All Competitors

Protein structure tokenizer that encodes a whole structure globally, with each successive token adding detail for adaptive-length representations.

Protein backbone generator running a diffusion transformer over SaProt structural tokens, with an IPA token cache to speed up de novo design.

Protein structural homology search from sequence alone, embedding proteins so that structural similarity becomes a fast nearest-neighbor lookup.

Protein language model that predicts per-residue local energetic frustration directly from sequence, covering whole proteomes and disordered regions.

Connects a frozen protein language model to a general LLM via a cross-modal projector, adding protein reasoning without catastrophic forgetting.

Full-atom SE(3)-equivariant diffusion model that inpaints binding interfaces to design proteins that bind DNA, RNA, and small molecules.

Masked language model for T-cell receptor and peptide-MHC binding prediction, with compositional pretraining and non-autoregressive decoding.

Latent flow-matching method that repurposes protein language model embeddings to generate high-fitness protein variants without predictor guidance.

Causal 309M-parameter protein language model that scores variant fitness zero-shot and generates sequences, reaching 0.390 Spearman on ProteinGym.

Enzyme design model that jointly generates enzyme sequences and substrate-binding pockets, conditioned on functional priors and substrate structure.

Partially latent flow-matching model for de novo protein design, jointly generating sequence and all-atom structure for proteins up to 800 residues.

Structure-based protein encoder that voxelizes every heavy atom into a 3D grid, learning orientation-robust representations for protein function.

Flow-matching generative model for de novo protein binder backbone design, built on a Pairformer architecture with in silico interface maturation.

LoRA adapter on ProstT5 predicting per-residue distributions over Foldseek 3Di tokens, capturing conformational flexibility from MD trajectories.

Structure-free protein-ligand binding affinity predictor built on OpenFold3 that scores potency from a protein sequence and a ligand SMILES string.

Zero-shot peptide binder designer that runs diffusion in a pretrained protein embedding space, proposing binders without structure prediction.

Generative transformer for ancestral protein sequence reconstruction that needs no multiple sequence alignment or phylogenetic tree as input.

Evolution-guided diffusion model that generates temporal protein folding pathways, from unfolded chain to native state, rather than static structures.

Inverse folding model that emits a pairwise Potts energy function from a backbone, so the same network designs sequences and predicts mutation ddG.

Contrastive geometric model unifying structure- and ligand-based drug design for zero-shot virtual screening, target fishing, and pocket selection.

Diffusion model for de novo AAV capsid design that steers sampling with a viability classifier toward assemblable, packaging-competent variants.

Sequence-only latent diffusion model that designs target-specific peptide binders, cascaded with an affinity classifier through joint optimization.

Metagenomic foundation model trained on 9.7 trillion nucleotide tokens for generative therapeutic design across genes, peptides, and microbiomes.