All Competitors

Protein sequence embedding model, contrastively fine-tuned from ESM-2, that places functionally and structurally related proteins close together.

Vector-based virtual screening model that co-embeds proteins and small molecules so a drug-target interaction reduces to a single dot product.

DNA-binding residue prediction across folded domains and disordered protein regions, with contrastive training that suppresses cross-predictions.

Proteome-scale protein dynamics prediction from sequence or structure, predicting residue flexibility, correlations, and conformational states.

Graph transformer over 3D protein structures predicting solvation free energy, hydrodynamic radius, diffusion constants, and molecular volume.

Estimation of model accuracy for protein complexes, predicting per-residue lDDT from Voronoi contact areas and contact-surface orientation features.

Interface residue accuracy estimation for protein complexes, predicting per-residue lDDT from whole-complex, per-monomer and cross-chain features.

MSA-free structure prediction for TCR-peptide-MHC complexes, pairing a protein-protein-interaction language model with a flexible docking module.

Protein conformational ensemble tokenizer that learns a discrete alphabet of states from molecular dynamics, reusable as a frozen feature layer.

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

Protein language model interpretability adapter that factors ESM2 and ProtBERT embeddings into named biochemical features plus a residual subspace.

Rigid protein-protein docking model that predicts a complex from two unbound structures in one pass, with no candidate sampling or refinement.

Sequence-only TM-score prediction pairing frozen ProtT5 embeddings with a bidirectional GRU and multi-scale convolution for protein homology search.

Generative pipeline for epitope-targeted de novo antibody (nanobody) CDR design that yields nanomolar binders from only dozens of designs per antigen.

All-atom foundation model for macrocyclic peptide structure prediction, permeability estimation, and de novo design across non-canonical chemistries.

Flow-matching protein backbone generator with hierarchical fold-class conditioning, reaching 99.0% designability and chains up to 800 residues.

Protein representation model adding global fold-similarity and local substructure signals to masked pretraining, reaching 79.2 long-range contact P@L.

Protein-protein interaction prediction from structure alone, embedding each protein once so a proteome-wide dot product replaces pairwise queries.

Antibody CDR design framework pairing a pretrained antibody language model with a hierarchical graph neural network for one-shot CDR generation.

All-atom generative model for de novo protein design using SE(3) flow matching over oriented residue rigid bodies.

Autoregressive protein language model based on GPT-2 that generates de novo protein sequences sampling unexplored regions of protein space.

GPCR structure prediction and peptide design model that generates linear and cyclic peptide agonists carrying noncanonical amino acids, zero-shot.

Potts-model inverse folding that conditions on a structural ensemble rather than a single backbone, improving designability and self-consistency.