All Competitors

Dirichlet flow-matching model for protein design that generates family-aware sequences from ancestral-reconstruction priors, not random noise.

Leakage-controlled multimodal model predicting within-species relative protein expression across 385 bacterial species, with transfer to unseen phyla.

OpenAI's frontier reasoning model for life-sciences research, tuned for multi-step workflows in protein engineering, genomics, and drug discovery.

Edit-based flow-matching model that proposes protein variants by learning insertions, deletions, and substitutions on a template sequence.

Codon-level BERT model that captures genomic signals invisible to amino acid models, outperforming billion-parameter PLMs with just 86M parameters.