A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data.
Aged
Biomarkers
/ metabolism
Case-Control Studies
Dementia
/ complications
Female
Genetic Association Studies
Humans
Lewy Body Disease
/ complications
Machine Learning
Male
MicroRNAs
/ blood
Phosphatidylinositol 3-Kinases
/ genetics
Polymorphism, Single Nucleotide
Risk
Signal Transduction
/ genetics
bcl-X Protein
/ genetics
Dementia with Lewy bodies
Risk prediction model
Single nucleotide polymorphism
microRNAs
Journal
BMC medical genomics
ISSN: 1755-8794
Titre abrégé: BMC Med Genomics
Pays: England
ID NLM: 101319628
Informations de publication
Date de publication:
30 10 2019
30 10 2019
Historique:
received:
06
05
2019
accepted:
18
10
2019
entrez:
1
11
2019
pubmed:
2
11
2019
medline:
3
4
2020
Statut:
epublish
Résumé
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. 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. 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). 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.
Sections du résumé
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.
Identifiants
pubmed: 31666070
doi: 10.1186/s12920-019-0607-3
pii: 10.1186/s12920-019-0607-3
pmc: PMC6822471
doi:
Substances chimiques
BCL2L1 protein, human
0
Biomarkers
0
MicroRNAs
0
bcl-X Protein
0
phosphoinositol-3 kinase regulatory subunit 2, human
EC 2.7.1.-
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
150Références
Neurology. 2017 Jul 4;89(1):88-100
pubmed: 28592453
Oncogene. 2000 Apr 27;19(18):2212-23
pubmed: 10822371
Nucleic Acids Res. 2015 Jul 1;43(W1):W460-6
pubmed: 25977294
BMC Bioinformatics. 2011 Sep 19;12:372
pubmed: 21929786
JAMA. 2016 Dec 13;316(22):2402-2410
pubmed: 27898976
Ann Hematol. 2012 Apr;91(4):553-9
pubmed: 21987025
Nat Rev Genet. 2009 Jun;10(6):392-404
pubmed: 19434077
J Pharmacol Sci. 2010;114(3):269-75
pubmed: 20953120
PLoS One. 2014 Mar 20;9(3):e92549
pubmed: 24651836
Nucleic Acids Res. 2019 Jan 8;47(D1):D590-D595
pubmed: 30321428
Nucleic Acids Res. 2015 Jan;43(Database issue):D146-52
pubmed: 25378301
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Cancer Med. 2017 Jul;6(7):1627-1638
pubmed: 28544536
BMC Med Inform Decis Mak. 2010 Mar 22;10:16
pubmed: 20307319
Neuroimage Clin. 2014 Aug 28;6:115-25
pubmed: 25379423
J Neurol. 2010 Mar;257(3):359-66
pubmed: 19795154
Lancet Neurol. 2004 Jan;3(1):19-28
pubmed: 14693108
Int J Neuropsychopharmacol. 2015 Jul 28;19(2):null
pubmed: 26221005
PLoS One. 2013 Dec 10;8(12):e81901
pubmed: 24339978
IEEE Trans Pattern Anal Mach Intell. 2014 May;36(5):942-54
pubmed: 26353228
Brain Pathol. 2012 May;22(3):280-94
pubmed: 21929559
PLoS One. 2017 Aug 8;12(8):e0181426
pubmed: 28792503
Nat Biotechnol. 2015 Jan;33(1):10-1
pubmed: 25574621
Cancer Sci. 2016 Mar;107(3):326-34
pubmed: 26749252
BMC Bioinformatics. 2013 Sep 04;14:266
pubmed: 24006840
BMC Bioinformatics. 2019 Jan 23;20(1):49
pubmed: 30674277
PLoS One. 2011 Mar 30;6(3):e18388
pubmed: 21479190
Commun Biol. 2019 Feb 25;2:77
pubmed: 30820472
Nucleic Acids Res. 2017 Jan 4;45(D1):D353-D361
pubmed: 27899662
Nat Genet. 2013 Jun;45(6):580-5
pubmed: 23715323
Curr Genomics. 2009 May;10(3):154-68
pubmed: 19881909
Aging (Albany NY). 2016 Oct 28;8(12):3185-3208
pubmed: 27794564
Aging (Albany NY). 2011 Dec;3(12):1178-91
pubmed: 22184282
Alzheimers Res Ther. 2018 Feb 15;10(1):19
pubmed: 29448953
J Biol Chem. 2000 Jan 7;275(1):322-7
pubmed: 10617621
BMC Res Notes. 2009 May 19;2:89
pubmed: 19454029
IEEE Trans Neural Netw. 2001;12(2):181-201
pubmed: 18244377
Neuropharmacology. 2010 Mar-Apr;58(4-5):722-9
pubmed: 20045708
Trends Cancer. 2019 Apr;5(4):233-244
pubmed: 30961830
J Hum Genet. 2015 Oct;60(10):581-7
pubmed: 26108142
Am J Hum Genet. 2011 Jul 15;89(1):82-93
pubmed: 21737059
Lancet Neurol. 2017 May;16(5):390-398
pubmed: 28342649
Proc Natl Acad Sci U S A. 2008 Jul 29;105(30):10513-8
pubmed: 18663219
Nat Immunol. 2003 May;4(5):410-5
pubmed: 12719730
Nucleic Acids Res. 2018 Jan 4;46(D1):D971-D976
pubmed: 29036324
J Alzheimers Dis. 2008 May;14(1):27-41
pubmed: 18525125