Stabilizing HIF to Ameliorate Anemia.

Erythropoietin (EPO) production in the kidney is regulated by the oxygen-sensing transcription factor HIF-1α, which is degraded under normoxic conditions by HIF-prolyl hydroxylase (HIF-PHD). Inhibition of HIF-PHD by roxadustat leads to increased EPO production, better iron absorption, and amelioration of anemia in chronic kidney disease (CKD).

Small Molecule Targets TMED9 and Promotes Lysosomal Degradation to Reverse Proteinopathy.

Intracellular accumulation of misfolded proteins causes toxic proteinopathies, diseases without targeted therapies. Mucin 1 kidney disease (MKD) results from a frameshift mutation in the MUC1 gene (MUC1-fs). Here, we show that MKD is a toxic proteinopathy. Intracellular MUC1-fs accumulation activated the ATF6 unfolded protein response (UPR) branch. We identified BRD4780, a small molecule that clears MUC1-fs from patient cells, from kidneys of knockin mice and from patient kidney organoids. MUC1-fs is trapped in TMED9 cargo receptor-containing vesicles of the early secretory pathway. BRD4780 binds TMED9, releases MUC1-fs, and re-routes it for lysosomal degradation, an effect phenocopied by TMED9 deletion. Our findings reveal BRD4780 as a promising lead for the treatment of MKD and other toxic proteinopathies. Generally, we elucidate a novel mechanism for the entrapment of misfolded proteins by cargo receptors and a strategy for their release and anterograde trafficking to the lysosome.

Intestinal CXCR6+ ILC3s migrate to the kidney and exacerbate renal fibrosis via IL-23 receptor signaling enhanced by PD-1 expression.

Group 3 innate lymphoid cells (ILC3s) regulate inflammation and tissue repair at mucosal sites, but whether these functions pertain to other tissues-like the kidneys-remains unclear. Here, we observed that renal fibrosis in humans was associated with increased ILC3s in the kidneys and blood. In mice, we showed that CXCR6+ ILC3s rapidly migrated from the intestinal mucosa and accumulated in the kidney via CXCL16 released from the injured tubules. Within the fibrotic kidney, ILC3s increased the expression of programmed cell death-1 (PD-1) and subsequent IL-17A production to directly activate myofibroblasts and fibrotic niche formation. ILC3 expression of PD-1 inhibited IL-23R endocytosis and consequently amplified the JAK2/STAT3/RORγt/IL-17A pathway that was essential for the pro-fibrogenic effect of ILC3s. Thus, we reveal a hitherto unrecognized migration pathway of ILC3s from the intestine to the kidney and the PD-1-dependent function of ILC3s in promoting renal fibrosis.

The immune cell landscape in kidneys of patients with lupus nephritis.

Lupus nephritis is a potentially fatal autoimmune disease for which the current treatment is ineffective and often toxic. To develop mechanistic hypotheses of disease, we analyzed kidney samples from patients with lupus nephritis and from healthy control subjects using single-cell RNA sequencing. Our analysis revealed 21 subsets of leukocytes active in disease, including multiple populations of myeloid cells, T cells, natural killer cells and B cells that demonstrated both pro-inflammatory responses and inflammation-resolving responses. We found evidence of local activation of B cells correlated with an age-associated B-cell signature and evidence of progressive stages of monocyte differentiation within the kidney. A clear interferon response was observed in most cells. Two chemokine receptors, CXCR4 and CX3CR1, were broadly expressed, implying a potentially central role in cell trafficking. Gene expression of immune cells in urine and kidney was highly correlated, which would suggest that urine might serve as a surrogate for kidney biopsies.

Multiscale topology classifies cells in subcellular spatial transcriptomics.

Spatial transcriptomics measures in situ gene expression at millions of locations within a tissue1, hitherto with some trade-off between transcriptome depth, spatial resolution and sample size2. Although integration of image-based segmentation has enabled impactful work in this context, it is limited by imaging quality and tissue heterogeneity. By contrast, recent array-based technologies offer the ability to measure the entire transcriptome at subcellular resolution across large samples3-6. Presently, there exist no approaches for cell type identification that directly leverage this information to annotate individual cells. Here we propose a multiscale approach to automatically classify cell types at this subcellular level, using both transcriptomic information and spatial context. We showcase this on both targeted and whole-transcriptome spatial platforms, improving cell classification and morphology for human kidney tissue and pinpointing individual sparsely distributed renal mouse immune cells without reliance on image data. By integrating these predictions into a topological pipeline based on multiparameter persistent homology7-9, we identify cell spatial relationships characteristic of a mouse model of lupus nephritis, which we validate experimentally by immunofluorescence. The proposed framework readily generalizes to new platforms, providing a comprehensive pipeline bridging different levels of biological organization from genes through to tissues.

Increased cathepsin S in Prdm1-/- dendritic cells alters the TFH cell repertoire and contributes to lupus.

Aberrant population expansion of follicular helper T cells (TFH cells) occurs in patients with lupus. An unanswered question is whether an altered repertoire of T cell antigen receptors (TCRs) is associated with such expansion. Here we found that the transcription factor Blimp-1 (encoded by Prdm1) repressed expression of the gene encoding cathepsin S (Ctss), a cysteine protease that cleaves invariant chains and produces antigenic peptides for loading onto major histocompatibility complex (MHC) class II molecules. The increased CTSS expression in dendritic cells (DCs) from female mice with dendritic cell-specific conditional knockout of Prdm1 (CKO mice) altered the presentation of antigen to CD4+ T cells. Analysis of complementarity-determining region 3 (CDR3) regions containing the ß-chain variable region (Vß) demonstrated a more diverse repertoire of TFH cells from female CKO mice than of those from wild-type mice. In vivo treatment of CKO mice with a CTSS inhibitor abolished the lupus-related phenotype and reduced the diversity of the TFH cell TCR repertoire. Thus, Blimp-1 deficiency in DCs led to loss of appropriate regulation of Ctss expression in female mice and thereby modulated antigen presentation and the TFH cell repertoire to contribute to autoimmunity.

Fumarate induces vesicular release of mtDNA to drive innate immunity.

Mutations in fumarate hydratase (FH) cause hereditary leiomyomatosis and renal cell carcinoma1. Loss of FH in the kidney elicits several oncogenic signalling cascades through the accumulation of the oncometabolite fumarate2. However, although the long-term consequences of FH loss have been described, the acute response has not so far been investigated. Here we generated an inducible mouse model to study the chronology of FH loss in the kidney. We show that loss of FH leads to early alterations of mitochondrial morphology and the release of mitochondrial DNA (mtDNA) into the cytosol, where it triggers the activation of the cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING)-TANK-binding kinase 1 (TBK1) pathway and stimulates an inflammatory response that is also partially dependent on retinoic-acid-inducible gene I (RIG-I). Mechanistically, we show that this phenotype is mediated by fumarate and occurs selectively through mitochondrial-derived vesicles in a manner that depends on sorting nexin 9 (SNX9). These results reveal that increased levels of intracellular fumarate induce a remodelling of the mitochondrial network and the generation of mitochondrial-derived vesicles, which allows the release of mtDNAin the cytosol and subsequent activation of the innate immune response.

An atlas of healthy and injured cell states and niches in the human kidney.

Understanding kidney disease relies on defining the complexity of cell types and states, their associated molecular profiles and interactions within tissue neighbourhoods1. Here we applied multiple single-cell and single-nucleus assays (>400,000 nuclei or cells) and spatial imaging technologies to a broad spectrum of healthy reference kidneys (45 donors) and diseased kidneys (48 patients). This has provided a high-resolution cellular atlas of 51 main cell types, which include rare and previously undescribed cell populations. The multi-omic approach provides detailed transcriptomic profiles, regulatory factors and spatial localizations spanning the entire kidney. We also define 28 cellular states across nephron segments and interstitium that were altered in kidney injury, encompassing cycling, adaptive (successful or maladaptive repair), transitioning and degenerative states. Molecular signatures permitted the localization of these states within injury neighbourhoods using spatial transcriptomics, while large-scale 3D imaging analysis (around 1.2 million neighbourhoods) provided corresponding linkages to active immune responses. These analyses defined biological pathways that are relevant to injury time-course and niches, including signatures underlying epithelial repair that predicted maladaptive states associated with a decline in kidney function. This integrated multimodal spatial cell atlas of healthy and diseased human kidneys represents a comprehensive benchmark of cellular states, neighbourhoods, outcome-associated signatures and publicly available interactive visualizations.

The renal lineage factor PAX8 controls oncogenic signalling in kidney cancer.

Large-scale human genetic data1-3 have shown that cancer mutations display strong tissue-selectivity, but how this selectivity arises remains unclear. Here, using experimental models, functional genomics and analyses of patient samples, we demonstrate that the lineage transcription factor paired box 8 (PAX8) is required for oncogenic signalling by two common genetic alterations that cause clear cell renal cell carcinoma (ccRCC) in humans: the germline variant rs7948643 at 11q13.3 and somatic inactivation of the von Hippel-Lindau tumour suppressor (VHL)4-6. VHL loss, which is observed in about 90% of ccRCCs, can lead to hypoxia-inducible factor 2α (HIF2A) stabilization6,7. We show that HIF2A is preferentially recruited to PAX8-bound transcriptional enhancers, including a pro-tumorigenic cyclin D1 (CCND1) enhancer that is controlled by PAX8 and HIF2A. The ccRCC-protective allele C at rs7948643 inhibits PAX8 binding at this enhancer and downstream activation of CCND1 expression. Co-option of a PAX8-dependent physiological programme that supports the proliferation of normal renal epithelial cells is also required for MYC expression from the ccRCC metastasis-associated amplicons at 8q21.3-q24.3 (ref. 8). These results demonstrate that transcriptional lineage factors are essential for oncogenic signalling and that they mediate tissue-specific cancer risk associated with somatic and inherited genetic variants.

A Randomized Phase 2 Trial of Felzartamab in Antibody-Mediated Rejection.

BACKGROUND: Antibody-mediated rejection is a leading cause of kidney-transplant failure. The targeting of CD38 to inhibit graft injury caused by alloantibodies and natural killer (NK) cells may be a therapeutic option. METHODS: In this phase 2, double-blind, randomized, placebo-controlled trial, we assigned patients with antibody-mediated rejection that had occurred at least 180 days after transplantation to receive nine infusions of the CD38 monoclonal antibody felzartamab (at a dose of 16 mg per kilogram of body weight) or placebo for 6 months, followed by a 6-month observation period. The primary outcome was the safety and side-effect profile of felzartamab. Key secondary outcomes were renal-biopsy results at 24 and 52 weeks, donor-specific antibody levels, peripheral NK-cell counts, and donor-derived cell-free DNA levels. RESULTS: A total of 22 patients underwent randomization (11 to receive felzartamab and 11 to receive placebo). The median time from transplantation until trial inclusion was 9 years. Mild or moderate infusion reactions occurred in 8 patients in the felzartamab group. Serious adverse events occurred in 1 patient in the felzartamab group and in 4 patients in the placebo group; graft loss occurred in 1 patient in the placebo group. At week 24, resolution of morphologic antibody-mediated rejection was more frequent with felzartamab (in 9 of 11 patients [82%]) than with placebo (in 2 of 10 patients [20%]), for a difference of 62 percentage points (95% confidence interval [CI], 19 to 100) and a risk ratio of 0.23 (95% confidence interval [CI], 0.06 to 0.83). The median microvascular inflammation score was lower in the felzartamab group than in the placebo group (0 vs. 2.5), for a mean difference of -1.95 (95% CI, -2.97 to -0.92). Also lower was a molecular score reflecting the probability of antibody-mediated rejection (0.17 vs. 0.77) and the level of donor-derived cell-free DNA (0.31% vs. 0.82%). At week 52, the recurrence of antibody-mediated rejection was reported in 3 of 9 patients who had a response to felzartamab, with an increase in molecular activity and biomarker levels toward baseline levels. CONCLUSIONS: Felzartamab had acceptable safety and side-effect profiles in patients with antibody-mediated rejection. (Funded by MorphoSys and Human Immunology Biosciences; ClinicalTrials.gov number, NCT05021484; and EUDRACT number, 2021-000545-40.).

COVID-19 tissue atlases reveal SARS-CoV-2 pathology and cellular targets.

COVID-19, which is caused by SARS-CoV-2, can result in acute respiratory distress syndrome and multiple organ failure1-4, but little is known about its pathophysiology. Here we generated single-cell atlases of 24 lung, 16 kidney, 16 liver and 19 heart autopsy tissue samples and spatial atlases of 14 lung samples from donors who died of COVID-19. Integrated computational analysis uncovered substantial remodelling in the lung epithelial, immune and stromal compartments, with evidence of multiple paths of failed tissue regeneration, including defective alveolar type 2 differentiation and expansion of fibroblasts and putative TP63+ intrapulmonary basal-like progenitor cells. Viral RNAs were enriched in mononuclear phagocytic and endothelial lung cells, which induced specific host programs. Spatial analysis in lung distinguished inflammatory host responses in lung regions with and without viral RNA. Analysis of the other tissue atlases showed transcriptional alterations in multiple cell types in heart tissue from donors with COVID-19, and mapped cell types and genes implicated with disease severity based on COVID-19 genome-wide association studies. Our foundational dataset elucidates the biological effect of severe SARS-CoV-2 infection across the body, a key step towards new treatments.

Kidney diseases.

Dysregulation and accelerated activation of the alternative pathway (AP) of complement is known to cause or accentuate several pathologic conditions in which kidney injury leads to the appearance of hematuria and proteinuria and ultimately to the development of chronic renal failure. Multiple genetic and acquired defects involving plasma- and membrane-associated proteins are probably necessary to impair the protection of host tissues and to confer a significant predisposition to AP-mediated kidney diseases. This review aims to explore how our current understanding will make it possible to identify the mechanisms that underlie AP-mediated kidney diseases and to discuss the available clinical evidence that supports complement-directed therapies. Although the value of limiting uncontrolled complement activation has long been recognized, incorporating complement-targeted treatments into clinical use has proved challenging. Availability of anti-complement therapy has dramatically transformed the outcome of atypical hemolytic uremic syndrome, one of the most severe kidney diseases. Innovative drugs that directly counteract AP dysregulation have also opened new perspectives for the management of other kidney diseases in which complement activation is involved. However, gained experience indicates that the choice of drug should be tailored to each patient's characteristics, including clinical, histologic, genetic, and biochemical parameters. Successfully treating patients requires further research in the field and close collaboration between clinicians and researchers who have special expertise in the complement system.

Heme-induced loss of renovascular endothelial protein C receptor promotes chronic kidney disease in sickle mice.

ABSTRACT: Chronic kidney disease (CKD) is a major contributor to morbidity and mortality in sickle cell disease (SCD). Anemia, induced by chronic persistent hemolysis, is associated with the progressive deterioration of renal health, resulting in CKD. Moreover, patients with SCD experience acute kidney injury (AKI), a risk factor for CKD, often during vaso-occlusive crisis associated with acute intravascular hemolysis. However, the mechanisms of hemolysis-driven pathogenesis of the AKI-to-CKD transition in SCD remain elusive. Here, we investigated the role of increased renovascular rarefaction and the resulting substantial loss of the vascular endothelial protein C receptor (EPCR) in the progressive deterioration of renal function in transgenic SCD mice. Multiple hemolytic events raised circulating levels of soluble EPCR (sEPCR), indicating loss of EPCR from the cell surface. Using bone marrow transplantation and super-resolution ultrasound imaging, we demonstrated that SCD mice overexpressing EPCR were protective against heme-induced CKD development. In a cohort of patients with SCD, plasma sEPCR was significantly higher in individuals with CKD than in those without CKD. This study concludes that multiple hemolytic events may trigger CKD in SCD through the gradual loss of renovascular EPCR. Thus, the restoration of EPCR may be a therapeutic target, and plasma sEPCR can be developed as a prognostic marker for sickle CKD.

Cep120 is essential for kidney stromal progenitor cell growth and differentiation.

Mutations in genes that disrupt centrosome structure or function can cause congenital kidney developmental defects and lead to fibrocystic pathologies. Yet, it is unclear how defective centrosome biogenesis impacts renal progenitor cell physiology. Here, we examined the consequences of impaired centrosome duplication on kidney stromal progenitor cell growth, differentiation, and fate. Conditional deletion of the ciliopathy gene Cep120, which is essential for centrosome duplication, in the stromal mesenchyme resulted in reduced abundance of interstitial lineages including pericytes, fibroblasts and mesangial cells. These phenotypes were caused by a combination of delayed mitosis, activation of the mitotic surveillance pathway leading to apoptosis, and changes in both Wnt and Hedgehog signaling that are key for differentiation of stromal cells. Cep120 ablation resulted in small hypoplastic kidneys with medullary atrophy and delayed nephron maturation. Finally, Cep120 and centrosome loss in the interstitium sensitized kidneys of adult mice, causing rapid fibrosis after renal injury via enhanced TGF-ß/Smad3-Gli2 signaling. Our study defines the cellular and developmental defects caused by loss of Cep120 and aberrant centrosome biogenesis in the embryonic kidney stroma.

Isthmin-1: A critical regulator of branching morphogenesis and metanephric mesenchyme condensation during early kidney development.

Isthmin-1 (Ism1) was first described to be syn-expressed with Fgf8 in Xenopus. However, its biological role has not been elucidated until recent years. Despite of accumulated evidence that Ism1 participates in angiogenesis, tumor invasion, macrophage apoptosis, and glucose metabolism, the cognate receptors for Ism1 remain largely unknown. Ism1 deficiency in mice results in renal agenesis (RA) with a transient loss of Gdnf transcription and impaired mesenchyme condensation at E11.5. Ism1 binds to and activates Integrin α8ß1 to positively regulate Gdnf/Ret signaling, thus promoting mesenchyme condensation and ureteric epithelium branching morphogenesis. Here, we propose the hypothesis underlying the mechanism by which Ism1 regulates branching morphogenesis during early kidney development.

Pharmacological Targeting of Mitochondria in Diabetic Kidney Disease.

Diabetic kidney disease (DKD) is the leading cause of end-stage renal disease (ESRD) in the United States and many other countries. DKD occurs through a variety of pathogenic processes that are in part driven by hyperglycemia and glomerular hypertension, leading to gradual loss of kidney function and eventually progressing to ESRD. In type 2 diabetes, chronic hyperglycemia and glomerular hyperfiltration leads to glomerular and proximal tubular dysfunction. Simultaneously, mitochondrial dysfunction occurs in the early stages of hyperglycemia and has been identified as a key event in the development of DKD. Clinical management for DKD relies primarily on blood pressure and glycemic control through the use of numerous therapeutics that slow disease progression. Because mitochondrial function is key for renal health over time, therapeutics that improve mitochondrial function could be of value in different renal diseases. Increasing evidence supports the idea that targeting aspects of mitochondrial dysfunction, such as mitochondrial biogenesis and dynamics, restores mitochondrial function and improves renal function in DKD. We will review mitochondrial function in DKD and the effects of current and experimental therapeutics on mitochondrial biogenesis and homeostasis in DKD over time. SIGNIFICANCE STATEMENT: Diabetic kidney disease (DKD) affects 20% to 40% of patients with diabetes and has limited treatment options. Mitochondrial dysfunction has been identified as a key event in the progression of DKD, and pharmacologically restoring mitochondrial function in the early stages of DKD may be a potential therapeutic strategy in preventing disease progression.

A RhoA-YAP-c-Myc signaling axis promotes the development of polycystic kidney disease.

Autosomal dominant polycystic kidney disease (ADPKD) is an inherited disorder caused by mutations in PKD1 or PKD2 and affects one in 500-1000 humans. Limited treatment is currently available for ADPKD. Here we identify the Hippo signaling effector YAP and its transcriptional target, c-Myc, as promoters of cystic kidney pathogenesis. While transgenic overexpression of YAP promotes proliferation and tubule dilation in mouse kidneys, loss of YAP/TAZ or c-Myc suppresses cystogenesis in a mouse ADPKD model resulting from Pkd1 deficiency. Through a comprehensive kinase inhibitor screen based on a novel three-dimensional (3D) culture of Pkd1 mutant mouse kidney cells, we identified a signaling pathway involving the RhoGEF (guanine nucleotide exchange factor) LARG, the small GTPase RhoA, and the RhoA effector Rho-associated kinase (ROCK) as a critical signaling module between PKD1 and YAP. Further corroborating its physiological importance, inhibition of RhoA signaling suppresses cystogenesis in 3D culture of Pkd1 mutant kidney cells as well as Pkd1 mutant mouse kidneys in vivo. Taken together, our findings implicate the RhoA-YAP-c-Myc signaling axis as a critical mediator and potential drug target in ADPKD.

Monoallelic pathogenic ALG5 variants cause atypical polycystic kidney disease and interstitial fibrosis.

Disorders of the autosomal dominant polycystic kidney disease (ADPKD) spectrum are characterized by the development of kidney cysts and progressive kidney function decline. PKD1 and PKD2, encoding polycystin (PC)1 and 2, are the two major genes associated with ADPKD; other genes include IFT140, GANAB, DNAJB11, and ALG9. Genetic testing remains inconclusive in ∼7% of the families. We performed whole-exome sequencing in a large multiplex genetically unresolved (GUR) family affected by ADPKD-like symptoms and identified a monoallelic frameshift variant (c.703_704delCA) in ALG5. ALG5 encodes an endoplasmic-reticulum-resident enzyme required for addition of glucose molecules to the assembling N-glycan precursors. To identify additional families, we screened a cohort of 1,213 families with ADPKD-like and/or autosomal-dominant tubulointerstitial kidney diseases (ADTKD), GUR (n = 137) or naive to genetic testing (n = 1,076), by targeted massively parallel sequencing, and we accessed Genomics England 100,000 Genomes Project data. Four additional families with pathogenic variants in ALG5 were identified. Clinical presentation was consistent in the 23 affected members, with non-enlarged cystic kidneys and few or no liver cysts; 8 subjects reached end-stage kidney disease from 62 to 91 years of age. We demonstrate that ALG5 haploinsufficiency is sufficient to alter the synthesis of the N-glycan chain in renal epithelial cells. We also show that ALG5 is required for PC1 maturation and membrane and ciliary localization and that heterozygous loss of ALG5 affects PC1 maturation. Overall, our results indicate that monoallelic variants of ALG5 lead to a disorder of the ADPKD-spectrum characterized by multiple small kidney cysts, progressive interstitial fibrosis, and kidney function decline.

Results of Two Cases of Pig-to-Human Kidney Xenotransplantation.

BACKGROUND: Xenografts from genetically modified pigs have become one of the most promising solutions to the dearth of human organs available for transplantation. The challenge in this model has been hyperacute rejection. To avoid this, pigs have been bred with a knockout of the alpha-1,3-galactosyltransferase gene and with subcapsular autologous thymic tissue. METHODS: We transplanted kidneys from these genetically modified pigs into two brain-dead human recipients whose circulatory and respiratory activity was maintained on ventilators for the duration of the study. We performed serial biopsies and monitored the urine output and kinetic estimated glomerular filtration rate (eGFR) to assess renal function and xenograft rejection. RESULTS: The xenograft in both recipients began to make urine within moments after reperfusion. Over the 54-hour study, the kinetic eGFR increased from 23 ml per minute per 1.73 m2 of body-surface area before transplantation to 62 ml per minute per 1.73 m2 after transplantation in Recipient 1 and from 55 to 109 ml per minute per 1.73 m2 in Recipient 2. In both recipients, the creatinine level, which had been at a steady state, decreased after implantation of the xenograft, from 1.97 to 0.82 mg per deciliter in Recipient 1 and from 1.10 to 0.57 mg per deciliter in Recipient 2. The transplanted kidneys remained pink and well-perfused, continuing to make urine throughout the study. Biopsies that were performed at 6, 24, 48, and 54 hours revealed no signs of hyperacute or antibody-mediated rejection. Hourly urine output with the xenograft was more than double the output with the native kidneys. CONCLUSIONS: Genetically modified kidney xenografts from pigs remained viable and functioning in brain-dead human recipients for 54 hours, without signs of hyperacute rejection. (Funded by Lung Biotechnology.).

Artificial intelligence-assisted quantification and assessment of whole slide images for pediatric kidney disease diagnosis.

MOTIVATION: Pediatric kidney disease is a widespread, progressive condition that severely impacts growth and development of children. Chronic kidney disease is often more insidious in children than in adults, usually requiring a renal biopsy for diagnosis. Biopsy evaluation requires copious examination by trained pathologists, which can be tedious and prone to human error. In this study, we propose an artificial intelligence (AI) method to assist pathologists in accurate segmentation and classification of pediatric kidney structures, named as AI-based Pediatric Kidney Diagnosis (APKD). RESULTS: We collected 2935 pediatric patients diagnosed with kidney disease for the development of APKD. The dataset comprised 93 932 histological structures annotated manually by three skilled nephropathologists. APKD scored an average accuracy of 94% for each kidney structure category, including 99% in the glomerulus. We found strong correlation between the model and manual detection in detected glomeruli (Spearman correlation coefficient r = 0.98, P < .001; intraclass correlation coefficient ICC = 0.98, 95% CI = 0.96-0.98). Compared to manual detection, APKD was approximately 5.5 times faster in segmenting glomeruli. Finally, we show how the pathological features extracted by APKD can identify focal abnormalities of the glomerular capillary wall to aid in the early diagnosis of pediatric kidney disease. AVAILABILITY AND IMPLEMENTATION: https://github.com/ChunyueFeng/Kidney-DataSet.