foundation-model

Aidoc CARE is one radiology foundation model, pretrained on CT scans without labels, whose task-specific heads have each been FDA-cleared to flag urgent findings in emergency scans so radiologists read those first. Its oncology relevance is indirect, catching incidental masses; the regulatory evidence covers triage, not diagnostic accuracy for tumours.

Predicts the 3D shape of proteins together with DNA, RNA, small molecules and antibodies, the starting point for much modern drug design.

Reads a million letters of DNA at once and predicts how a mutation changes gene regulation, splicing and chromatin.

Scored all 71 million possible single-letter protein changes in humans as likely harmful or benign.

Atlas is a pathology foundation model trained on 1.2 million slides from two of the world's largest hospitals.

BioEmu is a Microsoft generative diffusion model that predicts the range of shapes a protein moves between, not one static structure, thousands of times faster than molecular dynamics simulation. For cancer drug discovery that can reveal transient pockets, as in KRAS, that static predictors miss, but its outputs are approximate and validated mainly on small proteins.

Open-source structure models that match AlphaFold 3, with Boltz-2 also predicting how strongly a drug binds.

Turns a cell's gene expression into a sentence so a normal language model can reason about it; a 27-billion-parameter version proposed a cancer immunotherapy idea that was confirmed in the lab.

CellFM is an 800-million-parameter single-cell model trained on 100 million human cells.

Structure and antibody-design models from Chai Discovery, with Chai-2 reporting high zero-shot antibody hit rates.

A pathology model trained across 19 cancer types that predicts survival and mutations from slides.

A model pretrained on 148,000 CT scans to segment organs and triage findings.

Models that predict how DNA sequence controls gene activity, used to interpret non-coding cancer mutations.

ESM3 is a generative protein model that designed a working fluorescent protein far from any natural sequence.

A DNA language model trained on 9.3 trillion bases that can flag cancer-causing BRCA1 variants without being told about them.

A model trained on millions of hospital records that forecasts a patient's next diagnoses.

Geneformer is a transformer trained on about 30 million single cells that encodes each cell as a ranked list of its genes, so deleting a gene in silico shows which genes matter in a disease. It was the first single-cell foundation model in general use, though benchmarks find only modest gains over linear baselines on some tasks.

Uses text embeddings of gene descriptions from a general LLM to represent cells, and performs surprisingly well.

An open 1.1-billion-parameter pathology model from a French startup, among the strongest on public benchmarks.

Hibou is a family of open pathology foundation models under a permissive licence.

Google's medical versions of its Gemini models, able to reason over text, images, and long records.

Adaptations of Meta's Segment Anything model that outline tumours and organs on any scan with a click.

Merlin is a model trained on 15,000 CT scans with their reports that can find and describe hundreds of findings.

Midnight is a pathology model that matched the leaders while training on far fewer slides.

A model that reads slides and clinical text together to predict who will respond to immunotherapy.

Nicheformer is a model trained on both dissociated and spatial data so it learns how a cell's neighbourhood shapes it.

DNA language models trained on thousands of genomes for variant and regulatory prediction.

A model trained on billions of cell microscopy images to read what a drug or gene knockout does to a cell.

Owkin's open pathology models trained on TCGA and its federated hospital network.

PLUTO is PathAI's compact pathology foundation model, a vision transformer pretrained at several magnifications on 195 million tiles from 158,000 slides, so one network serves slide-level and biomarker quantification tasks at whatever resolution each needs. It runs inside PathAI's AISight product, but its weights are proprietary, so outside groups cannot benchmark or adapt it.

An open pathology model trained on 1.3 billion image tiles from a US health system, modelling whole slides at gigapixel scale.

An open generalist model that answers questions about 2D and 3D scans.

The tools that design entirely new proteins to bind a chosen target, now used for cancer binders and antibodies.

scFoundation is a 100-million-parameter model trained on 50 million cells, from China's BioMap.

A GPT-style model for single-cell data that predicts cell types, perturbation responses, and gene networks.

Predicts how cells will respond to a drug or gene knockout, trained on over 100 million perturbed cells.

Strand AI's first model, Lattice, predicts which proteins sit where across a tumour from the ordinary stained slide a hospital already has, so a whole archive can be profiled without spending tissue on extra laboratory staining.

Models trained on Tempus's paired genomic, pathology, imaging and outcome data to predict response and prognosis.

TITAN is a model that summarises a whole slide, not just tiles, and can write a draft pathology report.

CZI's open cross-species cell models and a reasoning model trained on them.

Two open academic pathology models: UNI reads tissue images, CONCH links images with pathology text.

Universal Cell Embedding maps any cell from any species into one shared space without retraining.

A pathology foundation model trained on millions of slides that can detect cancer and predict biomarkers from an ordinary H&E slide.