Netboost: Boosting-Supported Network Analysis Improves High-Dimensional Omics Prediction in Acute Myeloid Leukemia and Huntington's Disease

Infusing structural assumptions into dimensionality reduction for single-cell RNA sequencing data to identify small gene sets

Dimensionality reduction greatly facilitates the exploration of cellular heterogeneity in single-cell RNA sequencing data. While most of such approaches are data-driven, it can be useful to incorporate biologically plausible assumptions about the underlying structure or the experimental design. We propose the boosting autoencoder (BAE) approach, which combines the advantages of unsupervised deep learning for dimensionality reduction and boosting for formalizing assumptions. Specifically, our approach selects small sets of genes that explain latent dimensions. As illustrative applications, we explore the diversity of neural cell identities and temporal patterns of embryonic development.

Plasma proteomic signatures of social isolation and loneliness associated with morbidity and mortality

The biology underlying the connection between social relationships and health is largely unknown. Here, leveraging data from 42,062 participants across 2,920 plasma proteins in the UK Biobank, we characterized the proteomic signatures of social isolation and loneliness through proteome-wide association study and protein co-expression network analysis. Proteins linked to these constructs were implicated in inflammation, antiviral responses and complement systems. More than half of these proteins were prospectively linked to cardiovascular disease, type 2 diabetes, stroke and mortality during a 14 year follow-up. Moreover, Mendelian randomization (MR) analysis suggested causal relationships from loneliness to five proteins, with two proteins (ADM and ASGR1) further supported by colocalization. These MR-identified proteins (GFRA1, ADM, FABP4, TNFRSF10A and ASGR1) exhibited broad associations with other blood biomarkers, as well as volumes in brain regions involved in interoception and emotional and social processes. Finally, the MR-identified proteins partly mediated the relationship between loneliness and cardiovascular diseases, stroke and mortality. The exploration of the peripheral physiology through which social relationships influence morbidity and mortality is timely and has potential implications for public health.

Plasma proteomic characterization of motoric cognitive risk and mild cognitive impairment

INTRODUCTION

Motoric cognitive risk (MCR) is a pre-dementia syndrome characterized by mobility and cognitive dysfunction. This study conducted a proteome-wide study of MCR and compared the proteomic signatures of MCR to that of mild cognitive impairment (MCI).

METHODS

Participants were classified as MCR using a memory questionnaire and 4-meter walk. We measured 4877 plasma proteins collected during late-life and midlife. Multivariable logistic regression related each protein to late-life MCR/MCI. MCR-associated proteins were replicated internally at midlife and in an external cohort.

RESULTS

Proteome-wide analysis (n = 4076) identified 25 MCR-associated proteins. Eight of these proteins remained associated with late-life MCR when measured during midlife. Two proteins (SVEP1 and TAGLN) were externally replicated. Compared to MCI, MCR had a distinct and much stronger proteomic signature enriched for cardiometabolic and immune pathways.

DISCUSSION

Our findings highlight the divergent biology underlying two pre-dementia syndromes. Metabolic and immune dysfunction may be a primary driver of MCR.

HIGHLIGHTS

MCR is defined by concurrent cognitive and gait dysfunction. MCR protein biomarkers have key roles in cardiometabolic and vascular function. MCR biomarkers are also associated with cerebrovascular disease and dementia. MCR and MCI demonstrate overlapping but divergent proteomic signatures.

Proteomics and Incident Kidney Failure in Individuals With CKD: The African American Study of Kidney Disease and Hypertension and the Boston Kidney Biopsy Cohort

Rationale & Objective

Individuals with chronic kidney disease (CKD) are at increased risk of morbidity and mortality, particularly as they progress to kidney failure. Identifying circulating proteins that underlie kidney failure development may guide the discovery of new targets for intervention.

Study Design

Prospective cohort.

Setting & Participants

703 African American Study of Kidney Disease and Hypertension (AASK) and 434 Boston Kidney Biopsy Cohort (BKBC) participants with baseline proteomics data.

Exposures

Circulating proteins measured using SomaScan.

Outcomes

Kidney failure, defined as dialysis initiation or kidney transplantation.

Analytical Approach

Using adjusted Cox models, we studied associations of 6,284 circulating proteins with kidney failure risk separately in AASK and BKBC and meta-analyzed results. We then performed gene set enrichment analyses to identify underlying perturbations in biological pathways. In separate data sets with kidney-tissue level gene expression, we ascertained dominant regions of expression and correlated kidney tubular gene expression with fibrosis and estimated glomerular filtration rate (eGFR).

Results

Over median follow-up periods of 8.8 and 3.1 years, 210 AASK (mean age: 55 years, 39% female, mean GFR: 46 mL/min/1.73 m2) and 115 BKBC (mean age: 54 years, 47% female, mean eGFR: 51 mL/min/1.73 m2) participants developed kidney failure, respectively. We identified 143 proteins that were associated with incident kidney failure, of which only 1 (Testican-2) had a lower risk. Notable proteins included those related to vascular permeability (endothelial cell-selective adhesion molecule), glomerulosclerosis (ephrin-A1), glomerular development (ephrin-B2), intracellular sorting/transport (vesicular integral-membrane protein VIP36), podocyte effacement (pigment epithelium-derived factor), complement activation (complement decay-accelerating factor), and fibrosis (ephrin-A1, ephrin-B2, and pigment epithelium-derived factor). Gene set enrichment analyses detected overrepresented pathways that could be related to CKD progression, such as ephrin signaling, cell-cell junctions, intracellular transport, immune response, cell proliferation, and apoptosis. At the kidney level, glomerular expression predominated for genes corresponding to circulating proteins of interest, and several gene expression levels were correlated with eGFR and/or fibrosis.

Limitations

Possible residual confounding.

Conclusions

Multimodal data identified proteins and pathways associated with the development of kidney failure.

Plasma proteome-wide analysis of cerebral small vessel disease identifies novel biomarkers and disease pathways

Cerebral small vessel disease (SVD), as defined by neuroimaging characteristics such as white matter hyperintensities (WMHs), cerebral microhemorrhages (CMHs), and lacunar infarcts, is highly prevalent and has been associated with dementia risk and other clinical sequelae. Although conditions such as hypertension are known to contribute to SVD, little is known about the diverse set of subclinical biological processes and molecular mediators that may also influence the development and progression of SVD. To better understand the mechanisms underlying SVD and to identify novel SVD biomarkers, we used a large-scale proteomic platform to relate 4,877 plasma proteins to MRI-defined SVD characteristics within 1,508 participants of the Atherosclerosis Risk in Communities (ARIC) Study cohort. Our proteome-wide analysis of older adults (mean age: 76) identified 13 WMH-associated plasma proteins involved in synaptic function, endothelial integrity, and angiogenesis, two of which remained associated with late-life WMH volume when measured nearly 20 years earlier, during midlife. We replicated the relationship between 9 candidate proteins and WMH volume in one or more external cohorts; we found that 11 of the 13 proteins were associated with risk for future dementia; and we leveraged publicly available proteomic data from brain tissue to demonstrate that a subset of WMH-associated proteins was differentially expressed in the context of cerebral atherosclerosis, pathologically-defined Alzheimer's disease, and cognitive decline. Bidirectional two-sample Mendelian randomization analyses examined the causal relationships between candidate proteins and WMH volume, while pathway and network analyses identified discrete biological processes (lipid/cholesterol metabolism, NF-kB signaling, hemostasis) associated with distinct forms of SVD. Finally, we synthesized these findings to identify two plasma proteins, oligodendrocyte myelin glycoprotein (OMG) and neuronal pentraxin receptor (NPTXR), as top candidate biomarkers for elevated WMH volume and its clinical manifestations.

Machine learning and integrative multi-omics network analysis for survival prediction in acute myeloid leukemia

BACKGROUND

Acute myeloid leukemia (AML) is the most common malignant myeloid disorder in adults and the fifth most common malignancy in children, necessitating advanced technologies for outcome prediction.

METHOD

This study aims to enhance prognostic capabilities in AML by integrating multi-omics data, especially gene expression and methylation, through network-based feature selection methodologies. By employing artificial intelligence and network analysis, we are exploring different methods to build a machine learning model for predicting AML patient survival. We evaluate the effectiveness of combining omics data, identify the most informative method for network integration and compare the performance with standard feature selection methods.

RESULTS

Our findings demonstrate that integrating gene expression and methylation data significantly improves prediction accuracy compared to single omics data. Among network integration methods, our study identifies the best approach that improves informative feature selection for predicting patient outcomes in AML. Comparative analyses demonstrate the superior performance of the proposed network-based methods over standard techniques.

CONCLUSIONS

This research presents an innovative and robust methodology for building a survival prediction model tailored to AML patients. By leveraging multilayer network analysis for feature selection, our approach contributes to improving the understanding and prognostic capabilities in AML and laying the foundation for more effective personalized therapeutic interventions in the future.

Association of Integrated Proteomic and Metabolomic Modules with Risk of Kidney Disease Progression

Key Points

Integrated analysis of proteome and metabolome identifies modules associated with CKD progression and kidney failure. Ephrin transmembrane proteins and podocyte-expressed CRIM1 and NPNT emerged as central components and warrant experimental and clinical investigation.

Background

Proteins and metabolites play crucial roles in various biological functions and are frequently interconnected through enzymatic or transport processes.

Methods

We present an integrated analysis of 4091 proteins and 630 metabolites in the Chronic Renal Insufficiency Cohort study (N =1708; average follow-up for kidney failure, 9.5 years, with 537 events). Proteins and metabolites were integrated using an unsupervised clustering method, and we assessed associations between clusters and CKD progression and kidney failure using Cox proportional hazards models. Analyses were adjusted for demographics and risk factors, including the eGFR and urine protein–creatinine ratio. Associations were identified in a discovery sample (random two thirds, n =1139) and then evaluated in a replication sample (one third, n =569).

Results

We identified 139 modules of correlated proteins and metabolites, which were represented by their principal components. Modules and principal component loadings were projected onto the replication sample, which demonstrated a consistent network structure. Two modules, representing a total of 236 proteins and 82 metabolites, were robustly associated with both CKD progression and kidney failure in both discovery and validation samples. Using gene set enrichment, several transmembrane-related terms were identified as overrepresented in these modules. Transmembrane–ephrin receptor activity displayed the largest odds (odds ratio=13.2, P value = 5.5×10−5). A module containing CRIM1 and NPNT expressed in podocytes demonstrated particularly strong associations with kidney failure (P value = 2.6×10−5).

Conclusions

This study demonstrates that integration of the proteome and metabolome can identify functions of pathophysiologic importance in kidney disease.

Proteomics analysis of plasma from middle-aged adults identifies protein markers of dementia risk in later life

A diverse set of biological processes have been implicated in the pathophysiology of Alzheimer's disease (AD) and related dementias. However, there is limited understanding of the peripheral biological mechanisms relevant in the earliest phases of the disease. Here, we used a large-scale proteomics platform to examine the association of 4877 plasma proteins with 25-year dementia risk in 10,981 middle-aged adults. We found 32 dementia-associated plasma proteins that were involved in proteostasis, immunity, synaptic function, and extracellular matrix organization. We then replicated the association between 15 of these proteins and clinically relevant neurocognitive outcomes in two independent cohorts. We demonstrated that 12 of these 32 dementia-associated proteins were associated with cerebrospinal fluid (CSF) biomarkers of AD, neurodegeneration, or neuroinflammation. We found that eight of these candidate protein markers were abnormally expressed in human postmortem brain tissue from patients with AD, although some of the proteins that were most strongly associated with dementia risk, such as GDF15, were not detected in these brain tissue samples. Using network analyses, we found a protein signature for dementia risk that was characterized by dysregulation of specific immune and proteostasis/autophagy pathways in adults in midlife ~20 years before dementia onset, as well as abnormal coagulation and complement signaling ~10 years before dementia onset. Bidirectional two-sample Mendelian randomization genetically validated nine of our candidate proteins as markers of AD in midlife and inferred causality of SERPINA3 in AD pathogenesis. Last, we prioritized a set of candidate markers for AD and dementia risk prediction in midlife.

Genetic studies of paired metabolomes reveal enzymatic and transport processes at the interface of plasma and urine

The kidneys operate at the interface of plasma and urine by clearing molecular waste products while retaining valuable solutes. Genetic studies of paired plasma and urine metabolomes may identify underlying processes. We conducted genome-wide studies of 1,916 plasma and urine metabolites and detected 1,299 significant associations. Associations with 40% of implicated metabolites would have been missed by studying plasma alone. We detected urine-specific findings that provide information about metabolite reabsorption in the kidney, such as aquaporin (AQP)-7-mediated glycerol transport, and different metabolomic footprints of kidney-expressed proteins in plasma and urine that are consistent with their localization and function, including the transporters NaDC3 (SLC13A3) and ASBT (SLC10A2). Shared genetic determinants of 7,073 metabolite-disease combinations represent a resource to better understand metabolic diseases and revealed connections of dipeptidase 1 with circulating digestive enzymes and with hypertension. Extending genetic studies of the metabolome beyond plasma yields unique insights into processes at the interface of body compartments.

Up‐regulation of PRKDC was associated with poor renal dysfunction after renal transplantation: A multi‐centre analysis

Renal transplantation is the only efficacious treatment for end-stage kidney disease. However, some people have developed renal insufficiency after transplantation, the mechanisms of which have not been well clarified. Previous studies have focused on patient factors, while the effect of gene expression in the donor kidney on post-transplant renal function has been less studied. Donor kidney clinical data and mRNA expression status were extracted from the GEO database (GSE147451). Weight gene co-expression network analysis (WGCNA) and differential gene enrichment analysis were performed. For external validation, we collected data from 122 patients who accepted renal transplantation at several hospitals and measured the level of target genes by qPCR. This study included 192 patients from the GEO data set, and 13 co-expressed genes were confirmed by WGCNA and differential gene enrichment analysis. Then, the PPI network contained 17 edges as well as 12 nodes, and four central genes (PRKDC, RFC5, RFC3 and RBM14) were identified. We found by collecting data from 122 patients who underwent renal transplantation in several hospitals and by multivariate logistic regression that acute graft-versus-host disease postoperative infection, PRKDC [Hazard Ratio (HR) = 4.44; 95% CI = [1.60, 13.68]; p = 0.006] mRNA level correlated with the renal function after transplantation. The prediction model constructed had good predictive accuracy (C-index = 0.886). Elevated levels of donor kidney PRKDC are associated with renal dysfunction after transplantation. The prediction model of renal function status for post-transplant recipients based on PRKDC has good predictive accuracy and clinical application.

Integrated proteomic and metabolomic modules identified as biomarkers of mortality in the Atherosclerosis Risk in Communities study and the African American Study of Kidney Disease and Hypertension

BACKGROUND

Proteins and metabolites are essential for many biological functions and often linked through enzymatic or transport reactions. Individual molecules have been associated with all-cause mortality. Many of these are correlated and might jointly represent pathways or endophenotypes involved in diseases.

RESULTS

We present an integrated analysis of proteomics and metabolomics via a local dimensionality reduction clustering method. We identified 224 modules of correlated proteins and metabolites in the Atherosclerosis Risk in Communities (ARIC) study, a general population cohort of older adults (N = 4046, mean age 75.7, mean eGFR 65). Many of the modules displayed strong cross-sectional associations with demographic and clinical characteristics. In comprehensively adjusted analyses, including fasting plasma glucose, history of cardiovascular disease, systolic blood pressure and kidney function among others, 60 modules were associated with mortality. We transferred the network structure to the African American Study of Kidney Disease and Hypertension (AASK) (N = 694, mean age 54.5, mean mGFR 46) and identified mortality associated modules relevant in this disease specific cohort. The four mortality modules relevant in both the general population and CKD were all a combination of proteins and metabolites and were related to diabetes / insulin secretion, cardiovascular disease and kidney function. Key components of these modules included N-terminal (NT)-pro hormone BNP (NT-proBNP), Sushi, Von Willebrand Factor Type A, EGF And Pentraxin (SVEP1), and several kallikrein proteases.

CONCLUSION

Through integrated biomarkers of the proteome and metabolome we identified functions of (patho-) physiologic importance related to diabetes, cardiovascular disease and kidney function.

Serum Metabolites and Kidney Outcomes: The Atherosclerosis Risk in Communities Study

Rationale & Objective

Novel metabolite biomarkers of kidney failure with replacement therapy (KFRT) may help identify people at high risk for adverse kidney outcomes and implicated pathways may aid in developing targeted therapeutics.

Study Design

Prospective cohort.

Setting & Participants

The cohort included 3,799 Atherosclerosis Risk in Communities study participants with serum samples available for measurement at visit 1 (1987-1989).

Exposure

Baseline serum levels of 318 metabolites.

Outcomes

Incident KFRT, kidney failure (KFRT, estimated glomerular filtration rate <15 mL/min/1.73 m², or death from kidney disease).

Analytical Approach

Because metabolites are often intercorrelated and represent shared pathways, we used a high dimension reduction technique called Netboost to cluster metabolites. Longitudinal associations between clusters of metabolites and KFRT and kidney failure were estimated using a Cox proportional hazards model.

Results

Mean age of study participants was 53 years, 61% were African American, and 13% had diabetes. There were 160 KFRT cases and 357 kidney failure cases over a mean of 23 years. The 314 metabolites were grouped in 43 clusters. Four clusters were significantly associated with risk of KFRT and 6 were associated with kidney failure (including 3 shared clusters). The 3 shared clusters suggested potential pathways perturbed early in kidney disease: cluster 5 (15 metabolites involved in alanine, aspartate, and glutamate metabolism as well as 5-oxoproline and several gamma-glutamyl amino acids), cluster 26 (6 metabolites involved in sugar and inositol phosphate metabolism), and cluster 34 (21 metabolites involved in glycerophospholipid metabolism). Several individual metabolites were also significantly associated with both KFRT and kidney failure, including glucose and mannose, which were associated with higher risk of both outcomes, and 5-oxoproline, gamma-glutamyl amino acids, linoleoylglycerophosphocholine, 1,5-anhydroglucitol, which were associated with lower risk of both outcomes.

Limitations

Inability to determine if the metabolites cause or are a consequence of changes in kidney function.

Conclusions

We identified several clusters of metabolites reproducibly associated with development of KFRT. Future experimental studies are needed to validate our findings as well as continue unraveling metabolic pathways involved in kidney function decline.

Decreased complement 4d increases poor prognosis in patients with non‑small cell lung cancer combined with gastrointestinal lymph node metastasis

Lung cancer is a common malignancy that is difficult to treat and has a high risk of mortality. Although gastrointestinal lymph node metastasis has long been known to exert major impact on the prognosis of lung cancer, the mechanism of its occurrence and potential biological markers remain elusive. Therefore, the present study retrospectively analyzed data from 132 patients with non-small cell lung cancer (NSCLC) combined with lymph node metastasis between February 2010 and April 2019 from the First Affiliated Hospital of Soochow University (Suzhou, China) and Sichuan Cancer Hospital (Chengdu, China). Overall survival was assessed using Kaplan-Meier analysis and Cox logistic regression model. In addition, a prediction model was constructed based on immune indicators such as complement C3b and C4d (measured by ELISA), before the accuracy of this model was validated using calibration curves for 5-year OS. Among the 132 included patients, a total of 92 (70.0%) succumbed to the disease within 5 years. Multifactorial analysis revealed that complement C3b deficiency increased the risk of mortality by nearly two-fold [hazard ratio (HR)=2.23; 95% CI=1.20-4.14; P=0.017], whilst complement C4d deficiency similarly increased the risk of mortality by two-fold (HR=2.14; 95% CI=1.14-4.00; P=0.012). The variables were subsequently screened using Cox model to construct a prediction model based on complement C3b and C4d levels before a Nomogram plotted. By internal validation for the 132 patients, the Nomogram accurately estimated the risk of mortality, with a corrected C-index of 0.810. External validation of the model in another 50 patients from Sichuan Cancer Hospital revealed an accuracy of 77.0%. Overall, this mortality risk prediction model constructed based on complement levels showed accuracy in assessing the prognosis of patients with metastatic NSCLC. Therefore, complement C3b and C4d have potential for use as biomarkers to predict the risk of mortality in such patients.

Circulating Cell-Free Nucleic Acids as Epigenetic Biomarkers in Precision Medicine

The circulating cell-free nucleic acids (ccfNAs) are a mixture of single- or double-stranded nucleic acids, released into the blood plasma/serum by different tissues via apoptosis, necrosis, and secretions. Under healthy conditions, ccfNAs originate from the hematopoietic system, whereas under various clinical scenarios, the concomitant tissues release ccfNAs into the bloodstream. These ccfNAs include DNA, RNA, microRNA (miRNA), long non-coding RNA (lncRNA), fetal DNA/RNA, and mitochondrial DNA/RNA, and act as potential biomarkers in various clinical conditions. These are associated with different epigenetic modifications, which show disease-related variations and so finding their role as epigenetic biomarkers in clinical settings. This field has recently emerged as the latest advance in precision medicine because of its clinical relevance in diagnostic, prognostic, and predictive values. DNA methylation detected in ccfDNA has been widely used in personalized clinical diagnosis; furthermore, there is also the emerging role of ccfRNAs like miRNA and lncRNA as epigenetic biomarkers. This review focuses on the novel approaches for exploring ccfNAs as epigenetic biomarkers in personalized clinical diagnosis and prognosis, their potential as therapeutic targets and disease progression monitors, and reveals the tremendous potential that epigenetic biomarkers present to improve precision medicine. We explore the latest techniques for both quantitative and qualitative detection of epigenetic modifications in ccfNAs. The data on epigenetic modifications on ccfNAs are complex and often milieu-specific posing challenges for its understanding. Artificial intelligence and deep networks are the novel approaches for decoding complex data and providing insight into the decision-making in precision medicine.