All Competitors

Antibody language model family scaling to 1.7B parameters, tokenizing sequences as overlapping tripeptides to encode local structural motifs.

Lung pathology foundation model adapted from Virchow2 on whole-slide images, validated across 32 tasks spanning the lung diagnostic workflow.

Contrastive promoter-protein pretraining that aligns bacterial promoters with their encoded proteins to learn regulatory genomics representations.

Variant effect predictor pairing a protein language model with family-specific evolutionary constraints to score stability, binding, and epistasis.

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

Mixture-of-Experts genomic foundation model for the human microbiome, with 4.7B parameters pretrained on bacterial, archaeal, and phage genomes.

RNA language model that predicts secondary structure of internal ribosome entry sites from sequence alone, trained on roughly 50,000 IRES sequences.

Metabolomic foundation model pretrained on UK Biobank NMR metabolite profiles, reused with a frozen backbone for aging, subtyping, and disease risk.

Codon-level mRNA language model adapted from ESM-2 650M by swapping amino-acid tokens for codon tokens, transferring protein knowledge to mRNA tasks.

Spatial transcriptomics foundation model for the tumor microenvironment, giving TME-aware embeddings and in silico perturbation from one checkpoint.

Synthesis-aware generative model for small molecules that proposes drug-like analogs with forward routes from commercially available building blocks.

Promptable DNA language model that generates multi-kilobase plasmid sequences from plain-language component specs, refined with verifiable rewards.

SE(3)-invariant masked autoencoder that learns protein fold representations from AlphaFold-DB structures, supporting zero-shot fold classification.

Multimodal framework that detects and localizes DNA lesions from native nanopore signal, built on the damage-aware LesionBERT foundation model.

Protein structure prediction and binder design in a single generative step, replacing AlphaFold3's iterative diffusion sampling with one forward pass.

Multimodal Q-former that fuses DNA sequence, gene context, protein function, and text for zero-shot variant interpretation with a frozen LLM.

Multiphoton pathology vision-language system turning one label-free breast section into virtual H&E, a margin heatmap, and a written report.

Sparse autoencoders trained on protein language model embeddings to expose interpretable features and drive zero-shot variant effect prediction.

370M-parameter ligand-conditioned discrete diffusion model that co-designs protein sequence and structure under explicit small-molecule constraints.

Sequence-based discrete-diffusion framework that designs peptide binders with specified agonist or antagonist behavior against GPCR targets.

Protein language model for variant effect prediction and de novo sequence design, conditioned on Gene Ontology embeddings of molecular function.

Protein sequence-structure co-design model conditioned on Gene Ontology function embeddings, sampling residues and backbone angles together.

Domain-specific foundation model for zero-shot plant root image segmentation, built on a MobileSAM backbone and trained across nine root datasets.