All Competitors

RNA secondary structure prediction from a single sequence, without MSAs. Axial-attention transformer reaching F1 0.764 on the TS-PDB benchmark.

Protein-ligand binding affinity prediction from an amino acid sequence and a ligand SMILES string, with no structure, docked pose, or pocket needed.

Latent diffusion model for de novo DNA sequence generation, sampling species-conditioned promoter and gene regions of 256 or 2,048 base pairs.

Peptide tandem mass spectrum prediction across the full fragment ion series, with neutral losses and modification-specific peaks beyond b/y ions.

Antibody language model trained on paired and unpaired OAS sequences to suggest non-germline mutations instead of reverting them to germline.

Protein conformational ensemble generator that fine-tunes AlphaFold 2 with flow matching, sampling protein dynamics beyond a single static structure.

Protein sequence-structure co-design by multimodal flow matching, generating a backbone and its amino acids jointly rather than one after the other.

EHR foundation model that writes patient histories as token sequences carrying explicit visit and day-interval tokens, invertible back to OMOP tables.

Threshold-agnostic spot detection for 2D and 3D fluorescence microscopy, locating transcripts at subpixel accuracy via stereographic flow regression.

Causal discovery foundation model that aggregates classical FCI or GIES estimates over small variable subsets into a global gene regulatory graph.

Spot detection for single-molecule RNA FISH and fluorescence microscopy, trained on a differentiable F1 approximation, needing no threshold tuning.

Organelle phenotyping model that scores how perturbations shift subcellular localization and morphology in confocal images of human neurons.

Protein homology search via contrastive per-residue ResNet embeddings, acting as a pre-filter at least 5x faster than the one inside HMMER3.

Generative language model for single-cell transcriptomics with 368M parameters, unifying cell type annotation, batch integration, and cell generation.

Virtual staining model that generates 11-marker spatially resolved protein multiplexes from routine H&E histopathology whole-slide images.

Discrete graph diffusion transformer generating molecules under several numerical and categorical property targets at once, with no guiding predictor.

Instruction-tuned vision-language foundation model for chest X-ray interpretation, with 8 billion parameters spanning eight clinical task types.

Promptable foundation model for universal medical image segmentation, fine-tuned from SAM on 1.57M image-mask pairs across 10 imaging modalities.

Multimodal protein pre-training framework jointly learning sequence, 3D structure, and surface representations via implicit neural representations.

Structure-based drug design diffusion model that re-extracts the essential binding subcomplex from a pocket at every step of 3D ligand generation.

RNA-binding protein affinity prediction at single-base resolution from sequence alone. One model spans 155 RBP targets across three cell lines.

RNA language model trained on multiple sequence alignments of Rfam families, predicting secondary structure and solvent accessibility from homology.

Unified 100-billion-parameter protein language model combining autoencoding and autoregressive objectives for protein understanding and generation.