26 July 2024 in Journal of High Energy Physics
Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and ‘tag’ them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics beyond the Standard Model. Current approaches use deep learning to uncover hidden patterns in complex collision data. However, the representation of jets as inputs to a deep learning model have been varied, and often, informative features are withheld from models. In this study, we propose a graph-based representation of a jet that encodes the most information possible. To learn best from this representation, we design Particle Chebyshev Network (PCN), a graph neural network (GNN) using Chebyshev graph convolutions (ChebConv). ChebConv has been demonstrated as an effective alternative to classical graph convolutions in GNNs and has yet to be explored in jet tagging. PCN achieves a substantial improvement in accuracy over existing taggers and opens the door to future studies into graph-based representations of jets and ChebConv layers in high-energy physics experiments. Code is available at https://github.com/YVSemlani/PCN-Jet-Tagging
7 February 2026 in Cytoskeleton
We describe a method for determining the ultrastructural organization of axons and varicosities of cultured dorsal root ganglion (DRG) neurons using cryogenic electron microscopy (cryo‐EM). Cryo‐EM reveals the dimensions, proximity, and overall organization of biological specimens in a near‐native state, avoiding artifacts of fixation and heavy metal staining employed in classic thin section ultramicroscopy. Cryo‐EM excels with thin specimens, and the axons of cryo‐preserved cultured DRG neurons are the ideal thickness for high‐resolution cryo‐electron tomography. DRG neurons are a particularly interesting neuronal preparation because they can be isolated from animals of any age, providing a unique resource to examine age‐related changes in axonal morphology. We provide a detailed, step‐by‐step protocol from DRG isolation and culturing, through cryo‐preservation and data acquisition and analysis. We also provide a description for data processing in batch and how implementing deep‐learning strategies can facilitate taking tilt‐series data through the process of semi‐automated tomographic segmentation required for quantitative descriptions of ultrastructural features. We use segmentations focused on the cytoskeletal elements of axons and varicosities of young and old cultured DRG neurons to highlight the approach.