Accurate Blood-Based Diagnostic Biosignatures for Alzheimer’s Disease via Automated Machine Learning

Abstract

Alzheimer’s disease (AD) is the most common form of neurodegenerative dementia and its timely diagnosis remains a major challenge in biomarker discovery. In the present study, we analyzed publicly available high-throughput low-sample -omics datasets from studies in AD blood, by the AutoML technology Just Add Data Bio (JADBIO), to construct accurate predictive models for use as diagnostic biosignatures. Considering data from AD patients and age–sex matched cognitively healthy individuals, we produced three best performing diagnostic biosignatures specific for the presence of AD: A. A 506-feature transcriptomic dataset from 48 AD and 22 controls led to a miRNA-based biosignature via Support Vector Machines with three miRNA predictors (AUC 0.975 (0.906, 1.000)), B. A 38,327-feature transcriptomic dataset from 134 AD and 100 controls led to six mRNA-based statistically equivalent signatures via Classification Random Forests with 25 mRNA predictors (AUC 0.846 (0.778, 0.905)) and C. A 9483-feature proteomic dataset from 25 AD and 37 controls led to a protein-based biosignature via Ridge Logistic Regression with seven protein predictors (AUC 0.921 (0.849, 0.972)). These performance metrics were also validated through the JADBIO pipeline confirming stability. In conclusion, using the automated machine learning tool JADBIO, we produced accurate predictive biosignatures extrapolating available low sample -omics data. These results offer options for minimally invasive blood-based diagnostic tests for AD, awaiting clinical validation based on respective laboratory assays. They also highlight the value of AutoML in biomarker discovery.

Deciphering the Methylation Landscape in Breast Cancer: Diagnostic and Prognostic Biosignatures through Automated Machine Learning

“…Revisiting a given experimental observation is scientifically essential for maximum conclusion extraction as new and powerful statistical and computational methods are introduced. Numerous bioinformatic studies analyzing high-dimensional datasets of various modalities [ 25 , 26 , 27 ] have produced significant knowledge for BrCa biology, whereas applications of ML approaches have recently become spearheads for building powerful classifiers with major advantages towards diagnostic clinical applications [ 9 , 28 , 29 ]. Here, our ambition has been to exploit genome-wide BrCa methylation datasets through bioinformatic analysis using readily available tools in order to identify DMGs, to reveal pathophysiological implications by functional analysis and most importantly to build accurate and simple predictive signatures by means of feature selection, to be exploited in personalized BrCa management.…”

“…JADBio has previously been successfully used to produce signatures for clinical applications such as the development of lung cancer between smokers [ 29 ] or suicide amongst depressive patients [ 30 ]. Only recently, by revisiting publicly available -omics datasets via JADBio, we were able to deliver accurate highly-performing blood-based predictive biosignatures in Alzheimer’s disease [ 28 ] and classifiers for metastatic BrCa based on novel circulating cell free DNA methylation patterns [ 9 ].…”

Methylation Status of Corticotropin-Releasing Factor (CRF) Receptor Genes in Colorectal Cancer

“…JADBio has previously been successfully used to produce signatures for clinical applications such as development of classifiers for metastatic BrCa based on novel ccfDNA methylation patterns [ 16 ], identification of risk of lung cancer in smokers [ 72 ] or suicide prediction among depressive patients [ 73 ]. Recently, by revisiting publicly available omics datasets via JADBio, we were able to deliver accurate highly-performing blood-based predictive biosignatures in Alzheimer’s disease [ 74 ] and in breast cancer [ 75 ].…”

Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances

“…It was identified that RF classifier predicts AD with more effectively. To identify the presence of AD, three different diagnostic biosignatures were produced in [64] and the performance metrics were validated through AutoML tool JADBIO. The produced biosignatures were based on blood miRNA, mRNA, and protein, respectively.…”