How will artificial intelligence and bioinformatics change our understanding of IgA Nephropathy in the next decade?

Unveiling biomarkers and therapeutic targets in IgA nephropathy through large-scale blood transcriptome analysis

INTRODUCTION

IgA nephropathy (IgAN) is the most prevalent form of glomerulonephritis. Unfortunately, molecular biomarkers for IgAN derived from omics studies are still lacking. This research aims to identify critical genes associated with IgAN through large-scale blood transcriptome analysis.

METHODS

We constructed novel blood transcriptome profiles from peripheral blood mononuclear cells (PBMCs) of 53 Chinese IgAN patients and 28 healthy individuals. Our analysis included GO, KEGG, and GSEA for biological pathways. We analyzed immune cell profiles with CIBERSORT and constructed PPI networks with STRING, visualized in Cytoscape. Key differentially expressed genes (DEGs) were identified using CytoHubba and MCODE. We assessed the correlation between gene expressions and clinical data to evaluate clinical significance and identified hub genes through machine learning, validated with an open-access dataset. Potential drugs were explored using the CMap database.

RESULTS

We identified 333 DEGs between IgAN patients and healthy controls, mainly related to immune response and inflammation. Key pathways included NK cell mediated cytotoxicity, complement and coagulation cascades, antigen processing, and B cell receptor signaling. Cytoscape revealed 16 clinically significant genes (including KIR2DL1, KIR2DL3, VISIG4, C1QB, and C1QC, associated with sub-phenotype and prognosis). Machine learning identified two hub genes (KLRC1 and C1QB) for a diagnostic model of IgAN with 0.92 accuracy, validated at 1.00 against the GSE125818 dataset. Sirolimus, calcifediol, and efaproxiral were suggested as potential therapeutic agents.

CONCLUSION

Key DEGs, particularly VISIG4, KLRC1, and C1QB, emerge as potential specific markers for IgAN, paving the way for future targeted personalized treatment options.

Operational greenhouse-gas emissions of deep learning in digital pathology: a modelling study

BACKGROUND

Deep learning is a promising way to improve health care. Image-processing medical disciplines, such as pathology, are expected to be transformed by deep learning. The first clinically applicable deep-learning diagnostic support tools are already available in cancer pathology, and their number is increasing. However, data on the environmental sustainability of these tools are scarce. We aimed to conduct an environmental-sustainability analysis of a theoretical implementation of deep learning in patient-care pathology.

METHODS

For this modelling study, we first assembled and calculated relevant data and parameters of a digital-pathology workflow. Data were breast and prostate specimens from the university clinic at the Institute of Pathology of the Rheinisch-Westfälische Technische Hochschule Aachen (Aachen, Germany), for which commercially available deep learning was already available. Only specimens collected between Jan 1 and Dec 31, 2019 were used, to omit potential biases due to the COVID-19 pandemic. Our final selection was based on 2 representative weeks outside holidays, covering different types of specimens. To calculate carbon dioxide (CO2) or CO2 equivalent (CO2 eq) emissions of deep learning in pathology, we gathered relevant data for exact numbers and sizes of whole-slide images (WSIs), which were generated by scanning histopathology samples of prostate and breast specimens. We also evaluated different data input scenarios (including all slide tiles, only tiles containing tissue, or only tiles containing regions of interest). To convert estimated energy consumption from kWh to CO2 eq, we used the internet protocol address of the computational server and the Electricity Maps database to obtain information on the sources of the local electricity grid (ie, renewable vs non-renewable), and estimated the number of trees and proportion of the local and world's forests needed to sequester the CO2 eq emissions. We calculated the computational requirements and CO2 eq emissions of 30 deep-learning models that varied in task and size. The first scenario represented the use of one commercially available deep-learning model for one task in one case (1-task), the second scenario considered two deep-learning models for two tasks per case (2-task), the third scenario represented a future, potentially automated workflow that could handle 7 tasks per case (7-task), and the fourth scenario represented the use of a single potential, large, computer-vision model that could conduct multiple tasks (multitask). We also compared the performance (ie, accuracy) and CO2 eq emissions of different deep-learning models for the classification of renal cell carcinoma on WSIs, also from Rheinisch-Westfälische Technische Hochschule Aachen. We also tested other approaches to reducing CO2 eq emissions, including model pruning and an alternative method for histopathology analysis (pathomics).

FINDINGS

The pathology database contained 35 552 specimens (237 179 slides), 6420 of which were prostate specimens (10 115 slides) and 11 801 of which were breast specimens (19 763 slides). We selected and subsequently digitised 140 slides from eight breast-cancer cases and 223 slides from five prostate-cancer cases. Applying large deep-learning models on all WSI tiles of prostate and breast pathology cases would result in yearly CO2 eq emissions of 7·65 metric tons (t; 95% CI 7·62-7·68) with the use of a single deep-learning model per case; yearly CO2 eq emissions were up to 100·56 t (100·21-100·99) with the use of seven deep-learning models per case. CO2 eq emissions for different deep-learning model scenarios, data inputs, and deep-learning model sizes for all slides varied from 3·61 t (3·59-3·63) to 2795·30 t (1177·51-6482·13. For the estimated number of overall pathology cases worldwide, the yearly CO2 eq emissions varied, reaching up to 16 megatons (Mt) of CO2 eq, requiring up to 86 590 km2 (0·22%) of world forest to sequester the CO2 eq emissions. Use of the 7-task scenario and small deep-learning models on slides containing tissue only could substantially reduce CO2 eq emissions worldwide by up to 141 times (0·1 Mt, 95% CI 0·1-0·1). Considering the local environment in Aachen, Germany, the maximum CO2 eq emission from the use of deep learning in digital pathology only would require 32·8% (95% CI 13·8-76·6) of the local forest to sequester the CO2 eq emissions. A single pathomics run on a tissue could provide information that was comparable to or even better than the output of multitask deep-learning models, but with 147 times reduced CO2 eq emissions.

INTERPRETATION

Our findings suggest that widespread use of deep learning in pathology might have considerable global-warming potential. The medical community, policy decision makers, and the public should be aware of this potential and encourage the use of CO2 eq emissions reduction strategies where possible.

FUNDING

German Research Foundation, European Research Council, German Federal Ministry of Education and Research, Health, Economic Affairs and Climate Action, and the Innovation Fund of the Federal Joint Committee.

Long-term follow-up of IgA nephropathy: clinicopathological features and predictors of outcomes

Background

The establishment of the Oxford classification and newly developed prediction models have improved the prognostic information for immunoglobulin A nephropathy (IgAN). Considering new treatment options, optimizing prognostic information and improving existing prediction models are favorable.

Methods

We used random forest survival analysis to select possible predictors of end-stage kidney disease among 37 candidate variables in a cohort of 232 patients with biopsy-proven IgAN retrieved from the Norwegian Kidney Biopsy Registry. The predictive value of variables with relative importance >5% was assessed using concordance statistics and the Akaike information criterion. Pearson's correlation coefficient was used to identify correlations between the selected variables.

Results

The median follow-up period was 13.7 years. An isolated analysis of histological variables identified six variables with relative importance >5%: T %, segmental glomerular sclerosis without characteristics associated with other subtypes (not otherwise specified, NOS), normal glomeruli, global sclerotic glomeruli, segmental adherence and perihilar glomerular sclerosis. When histopathological and clinical variables were combined, estimated glomerular filtration rate (eGFR), proteinuria and serum albumin were added to the list. T % showed a better prognostic value than tubular atrophy/interstitial fibrosis (T) lesions with C-indices at 0.74 and 0.67 and was highly correlated with eGFR. Analysis of the subtypes of segmental glomerulosclerosis (S) lesions revealed that NOS and perihilar glomerular sclerosis were associated with adverse outcomes.

Conclusions

Reporting T lesions as a continuous variable, normal glomeruli and subtypes of S lesions could provide clinicians with additional prognostic information and contribute to the improved performance of the Oxford classification and prognostic tools.

Evaluating Progression Risk in Patients With Immunoglobulin A Nephropathy

The highly variable rate of decline in kidney function in patients with immunoglobulin A nephropathy (IgAN) provides a major clinical challenge. Predicting which patients will progress to kidney failure, and how quickly, is difficult. Multiple novel therapies are likely to be approved in the short-term, but clinicians lack the tools to identify patients most likely to benefit from specific treatments at the right time. Noninvasive and validated markers for selecting at-risk patients and longitudinal monitoring are urgently needed. This review summarizes what is known about demographic, clinical, and histopathologic prognostic markers in the clinician's toolkit, including the International IgAN Prediction Tool. We also briefly review what is known on these topics in children and adolescents with IgAN. Although helpful, currently used markers leave clinicians heavily reliant on histologic features from the diagnostic kidney biopsy and standard clinical data to guide treatment choice, and very few noninvasive markers reflect treatment efficacy over time. Novel prognostic and predictive markers are under clinical investigation, with considerable progress being made in markers of complement activation. Other areas of research are the interplay between gut microbiota and galactose-deficient IgA1 expression; microRNAs; imaging; artificial intelligence; and markers of fibrosis. Given the rate of therapeutic advancement, the remaining gaps in biomarker research need to be addressed. We finish by describing our route to clinical utility of predictive and prognostic markers in IgAN. This route will provide us with the chance to improve IgAN prognosis by using robust, clinically practical markers to inform patient care.

APOC1 exacerbates renal fibrosis through the activation of the NF-κB signaling pathway in IgAN

Introduction: IgA nephropathy (IgAN) is the most common disease leading to end-stage renal disease, and tubular fibrosis represents an important risk factor for disease progression. However, research on early molecular diagnostic indicators of tubular fibrosis and the mechanisms underlying disease progression is still lacking. Methods: The GSE93798 dataset was downloaded from the GEO database. DEGs were screened and analyzed for GO and KEGG enrichment in IgAN. The least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE) algorithms were applied to screen for hub secretory genes. The expression and diagnostic efficacy of hub genes were confirmed by the GSE35487 dataset. ELISA was applied to detect the expression of APOC1 in serum. The expression and localization of hub genes in IgAN were verified by the expression of IHC and IF in human kidney tissues, and the correlation of expression with clinical data was verified in the Nephroseq database. Finally, cellular experiments clarified the role of hub genes in the signaling pathway. Results: A total of 339 DEGs were identified in IgAN, of which 237 were upregulated and 102 downregulated. The KEGG signaling pathway is enriched in the ECM-receptor interaction and AGE-RAGE signaling pathway. APOC1, ALB, CCL8, CXCL2, SRPX2, and TGFBI identified six hub secretory genes using the LASSO and SVM-RFE algorithms. In vivo and in vitro experiments demonstrated that APOC1 expression was elevated in IgAN. The serum concentration of APOC1 was 1.232 ± 0.1812 μg/ml in IgAN patients, whereas it was 0.3956 ± 0.1233 μg/ml in healthy individuals. APOC1 exhibited high diagnostic efficacy for IgAN (AUC of 99.091%, specificity of 95.455%, and sensitivity of 99.141%) in the GSE93798 dataset. APOC1 expression negatively correlated with eGFR (R ² = 0.2285, p = 0.0385) and positively correlated with serum creatinine (R ² = 0.41, p = 0.000567) in IgAN. APOC1 exacerbated renal fibrosis, possibly in part by activating the NF-κB pathway in IgAN. Conclusion: APOC1 was identified as the core secretory gene of IgAN, which was closely associated with blood creatinine and eGFR and had significant efficacy in the diagnosis of IgAN. Mechanistic studies revealed that the knockdown of APOC1 could improve IgAN renal fibrosis by inhibiting the NF pathway, which may be a potential therapeutic target for improving renal fibrosis in IgAN.

Next-Generation Morphometry for pathomics-data mining in histopathology

Pathology diagnostics relies on the assessment of morphology by trained experts, which remains subjective and qualitative. Here we developed a framework for large-scale histomorphometry (FLASH) performing deep learning-based semantic segmentation and subsequent large-scale extraction of interpretable, quantitative, morphometric features in non-tumour kidney histology. We use two internal and three external, multi-centre cohorts to analyse over 1000 kidney biopsies and nephrectomies. By associating morphometric features with clinical parameters, we confirm previous concepts and reveal unexpected relations. We show that the extracted features are independent predictors of long-term clinical outcomes in IgA-nephropathy. We introduce single-structure morphometric analysis by applying techniques from single-cell transcriptomics, identifying distinct glomerular populations and morphometric phenotypes along a trajectory of disease progression. Our study provides a concept for Next-generation Morphometry (NGM), enabling comprehensive quantitative pathology data mining, i.e., pathomics.

Common molecular mechanism and immune infiltration patterns of thoracic and abdominal aortic aneurysms

BACKGROUND

Aortic disease (aortic aneurysm (AA), dissection (AD)) is a serious threat to patient lives. Little is currently known about the molecular mechanisms and immune infiltration patterns underlying the development and progression of thoracic and abdominal aortic aneurysms (TAA and AAA), warranting further research.

METHODS

We downloaded AA (includes TAA and AAA) datasets from the GEO database. The potential biomarkers in TAA and AAA were identified using differential expression analysis and two machine-learning algorithms. The discrimination power of the potential biomarkers and their diagnostic accuracy was assessed in validation datasets using ROC curve analysis. Then, GSEA, KEGG, GO and DO analyses were conducted. Furthermore, two immuno-infiltration analysis algorithms were utilized to analyze the common immune infiltration patterns in TAA and AAA. Finally, a retrospective clinical study was performed on 78 patients with AD, and the serum from 6 patients was used for whole exome sequencing (WES).

RESULTS

The intersection of TAA and AAA datasets yielded 82 differentially expressed genes (DEGs). Subsequently, the biomarkers (CX3CR1 and HBB) were acquired by screening using two machine-learning algorithms and ROC curve analysis. The functional analysis of DEGs showed significant enrichment in inflammation and regulation of angiogenic pathways. Immune cell infiltration analysis revealed that adaptive and innate immune responses were closely linked to AA progression. However, neither CX3CR1 nor HBB was associated with B cell-mediated humoral immunity. CX3CR1 expression was correlated with macrophages and HBB with eosinophils. Finally, our retrospective clinical study revealed a hyperinflammatory environment in aortic disease. The WES study identified disease biomarkers and gene variants, some of which may be druggable.

CONCLUSION

The genes CX3CR1 and HBB can be used as common biomarkers in TAA and AAA. Large numbers of innate and adaptive immune cells are infiltrated in AA and are closely linked to the development and progression of AA. Moreover, CX3CR1 and HBB are highly correlated with the infiltration of immune cells and may be potential targets of immunotherapeutic drugs. Gene mutation research is a promising direction for the treatment of aortic disease.

Advances in proteomic profiling of pediatric kidney diseases

Chronic kidney disease (CKD) can progress to kidney failure and require dialysis or transplantation, while early diagnosis can alter the course of disease and lead to better outcomes in both pediatric and adult patients. Significant CKD comorbidities include the manifestation of cardiovascular disease, heart failure, coronary disease, and hypertension. The pathogenesis of chronic kidney diseases can present as subtle and especially difficult to distinguish between different glomerular pathologies. Early detection of adult and pediatric CKD and detailed mechanistic understanding of the kidney damage can be helpful in delaying or curtailing disease progression via precise intervention toward diagnosis and prognosis. Clinically, serum creatinine and albumin levels can be indicative of CKD, but often are a lagging indicator only significantly affected once kidney function has severely diminished. The evolution of proteomics and mass spectrometry technologies has begun to provide a powerful research tool in defining these mechanisms and identifying novel biomarkers of CKD. Many of the same challenges and advances in proteomics apply to adult and pediatric patient populations. Additionally, proteomic analysis of adult CKD patients can be transferred directly toward advancing our knowledge of pediatric CKD as well. In this review, we highlight applications of proteomics that have yielded such biomarkers as PLA2R, SEMA3B, and other markers of membranous nephropathy as well as KIM-1, MCP-1, and NGAL in lupus nephritis among other potential diagnostic and prognostic markers. The potential for improving the clinical toolkit toward better treatment of pediatric kidney diseases is significantly aided by current and future development of proteomic applications.

Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects

Digital imaging and advanced microscopy play a pivotal role in the diagnosis of kidney diseases. In recent years, great achievements have been made in digital imaging, providing novel approaches for precise quantitative assessments of nephropathology and relieving burdens of renal pathologists. Developing novel methods of artificial intelligence (AI)-assisted technology through multidisciplinary interaction among computer engineers, renal specialists, and nephropathologists could prove beneficial for renal pathology diagnoses. An increasing number of publications has demonstrated the rapid growth of AI-based technology in nephrology. In this review, we offer an overview of AI-assisted renal pathology, including AI concepts and the workflow of processing digital image data, focusing on the impressive advances of AI application in disease-specific backgrounds. In particular, this review describes the applied computer vision algorithms for the segmentation of kidney structures, diagnosis of specific pathological changes, and prognosis prediction based on images. Lastly, we discuss challenges and prospects to provide an objective view of this topic.

Validation of two IgA nephropathy risk-prediction tools using a cohort with a long follow-up

BACKGROUND

Recently, two immunoglobulin A nephropathy prediction tools were developed that combine clinical and histopathological parameters. The International IgAN Prediction Tool predicts the risk for 50% declines in the estimated glomerular filtration rate or end-stage renal disease up to 80 months after diagnosis. The IgA Nephropathy Clinical Decision Support System uses artificial neural networks to estimate the risk for end-stage renal disease. We aimed to externally validate both prediction tools using a Norwegian cohort with a long-term follow-up.

METHODS

We included 306 patients with biopsy-proven primary immunoglobulin A nephropathy in this study. Histopathologic samples were retrieved from the Norwegian Kidney Biopsy Registry and reclassified according to the Oxford classification. We used discrimination and calibration as principles for externally validating the prognostic models.

RESULTS

The median patient follow-up was 17.1 years. A cumulative dynamic time-dependent receiver operating characteristic analysis showed area under the curve values of ranging from 0.90 at 5 years to 0.83 at 20 years for the International IgAN Prediction Tool, while time-naive analysis showed an area under the curve value at 0.83 for the IgA Nephropathy Clinical Decision Support System. The International IgAN Prediction Tool was well calibrated, while the IgA Nephropathy Clinical Decision Support System tends to underestimate risk for patients with higher risk, and overestimates risk in the lower risk categories.

CONCLUSIONS

We have externally validated two prediction tools for IgA nephropathy. The International IgAN Prediction Tool performed well, while the IgA Nephropathy Clinical Decision Support System has some limitations.

The potential of artificial intelligence-based applications in kidney pathology

PURPOSE OF REVIEW

The field of pathology is currently undergoing a significant transformation from traditional glass slides to a digital format dependent on whole slide imaging. Transitioning from glass to digital has opened the field to development and application of image analysis technology, commonly deep learning methods (artificial intelligence [AI]) to assist pathologists with tissue examination. Nephropathology is poised to leverage this technology to improve precision, accuracy, and efficiency in clinical practice.

RECENT FINDINGS

Through a multidisciplinary approach, nephropathologists, and computer scientists have made significant recent advances in developing AI technology to identify histological structures within whole slide images (segmentation), quantification of histologic structures, prediction of clinical outcomes, and classifying disease. Virtual staining of tissue and automation of electron microscopy imaging are emerging applications with particular significance for nephropathology.

SUMMARY

AI applied to image analysis in nephropathology has potential to transform the field by improving diagnostic accuracy and reproducibility, efficiency, and prognostic power. Reimbursement, demonstration of clinical utility, and seamless workflow integration are essential to widespread adoption.

Microbiome in Chronic Kidney Disease (CKD): An Omics Perspective

Chronic kidney disease (CKD) is predominant in 10% of the world’s adult population, and is increasingly considered a silent epidemic. Gut microbiota plays an essential role in maintaining host energy homeostasis and gut epithelial integrity. Alterations in gut microbiota composition, functions and, specifically, production of metabolites causing uremic toxicity are often associated with CKD onset and progression. Here, we present the latest omics (transcriptomics, proteomics and metabolomics) studies that explore the connection between CKD and gut microbiome. A review of the available literature using PubMed was performed using the keywords “microb*”, “kidney”, “proteom”, “metabolom” and “transcript” for the last 10 years, yielding a total of 155 publications. Following selection of the relevant studies (focusing on microbiome in CKD), a predominance of metabolomics (n = 12) over transcriptomics (n = 1) and proteomics (n = 6) analyses was observed. A consensus arises supporting the idea that the uremic toxins produced in the gut cause oxidative stress, inflammation and fibrosis in the kidney leading to CKD. Collectively, findings include an observed enrichment of Eggerthella lenta, Enterobacteriaceae and Clostridium spp., and a depletion in Bacteroides eggerthii, Roseburia faecis and Prevotella spp. occurring in CKD models. Bacterial species involved in butyrate production, indole synthesis and mucin degradation were also related to CKD. Consequently, strong links between CKD and gut microbial dysbiosis suggest potential therapeutic strategies to prevent CKD progression and portray the gut as a promising therapeutic target.

Precision medicine for the treatment of glomerulonephritis: A bold goal but not yet a transformative achievement

The revolution in our ability to recognize the alterations in fundamental biology brought about by disease has fostered a renewed interest in precision or personalized medicine (“the right treatment, or diagnostic test, for the right patient at the right time”). This nascent field has been led by oncology, immune-hematology and infectious disease, but nephrology is catching up, and quickly. Specific forms of glomerulonephritis thought to represent specific “diseases” have been “downgraded” to “patterns of injury”. New entities have emerged through application of sophisticated molecular technologies; often embraced by the term “multi-omics”. Kidney biopsies are now interpreted by next generation imaging and machine learning. Many opportunities are manifest that will translate these remarkable developments into novel safe and effective treatment regimens for specific pathogenic pathways evoking glomerulonephritis and its progression to kidney failure. A few successes emboldens a positive look to the future. A sustained and highly collaborative engagement with this new paradigm will be required for this field, full of hope and high expectations, to realize its goal of transforming glomerular therapeutics from “one size fits all (or many)” to a true individualized management principle.