All Competitors

Vision-language DNA model that renders genomic sequence as visual layouts, reading regions up to 450,000 bases with about 20x better token efficiency.

Causal 309M-parameter protein language model that scores variant fitness zero-shot and generates sequences, reaching 0.390 Spearman on ProteinGym.

Family of autoregressive genomic foundation models that reconcile k-mer tokenization with single-nucleotide resolution at contexts up to 98k bp.

Retrieval-augmented genomic foundation model that gives transformer backbones a hash-based k-mer motif memory for functional genomics tasks.

Large causal cell model trained on cancer perturbation data that generalizes zero-shot to patient-derived cells for therapeutic target prioritization.

Enzyme design model that jointly generates enzyme sequences and substrate-binding pockets, conditioned on functional priors and substrate structure.

Bidirectional generative framework linking nuclear morphology and gene expression, built on a morphology model trained on 21 million segmented nuclei.

Structure-based protein encoder that voxelizes every heavy atom into a 3D grid, learning orientation-robust representations for protein function.

Partially latent flow-matching model for de novo protein design, jointly generating sequence and all-atom structure for proteins up to 800 residues.

Flow-matching generative model for de novo protein binder backbone design, built on a Pairformer architecture with in silico interface maturation.

Bioimage restoration model pairing a NAFNet backbone with a perceptual GAN loss, best on LPIPS in 7 of 8 AI4Life microscopy benchmarks.

LoRA adapter on ProstT5 predicting per-residue distributions over Foldseek 3Di tokens, capturing conformational flexibility from MD trajectories.

Spatial transcriptomics foundation model built on a lightweight graph convolutional network and trained by masked central-spot prediction.

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

Zero-shot peptide binder designer that runs diffusion in a pretrained protein embedding space, proposing binders without structure prediction.

Generative transformer for ancestral protein sequence reconstruction that needs no multiple sequence alignment or phylogenetic tree as input.

Evolution-guided diffusion model that generates temporal protein folding pathways, from unfolded chain to native state, rather than static structures.

Contrastive geometric model unifying structure- and ligand-based drug design for zero-shot virtual screening, target fishing, and pocket selection.

Generative transformer foundation model for continuous glucose monitoring, forecasting glycemia and stratifying health risk from raw glucose traces.

Metagenomic foundation model trained on 9.7 trillion nucleotide tokens for generative therapeutic design across genes, peptides, and microbiomes.

Diffusion model for de novo AAV capsid design that steers sampling with a viability classifier toward assemblable, packaging-competent variants.

Single-cell RNA-seq language model that treats cells as gene-expression tokens, synthesizing whole transcriptomes from tissue and disease metadata.

Sequence-only latent diffusion model that designs target-specific peptide binders, cascaded with an affinity classifier through joint optimization.

Cross-modal single-cell foundation model that aligns gene-expression profiles with LLM-enriched cell descriptions in a shared embedding space.