Artificial Intelligence Medical Compendium

Decoder DNA foundation models pretrain with dense next-token prediction and scale to long sequences, but their representations are directional. This is a poor fit for genomic tasks that need sequence context both upstream and downstream of a locus. B... read more 

The International Mouse Phenotyping Consortium (IMPC) maintains a large archive of whole-body dorsoventral radiographs. However, heterogeneity in file formats, metadata completeness, orientation, and image quality limits its reuse for large-scale qua... read more 

Pancreatic lipomatosis, characterized by progressive adipose replacement of the exocrine pancreas, is a known consequence of chronic pancreatitis. Despite its clinical relevance, the mechanisms driving lipomatosis remain poorly understood. Here, we u... read more 

Tumour heterogeneity reflects both cellular identity (lineage) and state (active transcriptional programs), yet computational methods generally analyse these axes separately. We introduce CellScribe, a generative framework that conditions a pretraine... read more 

Subcellular transcript localization shapes gene regulation and cellular function, yet profiling it at scale remains difficult, limiting our ability to study subcellular heterogeneity across tissues and disease. Here, we present SVC, a Vision Transfor... read more 

Super-enhancers (SEs) drive cell-identity gene expression, yet their identification relies on epigenomic profiling (e.g., H3K27ac ChIP-seq), precluding discovery in unprofiled cellular states and leaving their underlying sequence grammar unknown. Her... read more 

Computed tomography (CT) is a widely used, non-invasive imaging tool to monitor tumor growth. Tumor identification and volumetric quantification are crucial for assessing tumor burden, whereas tracking individual tumors by aligning scans from multipl... read more 

Ovarian cancer, a gynecological malignancy, poses a significant challenge as researchers struggle to comprehend how tumor cells communicate with the immune system. Ovarian tumors contain both bulk cancer cells and cancer stem cells (CSCs), which are ... read more 

Background and Objective: Cardiac-cycle wall shear stress (WSS) is relevant to intracranial aneurysm hemodynamic assessment, but transient computational fluid dynamics (CFD) is costly. Existing surrogates use steady-flow priors or joint steady/transi... read more 

Glycans encode biological specificity through branching, linkage and stereochemical diversity, and have traditionally been modelled using specialised computational representations distinct from those developed for general chemistry. It remains unclea... read more