CLARITE Facilitates the Quality Control and Analysis Process for EWAS of Metabolic-Related Traits

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

OBJECTIVE

Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN.

METHODS

A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis.

RESULTS

Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN.

CONCLUSION

We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection.

Sex Differences in the Metabolome of Alzheimer's Disease Progression

Alzheimer's disease (AD) is the leading cause of dementia; however, men and women face differential AD prevalence, presentation, and progression risks. Characterizing metabolomic profiles during AD progression is fundamental to understand the metabolic disruptions and the biological pathways involved. However, outstanding questions remain of whether peripheral metabolic changes occur equally in men and women with AD. Here, we evaluated differential effects of metabolomic and brain volume associations between sexes. We used three cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI), evaluated 1,368 participants, two metabolomic platforms with 380 metabolites in total, and six brain segment volumes. Using dimension reduction techniques, we took advantage of the correlation structure of the brain volume phenotypes and the metabolite concentration values to reduce the number of tests while aggregating relevant biological structures. Using WGCNA, we aggregated modules of highly co-expressed metabolites. On the other hand, we used partial least squares regression-discriminant analysis (PLS-DA) to extract components of brain volumes that maximally co-vary with AD diagnosis as phenotypes. We tested for differences in effect sizes between sexes in the association between single metabolite and metabolite modules with the brain volume components. We found five metabolite modules and 125 single metabolites with significant differences between sexes. These results highlight a differential lipid disruption in AD progression between sexes. Men showed a greater negative association of phosphatidylcholines and sphingomyelins and a positive association of VLDL and large LDL with AD progression. In contrast, women showed a positive association of triglycerides in VLDL and small and medium LDL with AD progression. Explicitly identifying sex differences in metabolomics during AD progression can highlight particular metabolic disruptions in each sex. Our research study and strategy can lead to better-tailored studies and better-suited treatments that take sex differences into account.

Software Application Profile: exposomeShiny—a toolbox for exposome data analysis

Motivation

Studying the role of the exposome in human health and its impact on different omic layers requires advanced statistical methods. Many of these methods are implemented in different R and Bioconductor packages, but their use may require strong expertise in R, in writing pipelines and in using new R classes which may not be familiar to non-advanced users. ExposomeShiny provides a bridge between researchers and most of the state-of-the-art exposome analysis methodologies, without the need of advanced programming skills.

Implementation

ExposomeShiny is a standalone web application implemented in R. It is available as source files and can be installed in any server or computer avoiding problems with data confidentiality. It is executed in RStudio which opens a browser window with the web application.

General features

The presented implementation allows the conduct of: (i) data pre-processing: normalization and missing imputation (including limit of detection); (ii) descriptive analysis; (iii) exposome principal component analysis (PCA) and hierarchical clustering; (iv) exposome-wide association studies (ExWAS) and variable selection ExWAS; (v) omic data integration by single association and multi-omic analyses; and (vi) post-exposome data analyses to gain biological insight for the exposures, genes or using the Comparative Toxicogenomics Database (CTD) and pathway analysis.

Availability

The exposomeShiny source code is freely available on Github at [https://github.com/isglobal-brge/exposomeShiny], Git tag v1.4. The software is also available as a Docker image [https://hub.docker.com/r/brgelab/exposome-shiny], tag v1.4. A user guide with information about the analysis methodologies as well as information on how to use exposomeShiny is freely hosted at [https://isglobal-brge.github.io/exposome_bookdown/].

Methodology in phenome-wide association studies: a systematic review

Phenome-wide association study (PheWAS) has been increasingly used to identify novel genetic associations across a wide spectrum of phenotypes. This systematic review aims to summarise the PheWAS methodology, discuss the advantages and challenges of PheWAS, and provide potential implications for future PheWAS studies. Medical Literature Analysis and Retrieval System Online (MEDLINE) and Excerpta Medica Database (EMBASE) databases were searched to identify all published PheWAS studies up until 24 April 2021. The PheWAS methodology incorporating how to perform PheWAS analysis and which software/tool could be used, were summarised based on the extracted information. A total of 1035 studies were identified and 195 eligible articles were finally included. Among them, 137 (77.0%) contained 10 000 or more study participants, 164 (92.1%) defined the phenome based on electronic medical records data, 140 (78.7%) used genetic variants as predictors, and 73 (41.0%) conducted replication analysis to validate PheWAS findings and almost all of them (94.5%) received consistent results. The methodology applied in these PheWAS studies was dissected into several critical steps, including quality control of the phenome, selecting predictors, phenotyping, statistical analysis, interpretation and visualisation of PheWAS results, and the workflow for performing a PheWAS was established with detailed instructions on each step. This study provides a comprehensive overview of PheWAS methodology to help practitioners achieve a better understanding of the PheWAS design, to detect understudied or overstudied outcomes, and to direct their research by applying the most appropriate software and online tools for their study data structure.

Tissue specificity-aware TWAS (TSA-TWAS) framework identifies novel associations with metabolic, immunologic, and virologic traits in HIV-positive adults

As a type of relatively new methodology, the transcriptome-wide association study (TWAS) has gained interest due to capacity for gene-level association testing. However, the development of TWAS has outpaced statistical evaluation of TWAS gene prioritization performance. Current TWAS methods vary in underlying biological assumptions about tissue specificity of transcriptional regulatory mechanisms. In a previous study from our group, this may have affected whether TWAS methods better identified associations in single tissues versus multiple tissues. We therefore designed simulation analyses to examine how the interplay between particular TWAS methods and tissue specificity of gene expression affects power and type I error rates for gene prioritization. We found that cross-tissue identification of expression quantitative trait loci (eQTLs) improved TWAS power. Single-tissue TWAS (i.e., PrediXcan) had robust power to identify genes expressed in single tissues, but, often found significant associations in the wrong tissues as well (therefore had high false positive rates). Cross-tissue TWAS (i.e., UTMOST) had overall equal or greater power and controlled type I error rates for genes expressed in multiple tissues. Based on these simulation results, we applied a tissue specificity-aware TWAS (TSA-TWAS) analytic framework to look for gene-based associations with pre-treatment laboratory values from AIDS Clinical Trial Group (ACTG) studies. We replicated several proof-of-concept transcriptionally regulated gene-trait associations, including UGT1A1 (encoding bilirubin uridine diphosphate glucuronosyltransferase enzyme) and total bilirubin levels (p = 3.59×10⁻¹²), and CETP (cholesteryl ester transfer protein) with high-density lipoprotein cholesterol (p = 4.49×10⁻¹²). We also identified several novel genes associated with metabolic and virologic traits, as well as pleiotropic genes that linked plasma viral load, absolute basophil count, and/or triglyceride levels. By highlighting the advantages of different TWAS methods, our simulation study promotes a tissue specificity-aware TWAS analytic framework that revealed novel aspects of HIV-related traits.

Transcriptome-wide association studies (TWAS) are a type of bioinformatics methodology for identifying complex trait-associated genes. There have been various TWAS methods, each developed under distinct biological assumptions of how genes contribute to complex traits. It is unclear, however, how powerful different TWAS methods are under a variety of biological scenarios. Here, we design an unbiased simulation strategy to evaluate the performance of multiple representative TWAS methods. We find that no one method fits all. Different TWAS methods are advantageous at dealing with different biological scenarios and answering different research questions. Thus, we propose a novel TWAS analytic framework that integrates and maximizes the performance of multiple TWAS methods, and validate its capability using a well-studied real-world dataset. In summary, our study provides quantitative evaluation of method performance to aid future TWAS experimental design and understanding of genes underlying complex human traits. The TWAS evaluation tool is made publicly available.

Clinical laboratory test-wide association scan of polygenic scores identifies biomarkers of complex disease

BACKGROUND

Clinical laboratory (lab) tests are used in clinical practice to diagnose, treat, and monitor disease conditions. Test results are stored in electronic health records (EHRs), and a growing number of EHRs are linked to patient DNA, offering unprecedented opportunities to query relationships between genetic risk for complex disease and quantitative physiological measurements collected on large populations.

METHODS

A total of 3075 quantitative lab tests were extracted from Vanderbilt University Medical Center's (VUMC) EHR system and cleaned for population-level analysis according to our QualityLab protocol. Lab values extracted from BioVU were compared with previous population studies using heritability and genetic correlation analyses. We then tested the hypothesis that polygenic risk scores for biomarkers and complex disease are associated with biomarkers of disease extracted from the EHR. In a proof of concept analyses, we focused on lipids and coronary artery disease (CAD). We cleaned lab traits extracted from the EHR performed lab-wide association scans (LabWAS) of the lipids and CAD polygenic risk scores across 315 heritable lab tests then replicated the pipeline and analyses in the Massachusetts General Brigham Biobank.

RESULTS

Heritability estimates of lipid values (after cleaning with QualityLab) were comparable to previous reports and polygenic scores for lipids were strongly associated with their referent lipid in a LabWAS. LabWAS of the polygenic score for CAD recapitulated canonical heart disease biomarker profiles including decreased HDL, increased pre-medication LDL, triglycerides, blood glucose, and glycated hemoglobin (HgbA1C) in European and African descent populations. Notably, many of these associations remained even after adjusting for the presence of cardiovascular disease and were replicated in the MGBB.

CONCLUSIONS

Polygenic risk scores can be used to identify biomarkers of complex disease in large-scale EHR-based genomic analyses, providing new avenues for discovery of novel biomarkers and deeper understanding of disease trajectories in pre-symptomatic individuals. We present two methods and associated software, QualityLab and LabWAS, to clean and analyze EHR labs at scale and perform a Lab-Wide Association Scan.

What about the environment? Leveraging multi-omic datasets to characterize the environment's role in human health

The environment plays an important role in mediating human health. In this session we consider research addressing ways to overcome the challenges associated with studying the multifaceted and ever-changing environment. Environmental health research has a need for technological and methodological advances which will further our knowledge of how exposures precipitate complex phenotypes and exacerbate disease.

Investigation of gene-gene interactions in cardiac traits and serum fatty acid levels in the LURIC Health Study

Epistasis analysis elucidates the effects of gene-gene interactions (G×G) between multiple loci for complex traits. However, the large computational demands and the high multiple testing burden impede their discoveries. Here, we illustrate the utilization of two methods, main effect filtering based on individual GWAS results and biological knowledge-based modeling through Biofilter software, to reduce the number of interactions tested among single nucleotide polymorphisms (SNPs) for 15 cardiac-related traits and 14 fatty acids. We performed interaction analyses using the two filtering methods, adjusting for age, sex, body mass index (BMI), waist-hip ratio, and the first three principal components from genetic data, among 2,824 samples from the Ludwigshafen Risk and Cardiovascular (LURIC) Health Study. Using Biofilter, one interaction nearly met Bonferroni significance: an interaction between rs7735781 in XRCC4 and rs10804247 in XRCC5 was identified for venous thrombosis with a Bonferroni-adjusted likelihood ratio test (LRT) p: 0.0627. A total of 57 interactions were identified from main effect filtering for the cardiac traits G×G (10) and fatty acids G×G (47) at Bonferroni-adjusted LRT p < 0.05. For cardiac traits, the top interaction involved SNPs rs1383819 in SNTG1 and rs1493939 (138kb from 5’ of SAMD12) with Bonferroni-adjusted LRT p: 0.0228 which was significantly associated with history of arterial hypertension. For fatty acids, the top interaction between rs4839193 in KCND3 and rs10829717 in LOC107984002 with Bonferroni-adjusted LRT p: 2.28×10⁻⁵ was associated with 9-trans 12-trans octadecanoic acid, an omega-6 trans fatty acid. The model inflation factor for the interactions under different filtering methods was evaluated from the standard median and the linear regression approach. Here, we applied filtering approaches to identify numerous genetic interactions related to cardiac-related outcomes as potential targets for therapy. The approaches described offer ways to detect epistasis in the complex traits and to improve precision medicine capability.

Software tools, databases and resources in metabolomics: updates from 2018 to 2019

Metabolomics has evolved as a discipline from a discovery and functional genomics tool, and is now a cornerstone in the era of big data-driven precision medicine. Sample preparation strategies and analytical technologies have seen enormous growth, and keeping pace with data analytics is challenging, to say the least. This review introduces and briefly presents around 100 metabolomics software resources, tools, databases, and other utilities that have surfaced or have improved in 2019. Table 1 provides the computational dependencies of the tools, categorizes the resources based on utility and ease of use, and provides hyperlinks to webpages where the tools can be downloaded or used. This review intends to keep the community of metabolomics researchers up to date with all the software tools, resources, and databases developed in 2019, in one place.