All Competitors

Pretrains on EC, GO, InterPro and Gene3D ontology tokens with no amino acids, building a protein feature space from curated function alone.

Tandem mass spectrum prediction that builds explicit fragmentation pathways, mapping unknown spectra onto 800 million predicted PubChem spectra.

Antibody sequence design conditioned on antigen structure, generating CDRs or full variable regions without epitope annotation or docked frameworks.

Cell-free RNA language model for liquid biopsy, fusing RNA sequence embeddings with cfRNA abundance across 306 billion pretraining tokens.

Digital pathology model inferring collagen structure from H&E whole-slide images, trained against polarization imaging of Picrosirius Red slides.

Contrastive dual-encoder model for DIA proteomics, embedding peptides and spectra in a shared space for zero-shot peptide-spectrum matching.

Multimodal protein model pairing a sequence encoder with a Gene Ontology branch, trained in recursive cycles that clean their own noisy labels.

Retrieval-augmented diffusion model that designs antibody CDR sequences by conditioning on structurally homologous CDR-like motifs from the PDB.

Sequence-based multitask model predicting covalently ligandable cysteines and reversible ligand-binding residues across the human proteome.

RNA foundation model trained on chemical mapping data, with embeddings adapted to predict RNA secondary and tertiary structure and mRNA stability.

Cryo-ET particle picking model that localizes and classifies multiple protein complexes in a tomogram with a single 3D U-Net forward pass.

Small-molecule drug discovery foundation model covering ADMET, retrosynthesis, drug-target activity, and molecular optimization in a 2.6B checkpoint.

Machine-learned interatomic potential supplying quantum-quality geometric restraints for refining cryo-EM and X-ray protein structures in Phenix.

Mammography report generation model, a LoRA adaptation of MedGemma-4B-it that writes narrative radiology reports carrying BI-RADS assessments.

Breast-specialized multimodal pathology foundation model for core needle biopsy diagnosis, with conformal risk control gating report release.

Single-cell ATAC-seq foundation model pretrained on 2.8 million cells across 1.15 million chromatin regions via masked peak reconstruction.

Vision-language foundation model for coronary angiography that aligns six-view cine studies with procedural reports for zero-shot lesion assessment.

Cardiac SPECT attenuation correction that turns non-corrected myocardial perfusion scans into corrected images without any CT input at inference.

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.

Antibody CDR sequence and structure co-design from the whole antigen, using a relation-aware equivariant graph network with no specified epitope.

ADMET property prediction for CYP inhibition, PXR activation, hERG, microsomal clearance, and permeability, all trained on public assay data.

Tri-modal pathology foundation model aligning whole-slide images, transcriptomes, and diagnostic reports, and running on any subset of the three.

Single-cell foundation model inferring cis-regulatory relationships from scRNA-seq and scATAC-seq, pretrained on an atlas of 1.3 million cells.