Diagnosis of T-cell-mediated kidney rejection in formalin-fixed, paraffin-embedded tissues using RNA-Seq-based machine learning algorithms

Fluorescence spectroscopic profiling of urine samples for predicting kidney transplant rejection

Rejection is the primary factor affecting the functionality of a kidney post-transplant, where its prompt prediction of risk significantly influences therapeutic strategies and clinical outcomes. Current graft health assessment methods, including serum creatinine measurements and transplant kidney puncture biopsies, possess considerable limitations. In contrast, urine serves as a direct indicator of the graft's degenerative stage and provides a more accurate measure than peripheral blood analysis, given its non-invasive collection of kidney-specific metabolite. This research entailed collecting fluorescent fingerprint data from 120 urine samples of post-renal transplant patients using hyperspectral imaging, followed by the development of a learning model to detect various forms of immunological rejection. The model successfully identified multiple rejection types with an average diagnostic accuracy of 95.56 %.Beyond proposing an innovative approach for predicting the risk of complications post-kidney transplantation, this study heralds the potential introduction of a non-invasive, rapid, and accurate supplementary method for risk assessment in clinical practice.

Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis

A number of processes and pathways have been reported in the development of Group I pulmonary hypertension (Group I PAH); however, novel biomarkers need to be identified for a better diagnosis and management. We employed a robust rank aggregation (RRA) algorithm to shortlist the key differentially expressed genes (DEGs) between Group I PAH patients and controls. An optimal diagnostic model was obtained by comparing seven machine learning algorithms and was verified in an independent dataset. The functional roles of key DEGs and biomarkers were analyzed using various in silico methods. Finally, the biomarkers and a set of key candidates were experimentally validated using patient samples and a cell line model. A total of 48 key DEGs with preferable diagnostic value were identified. A gradient boosting decision tree algorithm was utilized to build a diagnostic model with three biomarkers, PBRM1, CA1, and TXLNG. An immune-cell infiltration analysis revealed significant differences in the relative abundances of seven immune cells between controls and PAH patients and a correlation with the biomarkers. Experimental validation confirmed the upregulation of the three biomarkers in Group I PAH patients. In conclusion, machine learning and a bioinformatics analysis along with experimental techniques identified PBRM1, CA1, and TXLNG as potential biomarkers for Group I PAH.

Diagnosis of T-cell-mediated kidney rejection by biopsy-based proteomic biomarkers and machine learning

Background

Biopsy-based diagnosis is essential for maintaining kidney allograft longevity by ensuring prompt treatment for graft complications. Although histologic assessment remains the gold standard, it carries significant limitations such as subjective interpretation, suboptimal reproducibility, and imprecise quantitation of disease burden. It is hoped that molecular diagnostics could enhance the efficiency, accuracy, and reproducibility of traditional histologic methods.

Methods

Quantitative label-free mass spectrometry analysis was performed on a set of formalin-fixed, paraffin-embedded (FFPE) biopsies from kidney transplant patients, including five samples each with diagnosis of T-cell-mediated rejection (TCMR), polyomavirus BK nephropathy (BKPyVN), and stable (STA) kidney function control tissue. Using the differential protein expression result as a classifier, three different machine learning algorithms were tested to build a molecular diagnostic model for TCMR.

Results

The label-free proteomics method yielded 800-1350 proteins that could be quantified with high confidence per sample by single-shot measurements. Among these candidate proteins, 329 and 467 proteins were defined as differentially expressed proteins (DEPs) for TCMR in comparison with STA and BKPyVN, respectively. Comparing the FFPE quantitative proteomics data set obtained in this study using label-free method with a data set we previously reported using isobaric labeling technology, a classifier pool comprised of features from DEPs commonly quantified in both data sets, was generated for TCMR prediction. Leave-one-out cross-validation result demonstrated that the random forest (RF)-based model achieved the best predictive power. In a follow-up blind test using an independent sample set, the RF-based model yields 80% accuracy for TCMR and 100% for STA. When applying the established RF-based model to two public transcriptome datasets, 78.1%-82.9% sensitivity and 58.7%-64.4% specificity was achieved respectively.

Conclusions

This proof-of-principle study demonstrates the clinical feasibility of proteomics profiling for FFPE biopsies using an accurate, efficient, and cost-effective platform integrated of quantitative label-free mass spectrometry analysis with a machine learning-based diagnostic model. It costs less than 10 dollars per test.

Machine Learning Applications in Solid Organ Transplantation and Related Complications

The complexity of transplant medicine pushes the boundaries of innate, human reasoning. From networks of immune modulators to dynamic pharmacokinetics to variable postoperative graft survival to equitable allocation of scarce organs, machine learning promises to inform clinical decision making by deciphering prodigious amounts of available data. This paper reviews current research describing how algorithms have the potential to augment clinical practice in solid organ transplantation. We provide a general introduction to different machine learning techniques, describing their strengths, limitations, and barriers to clinical implementation. We summarize emerging evidence that recent advances that allow machine learning algorithms to predict acute post-surgical and long-term outcomes, classify biopsy and radiographic data, augment pharmacologic decision making, and accurately represent the complexity of host immune response. Yet, many of these applications exist in pre-clinical form only, supported primarily by evidence of single-center, retrospective studies. Prospective investigation of these technologies has the potential to unlock the potential of machine learning to augment solid organ transplantation clinical care and health care delivery systems.

The Future Role of Machine Learning in Clinical Transplantation

The use of artificial intelligence and machine learning (ML) has revolutionized our daily lives and will soon be instrumental in healthcare delivery. The rise of ML is due to multiple factors: increasing access to massive datasets, exponential increases in processing power, and key algorithmic developments that allow ML models to tackle increasingly challenging questions. Progressively more transplantation research is exploring the potential utility of ML models throughout the patient journey, although this has not yet widely transitioned into the clinical domain. In this review, we explore common approaches used in ML in solid organ clinical transplantation and consider opportunities for ML to help clinicians and patients. We discuss ways in which ML can aid leverage of large complex datasets, generate cutting-edge prediction models, perform clinical image analysis, discover novel markers in molecular data, and fuse datasets to generate novel insights in modern transplantation practice. We focus on key areas in transplantation in which ML is driving progress, explore the future potential roles of ML, and discuss the challenges and limitations of these powerful tools.

Artificial intelligence and kidney transplantation

Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.

Molecular Analysis of Renal Allograft Biopsies: Where Do We Stand and Where Are We Going?

A renal core biopsy for histological evaluation is the gold standard for diagnosing renal transplant pathology. However, renal biopsy interpretation is subjective and can render insufficient precision, making it difficult to apply a targeted therapeutic regimen for the individual patient. This warrants a need for additional methods assessing disease state in the renal transplant. Significant research activity has been focused on the role of molecular analysis in the diagnosis of renal allograft rejection. The identification of specific molecular expression patterns in allograft biopsies related to different types of allograft injury could provide valuable information about the processes underlying renal transplant dysfunction and can be used for the development of molecular classifier scores, which could improve our diagnostic and prognostic ability and could guide treatment. Molecular profiling has the potential to be more precise and objective than histological evaluation and may identify injury even before it becomes visible on histology, making it possible to start treatment at the earliest time possible. Combining conventional diagnostics (histology, serology, and clinical data) and molecular evaluation will most likely offer the best diagnostic approach. We believe that the use of state-of-the-art molecular analysis will have a significant impact in diagnostics after renal transplantation. In this review, we elaborate on the molecular phenotype of both acute and chronic T cell-mediated rejection and antibody-mediated rejection and discuss the additive value of molecular profiling in the setting of diagnosing renal allograft rejection and how this will improve transplant patient care.

MicroRNA and mRNA analysis of angiotensin II-induced renal artery endothelial cell dysfunction

Continuous activation of angiotensin II (Ang II) induces renal vascular endothelial dysfunction, inflammation and oxidative stress, all of which may contribute to renal damage. MicroRNAs (miRs/miRNAs) play a crucial regulatory role in the pathogenesis of hypertensive nephropathy (HN). The present study aimed to assess the differential expression profiles of potential candidate genes involved in Ang II-induced rat renal artery endothelial cell (RRAEC) dysfunction and explore their possible functions. In the present study, the changes in energy metabolism and autophagy function in RRAECs were evaluated using the Seahorse XF Glycolysis Stress Test and dansylcadaverine/transmission electron microscopy following exposure to Ang II. Subsequently, mRNA-miRNA sequencing experiments were performed to determine the differential expression profiles of mRNAs and miRNAs. Integrated bioinformatics analysis was applied to further explore the molecular mechanisms of Ang II on endothelial injury induced by Ang II. The present data supported the notion that Ang II upregulated glycolysis levels and promoted autophagy activation in RRAECs. The sequencing data demonstrated that 443 mRNAs and 58 miRNAs were differentially expressed (DE) in response to Ang II exposure, where 66 mRNAs and 55 miRNAs were upregulated, while 377 mRNAs and 3 miRNAs were downregulated (fold change >1.5 or <0.67; P<0.05). Functional analysis indicated that DE mRNA and DE miRNA target genes were mainly associated with cell metabolism (metabolic pathways), differentiation (Th1 and Th2 cell differentiation), autophagy (autophagy-animal and autophagy-other) and repair (RNA-repair). To the best of the authors' knowledge, this is the first report on mRNA-miRNA integrated profiles of Ang II-induced RRAECs. The present results provided evidence suggesting that the miRNA-mediated effect on the ‘mTOR signaling pathway’ might play a role in Ang II-induced RRAEC injury by driving glycolysis and autophagy activation. Targeting miRNAs and their associated pathways may provide valuable insight into the clinical management of HN and may improve patient outcome.

Quantitative Proteomics for Monitoring Renal Transplant Injury

PURPOSE

This study is aimed at developing a molecular diagnostics platform to enhance the interpretation of renal allograft biopsies using quantitative proteomic profiling of formalin-fixed and paraffin-embedded (FFPE) specimens.

EXPERIMENTAL DESIGN

A quantitative proteomics platform composed of 1) an optimized FFPE protein sample preparation method, 2) a tandem mass tag TMT10-plex-based proteomic workflow, and 3) a systematic statistical analysis pipeline to reveal differentially expressed proteins has been developed. This platform is then tested on a small sample set (five samples per phenotype) to reveal proteomic signatures that can differentiate T-cell mediated rejection (TCMR) and polyomavirus BK nephropathy (BKPyVN) from healthy functionally stable kidney tissue (STA).

RESULTS

Among 2798 quantified proteins, the expression levels of 740 BKPyVN and 638 TCMR associated proteins are significantly changed compared to STA specimens. Principal component analysis demonstrated good segregation of all three phenotypes investigated. Protein detection and quantitation are highly reproducible: replicate comparative analyses demonstrated 71-84% overlap of detected proteins, and the coefficient of variation for protein measurements is <15% in triplicate liquid chromatography-tandem mass spectrometry runs.

CONCLUSIONS AND CLINICAL RELEVANCE

Quantitative proteomics can be applied to archived FFPE specimens to differentiate different causes of renal allograft injury.

Cellular and viral miRNA expression in polyomavirus BK infection

Polyomavirus BK (BKV) is an important pathogen in kidney transplant patients. Regulation of BKV encoded microRNAs (miRNAs) is not well understood. Therefore, tubular epithelial cells infected with BKV were examined for changes in small RNA expression. The observed changes were further evaluated by real-time PCR and RNA-seq analysis of renal allograft biopsies. BKV-miR-B1-5p and BKV-miR-B1-3p showed a 1000-fold increase over 12 days but did not prevent cell lysis. Downregulation of host miR-10b and miR-30a could be confirmed on all three platforms evaluated. Whereas, the BKV genome expressed more 3p than 5p miRNA species, the reverse was true for the human genome. Decreased expression of TP53INP2, and increased expression of BCL2A1, IL-6, IL8 and other proinflammatory cytokines were shown in biopsies with BKV nephropathy. No change in expression was seen in miR-10a dependent expression of NKG2D ligands ULBP3, MICA, or MICB. In conclusion, BKV infection results in regulation of cellular genes regulated by and possibly amenable to therapies targeting miR-10 and miR-30.

Defining housekeeping genes suitable for RNA-seq analysis of the human allograft kidney biopsy tissue

BACKGROUND

RNA-seq is poised to play a major role in the management of kidney transplant patients. Rigorous definition of housekeeping genes (HKG) is essential for further progress in this field. Using single genes or a limited set HKG is inherently problematic since their expression might be altered by specific diseases in the patients being studied.

METHODS

To generate a HKG set specific for kidney transplantation, we performed RNA-sequencing from renal allograft biopsies collected in a variety of clinical settings. Various normalization methods were applied to identify transcripts that had a coefficient of variation of expression that was below the 2nd percentile across all samples, and the corresponding genes were designated as housekeeping genes. Comparison with transcriptomic data from the Gene Expression Omnibus (GEO) database, pathway analysis and molecular biological functions were utilized to validate the housekeeping genes set.

RESULTS

We have developed a bioinformatics solution to this problem by using nine different normalization methods to derive large HKG gene sets from a RNA-seq data set of 47,611 transcripts derived from 30 biopsies. These biopsies were collected in a variety of clinical settings, including normal function, acute rejection, interstitial nephritis, interstitial fibrosis/tubular atrophy and polyomavirus nephropathy. Transcripts with coefficient of variation below the 2nd percentile were designated as HKG, and validated by showing their virtual absence in diseased allograft derived transcriptomic data sets available in the GEO. Pathway analysis indicated a role for these genes in maintenance of cell morphology, pyrimidine metabolism, and intracellular protein signaling.

CONCLUSIONS

Utilization of these objectively defined HKG data sets will guard against errors resulting from focusing on individual genes like 18S RNA, actin & tubulin, which do not maintain constant expression across the known spectrum of renal allograft pathology.