All Competitors

Protein-family language model trained on unaligned homolog sets for zero-shot variant fitness prediction and design. ProFam-1 holds 251M parameters.

De novo protein binder design suite from ByteDance pairing diffusion and hallucination generators with confidence-based filtering of designs.

Multimodal protein language model that adds a continuous-token diffusion head to a discrete pLM, modeling structure without vector quantization.

De novo peptide sequencing transformer that reads modified and unmodified peptides directly from tandem mass spectra without a reference database.

Energy-based model of protein conformational space, turning a diffusion model into a statistical potential for structure ranking and mutation scoring.

Structure-based drug design model that unifies de novo generation, docking, conformer generation, and pharmacophore conditioning via flow matching.

Atom-level diffusion model for de novo enzyme design that scaffolds arbitrary active-site geometries without specifying catalytic residue positions.

Structure-conditioned protein sequence design, pairing a three-track architecture with discrete flow matching for fast, few-step inverse folding.

Retrieval-augmented diffusion model for protein inverse folding that conditions sequence generation on profiles from structurally similar homologs.

Protein sequence encoder that maps ESM2 embeddings to a learned 20-letter alphabet for structure-quality remote homology detection at MMseqs2 speed.

Hierarchical single-cell foundation model that turns scRNA-seq profiles into zero-shot donor-level embeddings for disease and biomarker prediction.

Multimodal protein representation model that iteratively fuses a sequence language model with a 3D structure encoder through a shared learnable token.

RNA interaction foundation model for conditional, zero-shot design of RNA sequences that bind protein, DNA, or RNA targets without retraining.

All-atom generative model for de novo protein and peptide binder design against diverse biomolecular targets, wet-lab validated across 26 targets.

Flow-matching model that jointly samples 3D de novo molecules and several low-energy conformers, extending to pocket-conditioned ligand design.

Diffusion model for structure-based drug design that jointly generates 3D ligands and holo pocket conformations from an apo protein structure.

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

Retrieval-augmented protein encoders that fuse homologous sequences into a single-pass transformer for variant effect and contact prediction.

Spectral prediction model for modified peptides, forecasting fragment-ion intensities and retention time with zero-shot generalization to unseen PTMs.

Denoising diffusion bridge model for peptide binder design that generates ligand surfaces and backbones complementary to a target receptor surface.

Protein dynamics model that samples conformational ensembles autoregressively at slow and fast timescales, generalizing zero-shot to unseen proteins.

Equivariant diffusion model that converts peptide binders into drug-like small molecules, generating peptidomimetics inside the target protein pocket.

Antibody language model pretrained only on CDR-H3 loops, giving embeddings for immune repertoire analysis and antibody sequence classification.

Paired heavy/light antibody language model fine-tuning ESM-2 and ESM-C with CDR-preferential masking for zero-shot binding affinity embeddings.