Models (8)
A transformer that predicts protein-RNA binding affinity from Boltz-2 pre-structural embeddings via cross-modal attention, without requiring predicted structures.
A polarizable electrostatic machine-learning interatomic potential extending MACE with long-range induction, trained on 100M OMol25 DFT calculations.
Generative foundation model that enhances spatial transcriptomics by conditioning on H&E histology, scRNA-seq references, and spatial co-expression priors.
A family of sensor-language foundation models from Google that aligns wearable biosignals with natural language for zero-shot recognition, retrieval, and captioning.
BrainOmni
Tsinghua University / Shanghai AI Laboratory / University of Cambridge / University College London
Released May 18, 2025
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.
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.
Open respiratory acoustic foundation models pretrained on ~136K curated cough and breathing recordings for health tasks such as disease detection and lung function estimation.
Sequence-based deep learning model for antibody paratope prediction using convolutional and recurrent neural networks. Identifies antigen-contacting residues from CDR sequences alone.