All Competitors

Protein structure accuracy estimation predicting a global TM-score from an equivariant graph network over residue geometry and Rosetta energy terms.

Structure prediction for protein, RNA, and protein-RNA complexes in one AlphaFold2-derived framework that accepts MSA or language model encoders.

Parameter-efficient protein language model that matches larger models such as ESM-2 on protein prediction tasks using under 10% of the parameters.

Transformer framework for single-cell multi-omics that predicts cross-modality relationships using heterogeneous graphs of cells, genes, and proteins.

Multi-modal protein language model trained on sequences paired with biomedical text, enabling zero-shot function prediction and text-based retrieval.

Antibody CDR design model that reprograms a frozen English BERT for sequence infilling, avoiding training a dedicated protein language model.

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

Blind protein-ligand docking by diffusion over ligand translations, rotations and torsion angles, reaching 38% top-1 accuracy on PDBBind.

Protein language model reading each residue alongside an unsupervised local-fragment token, so one encoder serves residue- and chain-level tasks.

Predicts CLIP-seq crosslink counts along an RNA sequence base by base, separating protein-specific signal from experimental background.

Message passing neural network for fixed-backbone protein sequence design. Achieves 52.4% native sequence recovery, far surpassing Rosetta's 32.9%.

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

Protein model accuracy estimation from MSA co-evolution and homologous templates, predicting per-residue lDDT with a triangular-attention backbone.

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

In silico directed evolution that designs peptide binders against a chosen protein interface from sequence alone, scored by a frozen AlphaFold2.

Protein language model family from 8M to 15B parameters, used as a frozen sequence encoder whose representations encode atomic-level structure.

Protein structure prediction from a single sequence, with no multiple sequence alignment. Folds a 384-residue protein in 14.2 seconds on one GPU.

Transformer model for de novo peptide sequencing that reads amino acid sequences directly from tandem mass spectra, with no protein sequence database.

Autoregressive protein language model scoring variant effects zero-shot, blending sequence likelihood with homolog statistics retrieved at inference.

Protein language model family built on CNNs rather than transformers, matching transformer quality while scaling linearly with sequence length.

BERT-based antibody language model pretrained on 57M B cell receptor sequences for paratope prediction and convergent antibody discovery.

Full-atom protein model accuracy estimation, regressing per-atom lDDT with an SE(3)-transformer over a heavy-atom graph of the modeled structure.

Structure accuracy estimation over atom graphs, scoring macrocyclic peptide and protein-DNA models that residue-level predictors cannot represent.