All Competitors

Billion-parameter single-cell foundation model with self-attention over 28,000 human genes, adding Gene Ontology priors via a graph neural network.

Protein function prediction model that autoregressively generates Gene Ontology terms from amino acid sequence instead of classifying fixed labels.

Protein function prediction models that assign Gene Ontology terms using language model embeddings and neuro-symbolic reasoning over GO axioms.

Protein language model that fuses Gene Ontology knowledge graphs with masked language modeling, improving protein function and interaction prediction.

Protein language model pretrained on UniRef90 with masked language modeling and Gene Ontology annotation prediction, at 16 million parameters.