The Alan Turing Institute

Image-to-transcriptome diffusion model generating scGPT-space single-cell RNA embeddings from Cell Painting fluorescence microscopy features.

Energy-based flow matching for 3D molecular structure, using an idempotent predict-and-refine map for protein backbone generation and ligand docking.

Whole-heart segmentation foundation model for CT and MRI, pretrained self-supervised on unlabeled cardiac scans with an xLSTM-UNet backbone.

Crossmodal diffusion model synthesizing bulk tumor gene expression from H&E whole-slide images, so grading and survival prediction need no RNA assay.

Neuroscience literature language model that predicts experimental outcomes from study methods, LoRA-tuned on 1.3 billion tokens of papers.