All Competitors

3D MRI organ segmentation foundation model built on Swin-UNETR and trained on the UKBOB whole-body dataset covering 72 organs and skeletal structures.

Protein language model interpretability adapter that factors ESM2 and ProtBERT embeddings into named biochemical features plus a residual subspace.

Flexible protein-ligand docking and binding affinity prediction from an apo receptor structure and ligand SMILES, using an 8-layer pair transformer.

RNA 3D structure reconstruction from cryo-EM density maps, using a 3D U-Net that predicts 18 atom types and assigns sequence by global alignment.

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

TCR-pMHC specificity prediction that folds frozen ESM-2 and AlphaFold2 representations into a three-body peptide-MHC-CDR3 energy tensor.

Histopathology foundation models trained on up to 100x fewer whole-slide images than peers, matching UNI-2 across 13 tile- and slide-level tasks.

Protein binder design that inverts the frozen Boltz-1 all-atom predictor, targeting small molecules, nucleic acids, metals, and modified residues.

C/D box snoRNA gene predictor for any eukaryote genome, built on DNABERT and able to separate expressed snoRNAs from their pseudogenes.

Bacterial genome language model tokenizing whole genomes as ordered conserved elements; frozen embeddings beat Pfam baselines on 23 of 25 phenotypes.

DNA and RNA language model with a data-driven 4,096-token unigram vocabulary, matching larger genomic foundation models at 89.2M parameters.

Promptable 3D medical image and video segmentation foundation model fine-tuned from SAM 2.1, cutting lesion annotation time by up to 92%.

Sequence-based protein stability predictor estimating ddG for single and multi-point mutations while enforcing thermodynamic antisymmetry.

Regulatory genomics foundation model pretrained on 6,391 human ChIP-seq cistromes, representing how ~1,000 transcription regulators cooperate.

Hi-C resolution enhancement model combining a U²-Net with self-attention to recover TAD boundaries and chromatin loops from sparse contact maps.

Enhancer models predicting cell-type-specific chromatin accessibility from DNA sequence, with a pretrained zoo and synthetic enhancer design tools.

De novo protein design from natural language: a 16B-parameter framework turning text descriptions into sequences via structure-conditioned generation.

Multimodal graph foundation model fusing single-cell expression, biomedical text, and signaling networks, pretrained on ~80M sc/snRNA-seq profiles.

Retrieval-augmented protein language model that conditions ESM-2 on homologous sequences via cross-attention for conditional sequence generation.

General medical vision-language model trained with reinforcement learning to reason step by step over medical images for diagnosis and visual QA.

Histopathology foundation model pretrained on over 1 million H&E slides from 800,000 patients. Leads the HEST spatial gene expression benchmark.

Hypergraph foundation model for brain disease diagnosis from resting-state fMRI, self-supervised on high-order connectivity among brain regions.

Protein function prediction fusing five Gene Ontology pipelines, two of them deep models over protein and DNA language model embeddings.