Different spatial or temporal protein populations, such as cell-surface/intracellular or pre-existing/nascent subpopulations, determine the basal and activity-induced functions of individual synapses within a neuron in vivo. Here, we developed a simple and generalizable platform to image different spatial and temporal subpopulations of endogenous proteins at thousands of synapses in single neurons in the mammalian brain. The platform is based on the development, improvement and integration of CRISPR-Cas9-mediated protein labeling methods, chemical tag labeling techniques, and a semi-automatic analytical pipeline. The combined platform enables whole-cell mapping of total, cell-surface, intracellular, pre-existing, nascent or nascent-and-surface populations of endogenous proteins, such as receptor, scaffold and signaling proteins, at thousands of synapses in individual neurons in living or fixed mouse brain. Our single-cell “synaptome” mapping of endogenous protein subpopulations comprehensively visualizes the spatial representation of synapse diversity in protein localization, trafficking and turnover, providing valuable insights into single-cell organization and computations in the brain.
Aims: Severe coronary calcification complicates percutaneous coronary intervention (PCI), often necessitating atherectomy-based debulking devices that increase procedural complexity and risk. We aimed to develop and externally validate a Transformer-based deep learning model using preprocedural cardiac computed tomography angiography (CCTA) to predict atherectomy device use during PCI and compare its performance with that of blinded human readers, including general cardiologists and PCI experts. Methods and results: This retrospective multicentre study included 498 calcified coronary lesions from 419 patients who underwent PCI after preprocedural CCTA. Data from 12 institutions were used for training and validation with four-fold cross-validation, and data from two independent institutions (97 lesions) served as an external test cohort. The model combined a convolutional neural network feature extractor with Transformer-based multiple instance learning, and clinical variables were evaluated for incremental value. In the external test cohort, the CCTA-only model achieved an area under the receiver operating characteristic curve (AUC) of 0.788 (95% confidence interval [CI], 0.691–0.873) for predicting atherectomy device use. Adding clinical variables resulted in an AUC of 0.805 (95% CI, 0.713–0.886), indicating limited incremental value. In the reader comparison, the model showed higher accuracy than general cardiologists (0.742 vs. 0.619; P = 0.029) and numerically similar accuracy to PCI experts (0.742 vs. 0.670; P = 0.230). Conclusion: A Transformer-based deep learning model using preprocedural CCTA showed clinically relevant performance for predicting atherectomy device use during PCI in an independent external test cohort. These findings suggest that the model may support lesion assessment and procedural planning.