All Competitors

Structural brain MRI foundation model pretrained on synthetic healthy volumes only, giving frozen features for brain age, dementia risk and image QC.

Generates single-cell transcriptomes from structured biological metadata via contrastive language-omics pretraining and a diffusion transformer.

Compact 167M-parameter protein language model built on a multiplicative LSTM, giving zero-shot variant effect and fitness prediction from sequence.

3D CT volume reconstruction from real chest X-rays, using a diffusion cascade that lifts one or two radiographs into a volume and then upscales it.

EEG foundation model pretrained by spectrogram reconstruction that improves online directional motor-imagery brain-computer interface control.

Virtual cell model using masked discrete diffusion over the whole transcriptome to simulate scRNA-seq perturbation responses across tissues.

Protein-language diffusion model generating all-atom conformational ensembles for intrinsically disordered proteins and disordered regions.

Transformer that predicts protein-RNA binding affinity from Boltz-2 pre-structural embeddings via cross-modal attention, with no 3D structure step.

Joint embedding predictive architecture for at-home polysomnography, encoding full-night seven-channel recordings for sleep staging and disease risk.

Generative RNA foundation model trained on 114 million full-length sequences for de novo design of tRNAs, aptamers, CRISPR guide RNAs, and mRNAs.

Molecular foundation models pretrained on density functional theory data, encoding 3D geometry and quantum behavior for ADMET and drug discovery.

Autoregressive generative model for protein molecular dynamics that emits flexible-length trajectories frame by frame with anti-drifting sampling.

Multimodal reasoning LLM for protein function prediction, fusing protein language model embeddings to emit interpretable GO-term reasoning traces.

Protein complex quality assessment model that scores docked and predicted dimers with separate chain graphs and an interface contact graph.

Protein function prediction model that autoregressively generates Gene Ontology terms from amino acid sequence instead of classifying fixed labels.

Contrastive dual-encoder model embedding protein domains and peptides in one space to predict domain-peptide binding specificity at proteome scale.

Histopathology foundation model with 1.1B parameters, trained entirely on public data using JEDI, a dual-stage strategy combining JEPA and DINO.

Generative adversarial network trained on single-cell and bulk RNA-seq for sample stratification, marker analysis, and synthetic data generation.

Structure-aware protein language model using structure-guided masking and a causal objective for variant effect prediction and protein discovery.

Multimodal molecular foundation model fusing SELFIES, 2D graphs, text, and knowledge graphs via contrastive pretraining for property prediction.

All-atom E(3)-equivariant diffusion model that refines RNA structures by resolving steric clashes and completing missing atoms.

Generative foundation model that produces atom-level molecular dynamics trajectories for protein monomers and protein-ligand complexes.

Multimodal reverse-translation language model that generates species-aware mRNA coding sequences from protein sequences, conditioned on host taxonomy.