All Competitors

Learned compression autoencoders for histopathology whole-slide images, tuned so reconstructions preserve the features downstream models rely on.

Zero-shot pathogenicity scoring for in-frame insertions and deletions from protein language model likelihoods over residues both alleles share.

Protein conformational ensemble generator that samples heavy-atom structures in a latent space, with a variant conditioned on temperature.

Phylogenetic tree inference from unaligned nucleotide sequences, using a 2D genomic-footprint encoding and CNN classification of triplet topologies.

Self-supervised transformer encoding a full eight-hour, seven-channel polysomnogram into task-agnostic representations for automated sleep staging.

EEG foundation model for clinical diagnosis, combining a VQ-VAE spectral tokenizer with masked token prediction for seizure and pathology detection.

RNA inverse folding model that designs nucleotide sequences for a target 3D backbone by running discrete diffusion in hyperbolic space.

Vision-language model for open-vocabulary mouse behavior analysis, describing multi-view video and pose kinematics in natural language.

Enzyme turnover number (kcat) prediction from sequence and substrate SMILES, scaling to genome-wide kinetic parameters for metabolic modeling.

Single-cell foundation model that fuses scRNA-seq profiles with text, pairing a cell encoder with an LLM for cell annotation and clustering.

Residue-level carbohydrate binding-site identification on protein structures, using equivariant graph convolutions over ESM2 per-residue embeddings.

All-atom generative foundation model for biomolecular structure, unifying protein-ligand docking, structure-based drug design, and peptide design.

Whole-protein carbohydrate-binding classification from structure, for proteome-scale screening with graph convolutions over ESM2 embeddings.

Genomic language models with disentangled attention, pretrained on prokaryotic and eukaryotic genomes for sequence classification and variant effects.

Protein inverse folding ensemble that fuses five pretrained sequence designers through a self-attention encoder, reaching 63.1% recovery on CATH4.2.

Matryoshka sparse autoencoders scaled to ESM2-3B, exposing the features that drive protein structure prediction and steering ESMFold outputs.

Protein language model that tokenizes sequence, backbone structure, and text into one vocabulary for function prediction, design, and fold editing.

Retinal encoding models that predict ganglion cell responses to visual stimuli, with pretrained checkpoints across four species and two modalities.

Protein segmentation that locates folded domain, sub-domain, and disordered region boundaries from frozen ProtT5 embeddings without any training step.

Protein sequence-structure encoder biasing attention with relative residue-frame transforms, for inverse folding and peptide binding prediction.

Ab initio RNA 3D structure prediction from a single sequence, using a composite-likelihood language model and a denoising end-to-end structure module.

Structure-based drug design framework that scores interaction-aware fragments against protein subpockets, then diffuses a 3D scaffold to link them.

Protein complex structure prediction system combining AlphaFold2 and AlphaFold3 with stoichiometry prediction, MSA engineering, and model ranking.