Deep Learning for Integrated Analysis of Insulin Resistance with Multi-Omics Data

Abstract

Technological advances in next-generation sequencing (NGS) have made it possible to uncover extensive and dynamic alterations in diverse molecular components and biological pathways across healthy and diseased conditions. Large amounts of multi-omics data originating from emerging NGS experiments require feature engineering, which is a crucial step in the process of predictive modeling. The underlying relationship among multi-omics features in terms of insulin resistance is not well understood. In this study, using the multi-omics data of type II diabetes from the Integrative Human Microbiome Project, from 10,783 features, we conducted a data analytic approach to elucidate the relationship between insulin resistance and multi-omics features, including microbiome data. To better explain the impact of microbiome features on insulin classification, we used a developed deep neural network interpretation algorithm for each microbiome feature’s contribution to the discriminative model output in the samples.

Circulating microRNAs as clinically useful biomarkers for Type 2 Diabetes Mellitus: miRNomics from bench to bedside

“…16 For example, Huang et al adopted a multiomics approach based on clinical features, proteomic, cytokines profile, microbiome and RNA-seq in order to identify 17 parameters able to distinguish insulin resistant (IR) and insulin sensitive subjects. 17 Choi and colleagues 12 included miRNAs profiling and proteome analysis on plasma samples of obese insulin resistant and lean subjects alongside with clinical features. The authors observed that decreased miR-24-3p and miR-495-3p expression and increased IGFBP5 and glycerol-3-phosphate dehydrogenase 1 (GPD1) proteins, are associated to peripheral insulin sensitivity and significantly distinguished insulin resistant from insulin-sensitive subjects.…”