Dataset Information

A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data.

ABSTRACT: BACKGROUND:Dementia with Lewy bodies (DLB) is the second most common subtype of neurodegenerative dementia in humans following Alzheimer's disease (AD). Present clinical diagnosis of DLB has high specificity and low sensitivity and finding potential biomarkers of prodromal DLB is still challenging. MicroRNAs (miRNAs) have recently received a lot of attention as a source of novel biomarkers. METHODS:In this study, using serum miRNA expression of 478 Japanese individuals, we investigated potential miRNA biomarkers and constructed an optimal risk prediction model based on several machine learning methods: penalized regression, random forest, support vector machine, and gradient boosting decision tree. RESULTS:The final risk prediction model, constructed via a gradient boosting decision tree using 180 miRNAs and two clinical features, achieved an accuracy of 0.829 on an independent test set. We further predicted candidate target genes from the miRNAs. Gene set enrichment analysis of the miRNA target genes revealed 6 functional genes included in the DHA signaling pathway associated with DLB pathology. Two of them were further supported by gene-based association studies using a large number of single nucleotide polymorphism markers (BCL2L1: P?=?0.012, PIK3R2: P?=?0.021). CONCLUSIONS:Our proposed prediction model provides an effective tool for DLB classification. Also, a gene-based association test of rare variants revealed that BCL2L1 and PIK3R2 were statistically significantly associated with DLB.

SUBMITTER: Shigemizu D

PROVIDER: S-EPMC6822471 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data.

Shigemizu Daichi D Akiyama Shintaro S Asanomi Yuya Y Boroevich Keith A KA Sharma Alok A Tsunoda Tatsuhiko T Sakurai Takashi T Ozaki Kouichi K Ochiya Takahiro T Niida Shumpei S

BMC medical genomics 20191030 1

<h4>Background</h4>Dementia with Lewy bodies (DLB) is the second most common subtype of neurodegenerative dementia in humans following Alzheimer's disease (AD). Present clinical diagnosis of DLB has high specificity and low sensitivity and finding potential biomarkers of prodromal DLB is still challenging. MicroRNAs (miRNAs) have recently received a lot of attention as a source of novel biomarkers.<h4>Methods</h4>In this study, using serum miRNA expression of 478 Japanese individuals, we investi ...[more]

PMID: 31666070

Similar Datasets

Project description:Dementia with Lewy bodies (DLB) is the second most common cause of degenerative dementia after Alzheimer’s disease (AD) and presents several overlapping pathological and clinical features with both AD and Parkinson’s disease (PD). Consequently, only one in three DLB cases is diagnosed correctly. Platelets are anucleate cells containing cellular structures and molecules, such as microRNA (miRNA), the analysis of which provides biomarkers for several disorders. In this cross-sectional study, we profiled the whole platelet miRNA transcriptome from 7 DLB patients and 7 healthy controls using Next-Generation Sequencing (NGS) and found 22 differentially expressed miRNAs. These miRNAs were further validated with miRCURY LNA miRNA Custom PCR panels in three consecutive validation studies carried out from 2017-2019 with a total of 162 individuals including DLB (n=59), AD (n=28), and PD patients (n=24), and healthy controls (n=51). As a result, three different groups of miRNAs were identified as related to DLB, AD and PD, all in comparison with controls. Additionally, our results demonstrated a significant down-regulation of hsa-miR-26b-5p and hsa-miR-150-5p in DLB compared to PD; and a signature composed of seven miRNAs that had lower expression in DLB compared to AD. The predictive diagnostic value of this bio-signature for the differentiation of DLB from AD was assessed calculating the corresponding ROC curve, which yielded an area under the curve of 1.00. Predictive analyses using specialized software (miRTarbase, miRGate) were performed for the disease-specific miRNAs to identify target genes and corresponding pathways. Three disease-specific clusters of pathways and biological processes were identified as a result of platelet-miRNA deregulation. In DLB, pathways related to gene expression and small RNA metabolism; in AD, pathways related to stress response and RNA stress granules; and in PD pathways related to protein phosphorylation, and protein metabolism and degradation were identified. In conclusion, we describe the identification of a novel, highly specific and sensitive platelet-associated miRNA-based bio-signature, which permits us to distinguish between DLB and AD.

Dataset Information

A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data.

Publications

A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure