Serotonin is elevated in risk-genotype carriers of TCF7L2 - rs7903146

Machine Learning Approach to Metabolomic Data Predicts Type 2 Diabetes Mellitus Incidence

Metabolomics, with its wealth of data, offers a valuable avenue for enhancing predictions and decision-making in diabetes. This observational study aimed to leverage machine learning (ML) algorithms to predict the 4-year risk of developing type 2 diabetes mellitus (T2DM) using targeted quantitative metabolomics data. A cohort of 279 cardiovascular risk patients who underwent coronary angiography and who were initially free of T2DM according to American Diabetes Association (ADA) criteria was analyzed at baseline, including anthropometric data and targeted metabolomics, using liquid chromatography (LC)-mass spectroscopy (MS) and flow injection analysis (FIA)-MS, respectively. All patients were followed for four years. During this time, 11.5% of the patients developed T2DM. After data preprocessing, 362 variables were used for ML, employing the Caret package in R. The dataset was divided into training and test sets (75:25 ratio) and we used an oversampling approach to address the classifier imbalance of T2DM incidence. After an additional recursive feature elimination step, identifying a set of 77 variables that were the most valuable for model generation, a Support Vector Machine (SVM) model with a linear kernel demonstrated the most promising predictive capabilities, exhibiting an F1 score of 50%, a specificity of 93%, and balanced and unbalanced accuracies of 72% and 88%, respectively. The top-ranked features were bile acids, ceramides, amino acids, and hexoses, whereas anthropometric features such as age, sex, waist circumference, or body mass index had no contribution. In conclusion, ML analysis of metabolomics data is a promising tool for identifying individuals at risk of developing T2DM and opens avenues for personalized and early intervention strategies.

Estimating the Direct Effect between Dietary Macronutrients and Cardiometabolic Disease, Accounting for Mediation by Adiposity and Physical Activity

Assessing the causal effects of individual dietary macronutrients and cardiometabolic disease is challenging because distinguish direct effects from those mediated or confounded by other factors is difficult. To estimate these effects, intake of protein, carbohydrate, sugar, fat, and its subtypes were obtained using food frequency data derived from a Swedish population-based cohort (n~60,000). Data on clinical outcomes (i.e., type 2 diabetes (T2D) and cardiovascular disease (CVD) incidence) were obtained by linking health registry data. We assessed the magnitude of direct and mediated effects of diet, adiposity and physical activity on T2D and CVD using structural equation modelling (SEM). To strengthen causal inference, we used Mendelian randomization (MR) to model macronutrient intake exposures against clinical outcomes. We identified likely causal effects of genetically predicted carbohydrate intake (including sugar intake) and T2D, independent of adiposity and physical activity. Pairwise, serial- and parallel-mediational configurations yielded similar results. In the integrative genomic analyses, the candidate causal variant localized to the established T2D gene TCF7L2. These findings may be informative when considering which dietary modifications included in nutritional guidelines are most likely to elicit health-promoting effects.

The role of transcription factor 7-like 2 in metabolic disorders

Transcription factor 7-like 2 (TCF7L2), a member of the T cell factor/lymphoid enhancer factor family, generally forms a complex with β-catenin to regulate the downstream target genes as an effector of the canonical Wnt signalling pathway. TCF7L2 plays a vital role in various biological processes and functions in many organs and tissues, including the liver, islet and adipose tissues. Further, TCF7L2 down-regulates hepatic gluconeogenesis and promotes lipid accumulation. In islets, TCF7L2 not only affects the insulin secretion of the β-cells but also has an impact on other cells. In addition, TCF7L2 influences adipogenesis in adipose tissues. Thus, an out-of-control TCF7L2 expression can result in metabolic disorders. The TCF7L2 gene is composed of 17 exons, generating 13 different transcripts, and has many single-nucleotide polymorphisms (SNPs). The discovery that these SNPs have an impact on the risk of type 2 diabetes (T2D) has attracted thorough investigations in the study of TCF7L2. Apart from T2D, TCF7L2 SNPs are also associated with type 1, posttransplant and other types of diabetes. Furthermore, TCF7L2 variants affect the progression of other disorders, such as obesity, cancers, metabolic syndrome and heart diseases. Finally, the interaction between TCF7L2 variants and diet also needs to be investigated.