Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning

Dong Hoon Oh, Il Bin Kim, Seok Hyeon Kim, Dong Hyun Ahn

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

Objective: The aim of this study was to identify a transcriptomic signature that could be used to classify subjects with autism spectrum disorder (ASD) compared to controls on the basis of blood gene expression profiles. The gene expression profiles could ultimately be used as diagnostic biomarkers for ASD. Methods: We used the published microarray data (GSE26415) from the Gene Expression Omnibus database, which included 21 young adults with ASD and 21 age-And sex-matched unaffected controls. Nineteen differentially expressed probes were identified from a training dataset (n=26, 13 ASD cases and 13 controls) using the limma package in R language (adjusted p value 0.05) and were further analyzed in a test dataset (n=16, 8 ASD cases and 8 controls) using machine learning algorithms. Results: Hierarchical cluster analysis showed that subjects with ASD were relatively well-discriminated from controls. Based on the support vector machine and K-nearest neighbors analysis, validation of 19-DE probes with a test dataset resulted in an overall class prediction accuracy of 93.8% as well as a sensitivity and specificity of 100% and 87.5%, respectively. Conclusion: The results of our exploratory study suggest that the gene expression profiles identified from the peripheral blood samples of young adults with ASD can be used to identify a biological signature for ASD. Further study using a larger cohort and more homogeneous datasets is required to improve the diagnostic accuracy.

Original languageEnglish
Pages (from-to)47-52
Number of pages6
JournalClinical Psychopharmacology and Neuroscience
Volume15
Issue number1
DOIs
StatePublished - 2017 Jan 1

Fingerprint

Transcriptome
Young Adult
Autism Spectrum Disorder
Machine Learning
Cluster Analysis
Language
Biomarkers
Databases
Gene Expression
Sensitivity and Specificity
Datasets

Keywords

  • Autism spectrum disorder
  • Blood
  • Decision support techniques
  • Machine learning
  • Microarray analysis
  • Transcriptome

Cite this

@article{8383b5793d924f11a8321a140097a737,
title = "Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning",
abstract = "Objective: The aim of this study was to identify a transcriptomic signature that could be used to classify subjects with autism spectrum disorder (ASD) compared to controls on the basis of blood gene expression profiles. The gene expression profiles could ultimately be used as diagnostic biomarkers for ASD. Methods: We used the published microarray data (GSE26415) from the Gene Expression Omnibus database, which included 21 young adults with ASD and 21 age-And sex-matched unaffected controls. Nineteen differentially expressed probes were identified from a training dataset (n=26, 13 ASD cases and 13 controls) using the limma package in R language (adjusted p value 0.05) and were further analyzed in a test dataset (n=16, 8 ASD cases and 8 controls) using machine learning algorithms. Results: Hierarchical cluster analysis showed that subjects with ASD were relatively well-discriminated from controls. Based on the support vector machine and K-nearest neighbors analysis, validation of 19-DE probes with a test dataset resulted in an overall class prediction accuracy of 93.8{\%} as well as a sensitivity and specificity of 100{\%} and 87.5{\%}, respectively. Conclusion: The results of our exploratory study suggest that the gene expression profiles identified from the peripheral blood samples of young adults with ASD can be used to identify a biological signature for ASD. Further study using a larger cohort and more homogeneous datasets is required to improve the diagnostic accuracy.",
keywords = "Autism spectrum disorder, Blood, Decision support techniques, Machine learning, Microarray analysis, Transcriptome",
author = "Oh, {Dong Hoon} and Kim, {Il Bin} and Kim, {Seok Hyeon} and Ahn, {Dong Hyun}",
year = "2017",
month = "1",
day = "1",
doi = "10.9758/cpn.2017.15.1.47",
language = "English",
volume = "15",
pages = "47--52",
journal = "Clinical Psychopharmacology and Neuroscience",
issn = "1738-1088",
number = "1",

}

Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning. / Oh, Dong Hoon; Kim, Il Bin; Kim, Seok Hyeon; Ahn, Dong Hyun.

In: Clinical Psychopharmacology and Neuroscience, Vol. 15, No. 1, 01.01.2017, p. 47-52.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning

AU - Oh, Dong Hoon

AU - Kim, Il Bin

AU - Kim, Seok Hyeon

AU - Ahn, Dong Hyun

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Objective: The aim of this study was to identify a transcriptomic signature that could be used to classify subjects with autism spectrum disorder (ASD) compared to controls on the basis of blood gene expression profiles. The gene expression profiles could ultimately be used as diagnostic biomarkers for ASD. Methods: We used the published microarray data (GSE26415) from the Gene Expression Omnibus database, which included 21 young adults with ASD and 21 age-And sex-matched unaffected controls. Nineteen differentially expressed probes were identified from a training dataset (n=26, 13 ASD cases and 13 controls) using the limma package in R language (adjusted p value 0.05) and were further analyzed in a test dataset (n=16, 8 ASD cases and 8 controls) using machine learning algorithms. Results: Hierarchical cluster analysis showed that subjects with ASD were relatively well-discriminated from controls. Based on the support vector machine and K-nearest neighbors analysis, validation of 19-DE probes with a test dataset resulted in an overall class prediction accuracy of 93.8% as well as a sensitivity and specificity of 100% and 87.5%, respectively. Conclusion: The results of our exploratory study suggest that the gene expression profiles identified from the peripheral blood samples of young adults with ASD can be used to identify a biological signature for ASD. Further study using a larger cohort and more homogeneous datasets is required to improve the diagnostic accuracy.

AB - Objective: The aim of this study was to identify a transcriptomic signature that could be used to classify subjects with autism spectrum disorder (ASD) compared to controls on the basis of blood gene expression profiles. The gene expression profiles could ultimately be used as diagnostic biomarkers for ASD. Methods: We used the published microarray data (GSE26415) from the Gene Expression Omnibus database, which included 21 young adults with ASD and 21 age-And sex-matched unaffected controls. Nineteen differentially expressed probes were identified from a training dataset (n=26, 13 ASD cases and 13 controls) using the limma package in R language (adjusted p value 0.05) and were further analyzed in a test dataset (n=16, 8 ASD cases and 8 controls) using machine learning algorithms. Results: Hierarchical cluster analysis showed that subjects with ASD were relatively well-discriminated from controls. Based on the support vector machine and K-nearest neighbors analysis, validation of 19-DE probes with a test dataset resulted in an overall class prediction accuracy of 93.8% as well as a sensitivity and specificity of 100% and 87.5%, respectively. Conclusion: The results of our exploratory study suggest that the gene expression profiles identified from the peripheral blood samples of young adults with ASD can be used to identify a biological signature for ASD. Further study using a larger cohort and more homogeneous datasets is required to improve the diagnostic accuracy.

KW - Autism spectrum disorder

KW - Blood

KW - Decision support techniques

KW - Machine learning

KW - Microarray analysis

KW - Transcriptome

UR - http://www.scopus.com/inward/record.url?scp=85014027322&partnerID=8YFLogxK

U2 - 10.9758/cpn.2017.15.1.47

DO - 10.9758/cpn.2017.15.1.47

M3 - Article

VL - 15

SP - 47

EP - 52

JO - Clinical Psychopharmacology and Neuroscience

JF - Clinical Psychopharmacology and Neuroscience

SN - 1738-1088

IS - 1

ER -