 10-15% of the usual compounded frames.

Hi-C resolution enhancement model combining a U²-Net with self-attention to recover TAD boundaries and chromatin loops from sparse contact maps.

Single-cell RNA-seq representation model that separates batch-dependent from batch-independent variation to compare disease states across datasets.

Macrocyclic peptide binder design against protein targets, cyclizing a diffusion backbone generator's positional encoding so it closes rings.

Peptide-MHC class I immunogenicity prediction fusing sequence, predicted structure, and biochemical properties for vaccine and neoantigen design.

Poly(A)-tail length change predicted from mRNA 3' UTR sequence in maturing oocytes, scoring how single-nucleotide variants disrupt tail lengthening.

Protein domain annotation model pairing an ESM-2 backbone with a probabilistic decoder, bringing language-model sensitivity to Pfam-style assignment.

Multi-modal protein foundation model aligning 3D structure and literature text to a sequence anchor through contrastive pretraining.

Protein structure prediction for monomers and complexes in one three-track network, scaling past 1000 residues without triangle attention.

Protein-nucleic acid complex structure prediction from sequence, folding protein, DNA and RNA chains in one network with confidence estimates.

Protein structure and complex prediction from sequence, in a three-track network that reasons over alignments, distances, and 3D coordinates at once.

Protein model accuracy estimation predicting per-residue lDDT plus signed residue-pair distance errors that become Rosetta refinement restraints.

RNA-binding protein target site prediction from 1,000 bp of sequence, scoring how a noncoding variant disrupts binding across 88 RBPs.