Academic

University of Cambridge

British research university

Location: Cambridge, UK
Website
8 models(3 Protein, 3 Biosignals, 1 RNA, 1 Small molecule, 1 Spatial omics, 1 Pathology, 1 Single-cell, 1 Language model, 1 Imaging)

Models (8)

ZeroFold

University of Cambridge / AstraZeneca

Released March 24, 2026

A transformer that predicts protein-RNA binding affinity from Boltz-2 pre-structural embeddings via cross-modal attention, without requiring predicted structures.

RNAProtein

MACE-POLAR-1

University of Cambridge

Released February 23, 2026

9

A polarizable electrostatic machine-learning interatomic potential extending MACE with long-range induction, trained on 100M OMol25 DFT calculations.

Small moleculeProtein

FOCUS

University of Cambridge

Released December 23, 2025

Generative foundation model that enhances spatial transcriptomics by conditioning on H&E histology, scRNA-seq references, and spatial co-expression priors.

Spatial omicsPathologySingle-cell

SensorLM

Google Research / Google DeepMind / University of Cambridge

Released June 10, 2025

47

A family of sensor-language foundation models from Google that aligns wearable biosignals with natural language for zero-shot recognition, retrieval, and captioning.

BiosignalsLanguage model

BrainOmni

Tsinghua University / Shanghai AI Laboratory / University of Cambridge / University College London

Released May 18, 2025

2367

A brain foundation model that unifies EEG and MEG signals via a shared discrete tokenizer and self-supervised pretraining on 2,653 hours of recordings.

Biosignals

SAM-Brain3D

University of Cambridge / Shanghai AI Laboratory

Released May 1, 2025

76

A 3D brain MRI segmentation foundation model trained on 66,000+ brain image-label pairs across 14 MRI sub-modalities, paired with a hypergraph dynamic adapter for brain disease analysis.

Imaging

OPERA

University of Cambridge

Released June 23, 2024

4180

Open respiratory acoustic foundation models pretrained on ~136K curated cough and breathing recordings for health tasks such as disease detection and lung function estimation.

Biosignals

Parapred

University of Cambridge

Released September 1, 2018

15061

Sequence-based deep learning model for antibody paratope prediction using convolutional and recurrent neural networks. Identifies antigen-contacting residues from CDR sequences alone.

Protein