All Competitors

Health acoustics foundation model that turns short clips of coughs and breaths into embeddings for building acoustic biomarker models with less data.

Vision-language pretraining for 3D CT volumes, aligning scans with their radiology reports for zero-shot classification, retrieval, and segmentation.

Structure-aware antibody language model with sequence embeddings contrastively aligned to crystal structures, reaching AUROC 0.875 on HER2 binding.

Antibody language model pretrained on 779M human B cell receptor sequences, reading a heavy chain, a light chain, or both paired in one input.

Zero-shot variant effect prediction that fuses a frozen protein language model with an equivariant graph network over residue contact graphs.

Generative toolkit that synthesizes six aligned immunohistochemistry markers from one H&E histopathology image, trained on unpaired stains.

Vision foundation model for the tree of life, trained on TreeOfLife-10M for zero-shot species classification of plants, animals, and fungi.

Single-cell foundation model producing species-agnostic cell embeddings by representing genes through frozen ESM-2 protein language model embeddings.

AlphaFold fine-tuned via OpenFold on 944 high-resolution MHC-peptide structures, reaching median peptide RMSD of 0.65 Å on held-out complexes.

Protein structure tokenizer that encodes all-atom folds as artificial amino acids and decodes them back to coordinates at TM-score above 0.96.

Structure-based RNA virtual screening that scores small molecules against a binding site's base-pairing graph, around 10,000x faster than docking.

Promptable 3D foundation model for volumetric CT segmentation, covering over 200 anatomical categories through point, box, and free-text prompts.

Radiology-specific multimodal LLM that generates the findings section of a chest X-ray report from a frontal image, pairing RAD-DINO with Vicuna-7B.

Universal cell segmentation model adapting Meta's SAM to segment mammalian cells, yeast, and bacteria across imaging modalities without retraining.

Sequence-only cancer driver mutation predictor combining ProtT5-XL embeddings with per-position evolutionary statistics and a confidence score.

Multi-task pretrained biomedical imaging model whose frozen features match ImageNet fine-tuning on CT, X-ray and histology tasks from 1% of labels.

Generative language model trained on 558 million antibody sequences for infilling-based design of CDR loops and full-length immunoglobulin sequences.

Full-precision LoRA fine-tuning of ESM-2 for per-residue binding site prediction, where low-rank constraints curb overfitting on small datasets.

4-bit QLoRA fine-tunes of ESM-2 for per-residue protein binding site prediction, released as a checkpoint family spanning 8M to 650M parameters.

Pseudo-membrane generator for fluorescence microscopy that synthesizes missing membrane staining from nuclei to improve single-cell segmentation.

RNA 3D structure prediction pipeline pairing a transformer (RNAformer) that predicts inter-nucleotide geometries with Rosetta energy minimization.

EEG foundation model that pairs a convolutional encoder with a GPT backbone, pretrained by masked-segment reconstruction for low-data BCI decoding.

Diffusion model for programmable protein design that jointly samples structures and sequences, conditioned on symmetry, shape, or text prompts.