All Competitors

EEG foundation model that denoises, reconstructs, and upsamples scalp recordings at any electrode position. A 380M-parameter diffusion autoencoder.

A pathology tile encoder fine-tuned from Midnight-12k so its features track tissue morphology rather than the scanner and lab behind the slide.

A robustified fine-tune of Phikon-v2 for H&E tiles, retrained to strip scanner and laboratory signatures out of its feature space.

Few-step generative model for de novo protein backbone design, extending MeanFlow to the SE(3) Lie-group geometry of residue frames.

Biosynthetic gene cluster discovery in plant genomes, transferring supervision from microbial BGCs by label-free adaptation over Pfam-domain tokens.

Non-coding variant prioritization for rice GWAS loci, ranking SNPs by predicted effects on 12 chromatin features via a fine-tuned DNABERT-2.

Peptide-protein co-folding and small-molecule docking with an all-atom diffusion transformer. Recovers 59.1% of peptide interfaces to sub-2 Å RMSD.

Preparation-free protein-ligand binding affinity prediction from a protein sequence and a ligand SMILES, using a cascaded mixture-of-experts fusion.

Mass spectrometry foundation model for untargeted metabolomics and lipidomics, naming and quantifying molecules with no reference library.

Residue-level prediction of ligand-binding and cryptic pockets in one model, reading frozen ESM-2 embeddings with no 3D structure at inference.

Protein complex structure prediction from amino acid sequence, deployed as a self-hosted SageMaker endpoint that returns mmCIF and ipTM confidence.

Intracortical speech brain-to-text decoder jointly pretrained across six BCI users, with over 50% lower relative word error than per-user models.

Spatial proteomics foundation model for multiplex immunofluorescence, with a 268-marker vocabulary and marker-conditioned 768-dimensional embeddings.

Molecular graph foundation model for ADMET and pharmacokinetic property prediction, pretrained by contrastive learning with graph external attention.

Cross-species single-cell ageing-state classifier that transfers mouse age labels to human HSC and CD8+ T cells, reaching 0.953 held-out AUROC.

Cross-context protein binder design model that generates one sequence binding multiple targets or conformational states of the same target.

Spatial proteomics foundation model trained on over 51 million single cells to learn panel-robust cell representations across platforms.

Single-cell perturbation prediction model trained only on synthetic priors, inferring drug targets, intervention strengths, and regulatory graphs.

Calcium imaging foundation model for neural population forecasting and behavior decoding, with frozen-backbone transfer across three species.

VHH nanobody expression predictor needing only an amino-acid sequence, no structure. Leave-program-out ROC-AUC 0.81 on unseen antibody programs.

Single-cell cancer model scoring driver-associated expression programs by projecting scRNA-seq through axes frozen from genotype-matched bulk tumors.

Protein language model adding long-range contact supervision to ESM2 via LoRA, improving all eight protein-level tasks with no structural input.

Molecular glue degrader design model that jointly generates the glue molecule and the E3 ligase-target ternary complex from unbound monomers.