All Competitors

Pathology vision foundation model adapting DINOv3-style self-supervised learning to whole-slide histopathology across continuous magnifications and scales.

Pretrained antibody structure predictor that outputs full paired heavy/light 3D structures faster than protein language models generate embeddings.

Transformer framework that models protein-protein interactions at residue resolution, generalizing zero-shot to unseen MHC alleles and sequence-neutral PTMs from one fixed checkpoint.

A 120M-parameter genomic foundation model that learns adaptive DNA token boundaries via H-Net-style dynamic chunking instead of fixed k-mer or byte-pair tokenization.

A deep generative decoder that infers microRNA expression directly from bulk or single-cell mRNA gene expression via a shared mRNA/miRNA latent space.

Protein pretraining framework that learns representations directly from cryo-EM density maps, transferring to flexibility, active-site, binding-affinity, and stability tasks.

Self-supervised foundation model that learns reusable representations of cancer genomes from somatic SNVs and copy-number alterations across 33 tumor types.

A self-supervised masked autoencoder for RNA-seq count data, pretrained on 1.4M public samples to learn transferable transcriptomic representations without per-dataset re-training.

A dual-stream self-supervised foundation model for continuous glucose monitoring data, separating slow physiological state from transient glucose events.

Genetically aligned foundation model for blood smear cytology that links single white-blood-cell morphology to chromosomal aberrations and mutations for AML/APL diagnosis.

Biohub's 2026 protein language model trained on ~2.8 billion sequences, forming the representation core of its world model of protein biology.

A constrained deep flow-matching framework for distributional translation of omics signatures across biological domains, such as mouse-to-human transcriptomics, without paired samples.

A hyperbolic protein language model for alignment-free phylogenetic inference, producing distance matrices for tree placement without multiple sequence alignment.

A spatial-transcriptomics foundation model for the tumor microenvironment that produces TME-aware embeddings and enables in silico perturbation from a fixed pretrained checkpoint.

SE(3)-invariant masked autoencoder pretrained on ~370K AlphaFold-DB structures for protein fold representation learning, enabling frozen-feature and zero-shot fold classification.

A mechanistic-interpretability framework that trains sparse autoencoders on protein language model embeddings to extract interpretable features for zero-shot variant effect prediction.

A residual VQ-VAE tokenizer that learns a discrete alphabet of protein conformational ensembles from molecular dynamics data, usable as a frozen representation layer for downstream tasks.

A permutation-invariant denoising transformer trained on ~2 million bacterial community samples to learn member-level stability scores and predict microbiome composition dynamics zero-shot.

A multi-organ foundation model aligning histology image features with spatial-transcriptomics gene expression across 13 organs for zero-shot virtual ST and survival prediction.

Contrastively fine-tuned ESM-2 (35M and 150M) protein language models that produce general-purpose sequence embeddings where biological similarity maps to embedding proximity.

A family of GPT-2-style causal language models pretrained on 539,000+ microbiome samples, enabling zero- and few-shot transfer across microbiome prediction tasks.

A self-supervised DINOv3-based foundation model for brain MRI, pretrained on ~6.6M unlabeled axial slices and transferable to diverse neuroimaging tasks.

SMILES-based chemical language models pretrained on 100M+ molecules to natively represent therapeutic peptide chemistry, including non-canonical residues.

A CLIP-style dual-encoder model that learns a shared peptide-spectrum representation for zero-shot peptide-spectrum-match inference in DIA proteomics.