An omics-based machine learning approach to predict diabetes progression: a RHAPSODY study

AIMS/HYPOTHESIS

People with type 2 diabetes are heterogeneous in their disease trajectory, with some progressing more quickly to insulin initiation than others. Although classical biomarkers such as age, HbA1c and diabetes duration are associated with glycaemic progression, it is unclear how well such variables predict insulin initiation or requirement and whether newly identified markers have added predictive value.

METHODS

In two prospective cohort studies as part of IMI-RHAPSODY, we investigated whether clinical variables and three types of molecular markers (metabolites, lipids, proteins) can predict time to insulin requirement using different machine learning approaches (lasso, ridge, GRridge, random forest). Clinical variables included age, sex, HbA1c, HDL-cholesterol and C-peptide. Models were run with unpenalised clinical variables (i.e. always included in the model without weights) or penalised clinical variables, or without clinical variables. Model development was performed in one cohort and the model was applied in a second cohort. Model performance was evaluated using Harrel's C statistic.

RESULTS

Of the 585 individuals from the Hoorn Diabetes Care System (DCS) cohort, 69 required insulin during follow-up (1.0-11.4 years); of the 571 individuals in the Genetics of Diabetes Audit and Research in Tayside Scotland (GoDARTS) cohort, 175 required insulin during follow-up (0.3-11.8 years). Overall, the clinical variables and proteins were selected in the different models most often, followed by the metabolites. The most frequently selected clinical variables were HbA1c (18 of the 36 models, 50%), age (15 models, 41.2%) and C-peptide (15 models, 41.2%). Base models (age, sex, BMI, HbA1c) including only clinical variables performed moderately in both the DCS discovery cohort (C statistic 0.71 [95% CI 0.64, 0.79]) and the GoDARTS replication cohort (C 0.71 [95% CI 0.69, 0.75]). A more extensive model including HDL-cholesterol and C-peptide performed better in both cohorts (DCS, C 0.74 [95% CI 0.67, 0.81]; GoDARTS, C 0.73 [95% CI 0.69, 0.77]). Two proteins, lactadherin and proto-oncogene tyrosine-protein kinase receptor, were most consistently selected and slightly improved model performance.

CONCLUSIONS/INTERPRETATION

Using machine learning approaches, we show that insulin requirement risk can be modestly well predicted by predominantly clinical variables. Inclusion of molecular markers improves the prognostic performance beyond that of clinical variables by up to 5%. Such prognostic models could be useful for identifying people with diabetes at high risk of progressing quickly to treatment intensification.

DATA AVAILABILITY

Summary statistics of lipidomic, proteomic and metabolomic data are available from a Shiny dashboard at https://rhapdata-app.vital-it.ch .

Identifying Aging and Alzheimer Disease-Associated Somatic Variations in Excitatory Neurons From the Human Frontal Cortex

Background and Objectives

With age, somatic mutations accumulated in human brain cells can lead to various neurologic disorders and brain tumors. Because the incidence rate of Alzheimer disease (AD) increases exponentially with age, investigating the association between AD and the accumulation of somatic mutation can help understand the etiology of AD.

Methods

We designed a somatic mutation detection workflow by contrasting genotypes derived from whole-genome sequencing (WGS) data with genotypes derived from scRNA-seq data and applied this workflow to 76 participants from the Religious Order Study and the Rush Memory and Aging Project (ROSMAP) cohort. We focused only on excitatory neurons, the dominant cell type in the scRNA-seq data.

Results

We identified 196 sites that harbored at least 1 individual with an excitatory neuron-specific somatic mutation (ENSM), and these 196 sites were mapped to 127 genes. The single base substitution (SBS) pattern of the putative ENSMs was best explained by signature SBS5 from the Catalogue of Somatic Mutations in Cancer (COSMIC) mutational signatures, a clock-like pattern correlating with the age of the individual. The count of ENSMs per individual also showed an increasing trend with age. Among the mutated sites, we found 2 sites tend to have more mutations in older individuals (16:6899517 [RBFOX1], p = 0.04; 4:21788463 [KCNIP4], p < 0.05). In addition, 2 sites were found to have a higher odds ratio to detect a somatic mutation in AD samples (6:73374221 [KCNQ5], p = 0.01 and 13:36667102 [DCLK1], p = 0.02). Thirty-two genes that harbor somatic mutations unique to AD and the KCNQ5 and DCLK1 genes were used for gene ontology (GO)-term enrichment analysis. We found the AD-specific ENSMs enriched in the GO-term "vocalization behavior" and "intraspecies interaction between organisms." Of interest we observed both age-specific and AD-specific ENSMs enriched in the K⁺ channel-associated genes.

Discussion

Our results show that combining scRNA-seq and WGS data can successfully detect putative somatic mutations. The putative somatic mutations detected from ROSMAP data set have provided new insights into the association of AD and aging with brain somatic mutagenesis.

Single-cell RNA sequencing data reveals rewiring of transcriptional relationships in Alzheimer's Disease associated with risk variants

Understanding how genetic risk variants contribute to Alzheimer's Disease etiology remains a challenge. Single-cell RNA sequencing (scRNAseq) allows for the investigation of cell type specific effects of genomic risk loci on gene expression. Using seven scRNAseq datasets totalling >1.3 million cells, we investigated differential correlation of genes between healthy individuals and individuals diagnosed with Alzheimer's Disease. Using the number of differential correlations of a gene to estimate its involvement and potential impact, we present a prioritization scheme for identifying probable causal genes near genomic risk loci. Besides prioritizing genes, our approach pin-points specific cell types and provides insight into the rewiring of gene-gene relationships associated with Alzheimer's.

Identification of biomarkers for glycaemic deterioration in type 2 diabetes

We identify biomarkers for disease progression in three type 2 diabetes cohorts encompassing 2,973 individuals across three molecular classes, metabolites, lipids and proteins. Homocitrulline, isoleucine and 2-aminoadipic acid, eight triacylglycerol species, and lowered sphingomyelin 42:2;2 levels are predictive of faster progression towards insulin requirement. Of ~1,300 proteins examined in two cohorts, levels of GDF15/MIC-1, IL-18Ra, CRELD1, NogoR, FAS, and ENPP7 are associated with faster progression, whilst SMAC/DIABLO, SPOCK1 and HEMK2 predict lower progression rates. In an external replication, proteins and lipids are associated with diabetes incidence and prevalence. NogoR/RTN4R injection improved glucose tolerance in high fat-fed male mice but impaired it in male db/db mice. High NogoR levels led to islet cell apoptosis, and IL-18R antagonised inflammatory IL-18 signalling towards nuclear factor kappa-B in vitro. This comprehensive, multi-disciplinary approach thus identifies biomarkers with potential prognostic utility, provides evidence for possible disease mechanisms, and identifies potential therapeutic avenues to slow diabetes progression.

Consequences and opportunities arising due to sparser single-cell RNA-seq datasets

With the number of cells measured in single-cell RNA sequencing (scRNA-seq) datasets increasing exponentially and concurrent increased sparsity due to more zero counts being measured for many genes, we demonstrate here that downstream analyses on binary-based gene expression give similar results as count-based analyses. Moreover, a binary representation scales up to ~ 50-fold more cells that can be analyzed using the same computational resources. We also highlight the possibilities provided by binarized scRNA-seq data. Development of specialized tools for bit-aware implementations of downstream analytical tasks will enable a more fine-grained resolution of biological heterogeneity.

Diabetes risk loci-associated pathways are shared across metabolic tissues

Aims/hypothesis

Numerous genome-wide association studies have been performed to understand the influence of genetic variation on type 2 diabetes etiology. Many identified risk variants are located in non-coding and intergenic regions, which complicates understanding of how genes and their downstream pathways are influenced. An integrative data approach will help to understand the mechanism and consequences of identified risk variants.

Methods

In the current study we use our previously developed method CONQUER to overlap 403 type 2 diabetes risk variants with regulatory, expression and protein data to identify tissue-shared disease-relevant mechanisms.

Results

One SNP rs474513 was found to be an expression-, protein- and metabolite QTL. Rs474513 influenced LPA mRNA and protein levels in the pancreas and plasma, respectively. On the pathway level, in investigated tissues most SNPs linked to metabolism. However, in eleven of the twelve tissues investigated nine SNPs were linked to differential expression of the ribosome pathway. Furthermore, seven SNPs were linked to altered expression of genes linked to the immune system. Among them, rs601945 was found to influence multiple HLA genes, including HLA-DQA2, in all twelve tissues investigated.

Conclusion

Our results show that in addition to the classical metabolism pathways, other pathways may be important to type 2 diabetes that show a potential overlap with type 1 diabetes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12864-022-08587-5.

Differential analysis of binarized single-cell RNA sequencing data captures biological variation

Single-cell RNA sequencing data is characterized by a large number of zero counts, yet there is growing evidence that these zeros reflect biological variation rather than technical artifacts. We propose to use binarized expression profiles to identify the effects of biological variation in single-cell RNA sequencing data. Using 16 publicly available and simulated datasets, we show that a binarized representation of single-cell expression data accurately represents biological variation and reveals the relative abundance of transcripts more robustly than counts.

Distinct Molecular Signatures of Clinical Clusters in People With Type 2 Diabetes: An IMI-RHAPSODY Study

Type 2 diabetes is a multifactorial disease with multiple underlying aetiologies. To address this heterogeneity, investigators of a previous study clustered people with diabetes according to five diabetes subtypes. The aim of the current study is to investigate the etiology of these clusters by comparing their molecular signatures. In three independent cohorts, in total 15,940 individuals were clustered based on five clinical characteristics. In a subset, genetic (N = 12,828), metabolomic (N = 2,945), lipidomic (N = 2,593), and proteomic (N = 1,170) data were obtained in plasma. For each data type, each cluster was compared with the other four clusters as the reference. The insulin-resistant cluster showed the most distinct molecular signature, with higher branched-chain amino acid, diacylglycerol, and triacylglycerol levels and aberrant protein levels in plasma were enriched for proteins in the intracellular PI3K/Akt pathway. The obese cluster showed higher levels of cytokines. The mild diabetes cluster with high HDL showed the most beneficial molecular profile with effects opposite of those seen in the insulin-resistant cluster. This study shows that clustering people with type 2 diabetes can identify underlying molecular mechanisms related to pancreatic islets, liver, and adipose tissue metabolism. This provides novel biological insights into the diverse aetiological processes that would not be evident when type 2 diabetes is viewed as a homogeneous disease.

Replication and cross-validation of type 2 diabetes subtypes based on clinical variables: an IMI-RHAPSODY study

AIMS/HYPOTHESIS

Five clusters based on clinical characteristics have been suggested as diabetes subtypes: one autoimmune and four subtypes of type 2 diabetes. In the current study we replicate and cross-validate these type 2 diabetes clusters in three large cohorts using variables readily measured in the clinic.

METHODS

In three independent cohorts, in total 15,940 individuals were clustered based on age, BMI, HbA_1c, random or fasting C-peptide, and HDL-cholesterol. Clusters were cross-validated against the original clusters based on HOMA measures. In addition, between cohorts, clusters were cross-validated by re-assigning people based on each cohort's cluster centres. Finally, we compared the time to insulin requirement for each cluster.

RESULTS

Five distinct type 2 diabetes clusters were identified and mapped back to the original four All New Diabetics in Scania (ANDIS) clusters. Using C-peptide and HDL-cholesterol instead of HOMA2-B and HOMA2-IR, three of the clusters mapped with high sensitivity (80.6-90.7%) to the previously identified severe insulin-deficient diabetes (SIDD), severe insulin-resistant diabetes (SIRD) and mild obesity-related diabetes (MOD) clusters. The previously described ANDIS mild age-related diabetes (MARD) cluster could be mapped to the two milder groups in our study: one characterised by high HDL-cholesterol (mild diabetes with high HDL-cholesterol [MDH] cluster), and the other not having any extreme characteristic (mild diabetes [MD]). When these two milder groups were combined, they mapped well to the previously labelled MARD cluster (sensitivity 79.1%). In the cross-validation between cohorts, particularly the SIDD and MDH clusters cross-validated well, with sensitivities ranging from 73.3% to 97.1%. SIRD and MD showed a lower sensitivity, ranging from 36.1% to 92.3%, where individuals shifted from SIRD to MD and vice versa. People belonging to the SIDD cluster showed the fastest progression towards insulin requirement, while the MDH cluster showed the slowest progression.

CONCLUSIONS/INTERPRETATION

Clusters based on C-peptide instead of HOMA2 measures resemble those based on HOMA2 measures, especially for SIDD, SIRD and MOD. By adding HDL-cholesterol, the MARD cluster based upon HOMA2 measures resulted in the current clustering into two clusters, with one cluster having high HDL levels. Cross-validation between cohorts showed generally a good resemblance between cohorts. Together, our results show that the clustering based on clinical variables readily measured in the clinic (age, HbA_1c, HDL-cholesterol, BMI and C-peptide) results in informative clusters that are representative of the original ANDIS clusters and stable across cohorts. Adding HDL-cholesterol to the clustering resulted in the identification of a cluster with very slow glycaemic deterioration.

CONQUER: an interactive toolbox to understand functional consequences of GWAS hits

Numerous large genome-wide association studies have been performed to understand the influence of genetics on traits. Many identified risk loci are in non-coding and intergenic regions, which complicates understanding how genes and their downstream pathways are influenced. An integrative data approach is required to understand the mechanism and consequences of identified risk loci. Here, we developed the R-package CONQUER. Data for SNPs of interest are acquired from static- and dynamic repositories (build GRCh38/hg38), including GTExPortal, Epigenomics Project, 4D genome database and genome browsers. All visualizations are fully interactive so that the user can immediately access the underlying data. CONQUER is a user-friendly tool to perform an integrative approach on multiple SNPs where risk loci are not seen as individual risk factors but rather as a network of risk factors.

NACHO: an R package for quality control of NanoString nCounter data

SUMMARY

The NanoStringTM nCounter® is a platform for the targeted quantification of expression data in biofluids and tissues. While software by the manufacturer is available in addition to third parties packages, they do not provide a complete quality control (QC) pipeline. Here, we present NACHO ('NAnostring quality Control dasHbOard'), a comprehensive QC R-package. The package consists of three subsequent steps: summarize, visualize and normalize. The summarize function collects all the relevant data and stores it in a tidy format, the visualize function initiates a dashboard with plots of the relevant QC outcomes. It contains QC metrics that are measured by default by the manufacturer, but also calculates other insightful measures, including the scaling factors that are needed in the normalization step. In this normalization step, different normalization methods can be chosen to optimally preprocess data. Together, NACHO is a comprehensive method that optimizes insight and preprocessing of nCounter® data.

AVAILABILITY AND IMPLEMENTATION

NACHO is available as an R-package on CRAN and the development version on GitHub https://github.com/mcanouil/NACHO.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.