Detecting methylation signatures in neurodegenerative disease by density-based clustering of applications with reducing noise

Abstract

There have been numerous genetic and epigenetic datasets generated for the study of complex disease including neurodegenerative disease. However, analysis of such data often suffers from detecting the outliers of the samples, which subsequently affects the extraction of the true biological signals involved in the disease. To address this critical issue, we developed a novel framework for identifying methylation signatures using consecutive adaptation of a well-known outlier detection algorithm, density based clustering of applications with reducing noise (DBSCAN) followed by hierarchical clustering. We applied the framework to two representative neurodegenerative diseases, Alzheimer’s disease (AD) and Down syndrome (DS), using DNA methylation datasets from public sources (Gene Expression Omnibus, GEO accession ID: GSE74486). We first applied DBSCAN algorithm to eliminate outliers, and then used Limma statistical method to determine differentially methylated genes. Next, hierarchical clustering technique was applied to detect gene modules. Our analysis identified a methylation signature comprising 21 genes for AD and a methylation signature comprising 89 genes for DS, respectively. Our evaluation indicated that these two signatures could lead to high classification accuracy values (92% and 70%) for these two diseases. In summary, this framework will be useful to better detect outlier-free genetic and epigenetic signatures in various complex diseases and their developmental stages.

Phenotype clustering in health care: A narrative review for clinicians

“…Outlier insensitivity offers unique advantages for clustering tasks related to complex pathophysiologic processes like neurodegenerative disease. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm identified noisy features outside cluster density boundaries in the more than 20,000 gene vectors that represent neurodegenerative disease-associated methylation processes (Mallik and Zhao, 2020). Removing noisy features allowed identification of 229 differentially methylated genes associated with Alzheimer's disease, bringing focus and clarity to subsequent analyses.…”

Integrative multi-omics and systems bioinformatics in translational neuroscience: A data mining perspective

“…Another data mining study implemented a new computational framework, including the use of the DBSCAN algorithm and Limma statistical methods, to analyze GEO datasets and identified 21 and 89 differentially methylated genes for AD and Down syndrome respectively [ 41 ]. Their evaluation indicated high classification accuracy of these two methylation signatures with 92% for AD and 70% for Down syndrome.…”

“…Their evaluation indicated high classification accuracy of these two methylation signatures with 92% for AD and 70% for Down syndrome. Their framework is capable of detecting outlier-free epigenetic signatures in complex diseases, with applications to analyze various epigenetic signatures throughout disease pathogenesis [ 41 ]. Studies performing meta-analyses of epigenomic datasets have found differentially methylated genes in varying brain regions [ 41 ], as well as age-associated methylation patterns concurrent with epigenetic dysregulation observed in AD [ 42 ].…”

Potential Therapeutic Agents on Alzheimer's Disease through Molecular Docking and Molecular Dynamics Simulation Study of Plant‐Based Compounds

“…Current statistics reported that there are ∼55 million human individuals who suffer from AD and it is predicted to go up to 74.7 million individuals in 2030 and 131.5 million in 2050 [1,3] . AD is a complex neurodegenerative disease among all dementia that leads to loss of memory and other intelligible abilities [4,5] . Neuropathology of AD includes the abnormal formation of amyloid beta in the form of senile plaques and intracellular accumulation of hyperphosphorylated tau protein in the form of neurofibrillary tangles [6] .…”

“…[1,3] AD is a complex neurodegenerative disease among all dementia that leads to loss of memory and other intelligible abilities. [4,5] Neuropathology of AD includes the abnormal formation of amyloid beta in the form of senile plaques and intracellular accumulation of hyperphosphorylated tau protein in the form of neurofibrillary tangles. [6] An enormous amount of work has been carried out to understand the molecular mechanism and pathology of AD; still, it is unclear how AD progresses and what risk factors lead to the development of AD.…”