Machine Learning Approaches Reveal Metabolic Signatures of Incident Chronic Kidney Disease in Individuals With Prediabetes and Type 2 Diabetes.

Early and precise identification of individuals with prediabetes and type 2 diabetes (T2D) at risk for progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin C18:1 and phosphatidylcholine diacyl C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors, and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in people with prediabetes and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation.

Arrhythmic Gut Microbiome Signatures Predict Risk of Type 2 Diabetes.

Lifestyle, obesity, and the gut microbiome are important risk factors for metabolic disorders. We demonstrate in 1,976 subjects of a German population cohort (KORA) that specific microbiota members show 24-h oscillations in their relative abundance and identified 13 taxa with disrupted rhythmicity in type 2 diabetes (T2D). Cross-validated prediction models based on this signature similarly classified T2D. In an independent cohort (FoCus), disruption of microbial oscillation and the model for T2D classification was confirmed in 1,363 subjects. This arrhythmic risk signature was able to predict T2D in 699 KORA subjects 5 years after initial sampling, being most effective in combination with BMI. Shotgun metagenomic analysis functionally linked 26 metabolic pathways to the diurnal oscillation of gut bacteria. Thus, a cohort-specific risk pattern of arrhythmic taxa enables classification and prediction of T2D, suggesting a functional link between circadian rhythms and the microbiome in metabolic diseases.

Investigation of Adiposity Measures and Operational Taxonomic unit (OTU) Data Transformation Procedures in Stool Samples from a German Cohort Study Using Machine Learning Algorithms.

The analysis of the gut microbiome with respect to health care prevention and diagnostic purposes is increasingly the focus of current research. We analyzed around 2000 stool samples from the KORA (Cooperative Health Research in the Region of Augsburg) cohort using high-throughput 16S rRNA gene amplicon sequencing representing a total microbial diversity of 2089 operational taxonomic units (OTUs). We evaluated the combination of three different components to assess the reflection of obesity related to microbiota profiles: (i) four prediction methods (i.e., partial least squares (PLS), support vector machine regression (SVMReg), random forest (RF), and M5Rules); (ii) five OTU data transformation approaches (i.e., no transformation, relative abundance without and with log-transformation, as well as centered and isometric log-ratio transformations); and (iii) predictions from nine measurements of obesity (i.e., body mass index, three measures of body shape, and five measures of body composition). Our results showed a substantial impact of all three components. The applications of SVMReg and PLS in combination with logarithmic data transformations resulted in considerably predictive models for waist circumference-related endpoints. These combinations were at best able to explain almost 40% of the variance in obesity measurements based on stool microbiota data (i.e., OTUs) only. A reduced loss in predictive performance was seen after sex-stratification in waist-height ratio compared to other waist-related measurements. Moreover, our analysis showed that the contribution of OTUs less prevalent and abundant is minor concerning the predictive power of our models.

The Reproduction Rate of Peptide Transporter PEPT-1 Deficient C. elegans Is Dependent on Dietary Glutamate Supply.

Intestinal absorption of dietary amino acids is mediated via two routes. Free amino acids released by hydrolysis of dietary proteins are taken up by a multitude of amino acid transporters while di- and tripeptides released are taken up by the peptide transporter PEPT-1. Loss of PEPT-1 impairs growth, post-embryonic development and reproduction in Caenorhabditis elegans, and supplementation with a mixture of all L-amino acids only partially rescues fertility. In the present study, we demonstrate that dietary L-glutamate is the responsible amino acid that can increase fertility in hermaphrodite pept-1 worms. This effect was associated with a significantly higher uptake of glutamate/aspartate in pept-1 than in wildtype C. elegans. Furthermore, we found that the intestinal transporter proteins SNF-5 of the solute carrier SLC6 family of nutrient amino acid transporters (NAT) and AAT-6 of the SLC7 family as the light subunit of a heteromeric amino acid transporter (HAT) play a key role in glutamate homeostasis in pept-1 C. elegans. Genes encoding these transporters are highly expressed and upon silencing a 95% reduced fertility (snf-5) and sterility (aat-6) was observed. A subsequent L-glutamate supplementation failed to rescue these phenotypes. Dietary glutamate supplementation did neither influence the feeding frequency, nor did it improve mating efficiency of pept-1 males. Most strikingly, pept-1 were more prone to habituation to repeated gentle touch stimuli than wildtype C. elegans, and dietary glutamate supply was sufficient to alter this behavioral output by restoring the mechanosensory response to wildtype levels. Taken together, our data demonstrate a key role of L-glutamate in amino acid homeostasis in C. elegans lacking the peptide transporter in the intestine and demonstrate its distinct role in reproduction and for neural circuits mediating touch sensitivity.

Night Shift Work Affects Urine Metabolite Profiles of Nurses with Early Chronotype.

Night shift work can have a serious impact on health. Here, we assess whether and how night shift work influences the metabolite profiles, specifically with respect to different chronotype classes. We have recruited 100 women including 68 nurses working both, day shift and night shifts for up to 5 consecutive days and collected 3640 spontaneous urine samples. About 424 waking-up urine samples were measured using a targeted metabolomics approach. To account for urine dilution, we applied three methods to normalize the metabolite values: creatinine-, osmolality- and regression-based normalization. Based on linear mixed effect models, we found 31 metabolites significantly (false discovery rate <0.05) affected in nurses working in night shifts. One metabolite, acylcarnitine C10:2, was consistently identified with all three normalization methods. We further observed 11 and 4 metabolites significantly associated with night shift in early and late chronotype classes, respectively. Increased levels of medium- and long chain acylcarnitines indicate a strong impairment of the fatty acid oxidation. Our results show that night shift work influences acylcarnitines and BCAAs, particularly in nurses in the early chronotype class. Women with intermediate and late chronotypes appear to be less affected by night shift work.

Metformin Effect on Nontargeted Metabolite Profiles in Patients With Type 2 Diabetes and in Multiple Murine Tissues.

Metformin is the first-line oral medication to increase insulin sensitivity in patients with type 2 diabetes (T2D). Our aim was to investigate the pleiotropic effect of metformin using a nontargeted metabolomics approach. We analyzed 353 metabolites in fasting serum samples of the population-based human KORA (Cooperative Health Research in the Region of Augsburg) follow-up survey 4 cohort. To compare T2D patients treated with metformin (mt-T2D, n = 74) and those without antidiabetes medication (ndt-T2D, n = 115), we used multivariable linear regression models in a cross-sectional study. We applied a generalized estimating equation to confirm the initial findings in longitudinal samples of 683 KORA participants. In a translational approach, we used murine plasma, liver, skeletal muscle, and epididymal adipose tissue samples from metformin-treated db/db mice to further corroborate our findings from the human study. We identified two metabolites significantly (P < 1.42E-04) associated with metformin treatment. Citrulline showed lower relative concentrations and an unknown metabolite X-21365 showed higher relative concentrations in human serum when comparing mt-T2D with ndt-T2D. Citrulline was confirmed to be significantly (P < 2.96E-04) decreased at 7-year follow-up in patients who started metformin treatment. In mice, we validated significantly (P < 4.52E-07) lower citrulline values in plasma, skeletal muscle, and adipose tissue of metformin-treated animals but not in their liver. The lowered values of citrulline we observed by using a nontargeted approach most likely resulted from the pleiotropic effect of metformin on the interlocked urea and nitric oxide cycle. The translational data derived from multiple murine tissues corroborated and complemented the findings from the human cohort.

Random Survival Forest in practice: a method for modelling complex metabolomics data in time to event analysis.

BACKGROUND: The application of metabolomics in prospective cohort studies is statistically challenging. Given the importance of appropriate statistical methods for selection of disease-associated metabolites in highly correlated complex data, we combined random survival forest (RSF) with an automated backward elimination procedure that addresses such issues. METHODS: Our RSF approach was illustrated with data from the European Prospective Investigation into Cancer and Nutrition (EPIC)-Potsdam study, with concentrations of 127 serum metabolites as exposure variables and time to development of type 2 diabetes mellitus (T2D) as outcome variable. Out of this data set, Cox regression with a stepwise selection method was recently published. Replication of methodical comparison (RSF and Cox regression) was conducted in two independent cohorts. Finally, the R-code for implementing the metabolite selection procedure into the RSF-syntax is provided. RESULTS: The application of the RSF approach in EPIC-Potsdam resulted in the identification of 16 incident T2D-associated metabolites which slightly improved prediction of T2D when used in addition to traditional T2D risk factors and also when used together with classical biomarkers. The identified metabolites partly agreed with previous findings using Cox regression, though RSF selected a higher number of highly correlated metabolites. CONCLUSIONS: The RSF method appeared to be a promising approach for identification of disease-associated variables in complex data with time to event as outcome. The demonstrated RSF approach provides comparable findings as the generally used Cox regression, but also addresses the problem of multicollinearity and is suitable for high-dimensional data.