All Competitors

Protein-DNA binding prediction and binder design from sequence, aligning protein and DNA language model embeddings instead of co-folding a complex.

Subject-level disease prediction from scRNA-seq, pairing cell-type-grouped scGPT pretraining with a Reactome pathway-constrained decoder.

Antibody CDR design model fusing diffusion with a GFlowNet objective so binding energy is optimized during training rather than by post-hoc RL.

Retinal fundus foundation model conditioned on patient age and sex, pretrained on 1.0 million colour photographs from 292,000 patients.

Brain foundation model unifying EEG and MEG in a single encoder via a shared discrete tokenizer that transfers across sensor layouts and montages.

Protein representation model adding global fold-similarity and local substructure signals to masked pretraining, reaching 79.2 long-range contact P@L.

Surgical video foundation model pretrained by entropy-maximizing compression on 0.78M unlabeled frames from 2,122 minimally invasive procedures.

Recombinant protein expression predictor scoring soluble E. coli production from construct sequence, with AUROC 0.83 on prospective constructs.

T-cell epitope immunogenicity prediction that fuses MHC presentation, TCR binding, and activation data via adversarial multi-domain pretraining.

Structure-based drug design by diffusing medicinal-chemistry fragments into a binding pocket, yielding synthesizable, selective, drug-like molecules.

Predicts 16-channel multiplex immunofluorescence from H&E histology using a ViT foundation-model encoder, validated on five external datasets.

Pharmacophore-conditioned diffusion model generating 3D molecular graphs that satisfy a given pharmacophore hypothesis without a target structure.

End-to-end protein structure alignment from 3D coordinates, matching TM-align quality at LDDT 0.56 and beating Foldseek on SCOPe40 search.

Ligand-aware protein language model that cross-attends SaProt embeddings to ligand SMILES, beating SaProt across six downstream benchmarks.

Deep mutational scanning score imputation across protein domains, pairing ESM-1v embeddings with EVE conservation and physicochemical features.

Encoder-decoder codon language model that reverse-translates a protein into species-specific coding sequences for synthetic mRNA design.

Molecular conformation description language encoding 3D geometry as SMILES plus internal-coordinate tokens, turning 3D modeling into a sequence task.

Structure-based drug design that schedules noise separately for 3D coordinates and 2D topology, reaching a 95.9% PoseBusters valid rate on CrossDock.

Latent diffusion model for H&E-to-IHC stain transfer, dual-conditioned on pathology foundation-model embeddings, covering HER2, Ki67, ER, and PR.

Graph neural network that reconstructs chemical bonds and bond orders from 3D coordinates, distorted generated geometries, or bare 2D connectivity.

Unified atomic diffusion model for protein structure prediction and de novo antibody design, steered by epitope and target-structure constraints.

Pocket-conditioned 3D diffusion model for scaffold decoration, guided by evolutionary residue conservation and a protein-ligand interaction prior.

EEG foundation model that separates channel-wise from temporal attention, pretrained on 25,000 hours of recordings spanning eight task paradigms.