Naturally occurring pain and itch disorders in the domestic dog represent an important and underexploited opportunity for translational sensory neuroscience. These conditions largely mirror human disease, highlighting the need for detailed comparative understanding of canine somatosensory neurobiology. Here, we present a single-cell transcriptomic characterisation of the canine dorsal root ganglion (DRG), providing molecular insights into sensory neuron diversity in a species of direct veterinary and biomedical relevance. We develop a novel mechanical dissociation and fluorescence-activated cell sorting strategy enabling purification of intact whole neurons from adult canine DRG, followed by deep, full-length RNA sequencing using FLASH-seq. This approach yields high-quality transcriptional profiles with molecular depth analogous to deep neuronal profiling in human DRG, enabling resolution of neuronal identities and subtype-specific gene programs. Using these data, we identify canine sensory neuron clusters conforming to conserved principles of DRG molecular organization observed across species, including peptidergic and non-peptidergic nociceptors, low-threshold mechanoreceptors, proprioceptors, and thermosensory populations. Cross-species comparisons with human and mouse DRG datasets reveal broad conservation of pain- and itch-relevant pathways and therapeutic targets, alongside biologically meaningful divergence. We further identify species-specific differences in subtype-restricted expression of the pharmacologically relevant receptors IL31RA and SSTR2, which we validate using in situ hybridization and contextualize with human spatial transcriptomic data. Finally, we provide evidence that domestication-associated genes are non-randomly enriched in specific sensory neuron populations, suggesting that evolutionary history may have shaped somatosensory function. These data represent a resource for comparative sensory neuroscience and inform translational interpretation of pain and itch therapeutics across species.
SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images
arXiv:2604.15777v1 Announce Type: cross Abstract: Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is

