Evolution of the Insulin Gene: Changes in Gene Number, Sequence, and Processing

Insulin has not only made major contributions to the field of clinical medicine but has also played central roles in the advancement of fundamental molecular biology, including evolution. Insulin is essential for the health of vertebrate species, yet its function has been modified in species-specific manners. With the advent of genome sequencing, large numbers of insulin coding sequences have been identified in genomes of diverse vertebrates and have revealed unexpected changes in the numbers of genes within genomes and in their sequence that likely impact biological function. The presence of multiple insulin genes within a genome potentially allows specialization of an insulin gene. Discovery of changes in proteolytic processing suggests that the typical two-chain hormone structure is not necessary for all of inulin’s biological activities.

Machine learning algorithms in big data analyses identify determinants of insulin gene transcription

Machine learning (ML) workflows enable unprejudiced and robust evaluation of complex datasets and are being increasingly sought in analyzing transcriptome-based big datasets. Here, we analysed over 490,000,000 data points to compare 10 different ML algorithms in a large (N=11,652) training dataset of single-cell RNA-sequencing of human pancreatic cells to identify features (genes) associated with the presence or absence of insulin gene transcript(s). Prediction accuracy and sensitivity of models were tested in a separate validation dataset (N=2,913 single-cell transcriptomes) and the efficacy of each ML workflow to accurately identify insulin-producing cells assessed. Overall, Ensemble ML workflows, and in particular, Random Forest ML algorithm delivered high predictive power in a receiver operator characteristic (ROC) curve analysis (AUC=0.83) at the highest sensitivity (0.98) as compared to the other nine algorithms. The top 10 features, (including IAPP, ADCYAP1, LDHA and SST) common to the three Ensemble ML workflows were identified to be localized to human islet-β cells as well as non-β cells and were significantly dysregulated in scRNA-seq datasets from Ire-1αβ-/- mice that demonstrate de-differentiation of pancreatic β-cells as well as in pancreatic single cells from individuals with Type 2 Diabetes. Our findings provide a direct comparison of ML workflows in big data analyses, identify key determinants of insulin transcription and provide workflows for other regulatory analyses to identify/validate novel genes/features of endocrine pancreatic gene transcription.