All Competitors

Gastrointestinal histopathology foundation model pretrained on 353 million multi-scale patches from 210,000 H&E whole-slide images of GI tissue.

Single-cell foundation model combining regulatory network priors with a Mamba backbone for clustering, batch integration, and perturbation modeling.

Generative imaging model simulating single-cell fluorescence microscopy for all 12,800 human proteins in the Human Protein Atlas.

Protein foundation model for de novo enzyme design that co-designs sequence and 3D structure under small-molecule ligand guidance, at 730M parameters.

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

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

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.

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

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

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.

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

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

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

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

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.

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

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

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.

Protein backbone design model pairing flow matching with a Mamba state-space backbone, generating long proteins in linear time with exact geometry.