Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism

Ray O. Bahado-Singh, Sangeetha Vishweswaraiah, Buket Aydas, Nitish K. Mishra, Ali Yilmaz, Chittibabu Guda, Uppala Radhakrishna

Research output: Contribution to journalArticle

Abstract

A great diversity of factors contribute to the pathogenesis of autism and autism spectrum disorder (ASD). Early detection is known to correlate with improved long term outcomes. There is therefore intense scientific interest in the pathogenesis of and early prediction of autism. Recent reports suggest that epigenetic alterations may play a vital role in disease pathophysiology. We conducted an epigenome-wide analysis of newborn leucocyte (blood spot) DNA in autism as defined at the time of sample collection. Our goal was to investigate the epigenetic basis of autism and identification of early biomarkers for disease prediction. Infinium HumanMethylation450 BeadChip assay was performed to measure DNA methylation level in 14 autism cases and 10 controls. The accuracy of cytosine methylation for autism detection using six different Machine Learning/Artificial Intelligence (AI) approaches including Deep-Learning (DL) was determined. Ingenuity Pathway Analysis (IPA) was further used to interrogate autism pathogenesis by identifying over-represented biological pathways. We found highly significant dysregulation of CpG methylation in 230 loci (249 genes). DL yielded an AUC (95% CI) = 1.00 (0.80–1.00) with 97.5% sensitivity and 100.0% specificity for autism detection. Epigenetic dysregulation was identified in several important candidate genes including some previously linked to autism development e.g.: EIF4E, FYN, SHANK1, VIM, LMX1B, GABRB1, SDHAP3 and PACS2. We observed significant enrichment of molecular pathways involved in neuroinflammation signaling, synaptic long term potentiation, serotonin degradation, mTOR signaling and signaling by Rho-Family GTPases. Our findings suggest significant epigenetic role in autism development and epigenetic markers appeared highly accurate for newborn prediction.

Original languageEnglish (US)
Article number146457
JournalBrain Research
Volume1724
DOIs
StatePublished - Dec 1 2019

Fingerprint

Artificial Intelligence
Autistic Disorder
Epigenomics
Leukocytes
Methylation
Eukaryotic Initiation Factor-4E
Learning
rho GTP-Binding Proteins
Long-Term Potentiation
Cytosine
DNA Methylation
Genes
Area Under Curve
Serotonin
Biomarkers
Sensitivity and Specificity

Keywords

  • Artificial intelligence
  • Autism
  • DNA methylation
  • Epigenetics
  • Newborns

ASJC Scopus subject areas

  • Neuroscience(all)
  • Molecular Biology
  • Clinical Neurology
  • Developmental Biology

Cite this

Bahado-Singh, R. O., Vishweswaraiah, S., Aydas, B., Mishra, N. K., Yilmaz, A., Guda, C., & Radhakrishna, U. (2019). Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism. Brain Research, 1724, [146457]. https://doi.org/10.1016/j.brainres.2019.146457

Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism. / Bahado-Singh, Ray O.; Vishweswaraiah, Sangeetha; Aydas, Buket; Mishra, Nitish K.; Yilmaz, Ali; Guda, Chittibabu; Radhakrishna, Uppala.

In: Brain Research, Vol. 1724, 146457, 01.12.2019.

Research output: Contribution to journalArticle

Bahado-Singh, RO, Vishweswaraiah, S, Aydas, B, Mishra, NK, Yilmaz, A, Guda, C & Radhakrishna, U 2019, 'Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism', Brain Research, vol. 1724, 146457. https://doi.org/10.1016/j.brainres.2019.146457
Bahado-Singh, Ray O. ; Vishweswaraiah, Sangeetha ; Aydas, Buket ; Mishra, Nitish K. ; Yilmaz, Ali ; Guda, Chittibabu ; Radhakrishna, Uppala. / Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism. In: Brain Research. 2019 ; Vol. 1724.
@article{8b8db55ef03147158e01dac249827b84,
title = "Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism",
abstract = "A great diversity of factors contribute to the pathogenesis of autism and autism spectrum disorder (ASD). Early detection is known to correlate with improved long term outcomes. There is therefore intense scientific interest in the pathogenesis of and early prediction of autism. Recent reports suggest that epigenetic alterations may play a vital role in disease pathophysiology. We conducted an epigenome-wide analysis of newborn leucocyte (blood spot) DNA in autism as defined at the time of sample collection. Our goal was to investigate the epigenetic basis of autism and identification of early biomarkers for disease prediction. Infinium HumanMethylation450 BeadChip assay was performed to measure DNA methylation level in 14 autism cases and 10 controls. The accuracy of cytosine methylation for autism detection using six different Machine Learning/Artificial Intelligence (AI) approaches including Deep-Learning (DL) was determined. Ingenuity Pathway Analysis (IPA) was further used to interrogate autism pathogenesis by identifying over-represented biological pathways. We found highly significant dysregulation of CpG methylation in 230 loci (249 genes). DL yielded an AUC (95{\%} CI) = 1.00 (0.80–1.00) with 97.5{\%} sensitivity and 100.0{\%} specificity for autism detection. Epigenetic dysregulation was identified in several important candidate genes including some previously linked to autism development e.g.: EIF4E, FYN, SHANK1, VIM, LMX1B, GABRB1, SDHAP3 and PACS2. We observed significant enrichment of molecular pathways involved in neuroinflammation signaling, synaptic long term potentiation, serotonin degradation, mTOR signaling and signaling by Rho-Family GTPases. Our findings suggest significant epigenetic role in autism development and epigenetic markers appeared highly accurate for newborn prediction.",
keywords = "Artificial intelligence, Autism, DNA methylation, Epigenetics, Newborns",
author = "Bahado-Singh, {Ray O.} and Sangeetha Vishweswaraiah and Buket Aydas and Mishra, {Nitish K.} and Ali Yilmaz and Chittibabu Guda and Uppala Radhakrishna",
year = "2019",
month = "12",
day = "1",
doi = "10.1016/j.brainres.2019.146457",
language = "English (US)",
volume = "1724",
journal = "Brain Research",
issn = "0006-8993",
publisher = "Elsevier",

}

TY - JOUR

T1 - Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism

AU - Bahado-Singh, Ray O.

AU - Vishweswaraiah, Sangeetha

AU - Aydas, Buket

AU - Mishra, Nitish K.

AU - Yilmaz, Ali

AU - Guda, Chittibabu

AU - Radhakrishna, Uppala

PY - 2019/12/1

Y1 - 2019/12/1

N2 - A great diversity of factors contribute to the pathogenesis of autism and autism spectrum disorder (ASD). Early detection is known to correlate with improved long term outcomes. There is therefore intense scientific interest in the pathogenesis of and early prediction of autism. Recent reports suggest that epigenetic alterations may play a vital role in disease pathophysiology. We conducted an epigenome-wide analysis of newborn leucocyte (blood spot) DNA in autism as defined at the time of sample collection. Our goal was to investigate the epigenetic basis of autism and identification of early biomarkers for disease prediction. Infinium HumanMethylation450 BeadChip assay was performed to measure DNA methylation level in 14 autism cases and 10 controls. The accuracy of cytosine methylation for autism detection using six different Machine Learning/Artificial Intelligence (AI) approaches including Deep-Learning (DL) was determined. Ingenuity Pathway Analysis (IPA) was further used to interrogate autism pathogenesis by identifying over-represented biological pathways. We found highly significant dysregulation of CpG methylation in 230 loci (249 genes). DL yielded an AUC (95% CI) = 1.00 (0.80–1.00) with 97.5% sensitivity and 100.0% specificity for autism detection. Epigenetic dysregulation was identified in several important candidate genes including some previously linked to autism development e.g.: EIF4E, FYN, SHANK1, VIM, LMX1B, GABRB1, SDHAP3 and PACS2. We observed significant enrichment of molecular pathways involved in neuroinflammation signaling, synaptic long term potentiation, serotonin degradation, mTOR signaling and signaling by Rho-Family GTPases. Our findings suggest significant epigenetic role in autism development and epigenetic markers appeared highly accurate for newborn prediction.

AB - A great diversity of factors contribute to the pathogenesis of autism and autism spectrum disorder (ASD). Early detection is known to correlate with improved long term outcomes. There is therefore intense scientific interest in the pathogenesis of and early prediction of autism. Recent reports suggest that epigenetic alterations may play a vital role in disease pathophysiology. We conducted an epigenome-wide analysis of newborn leucocyte (blood spot) DNA in autism as defined at the time of sample collection. Our goal was to investigate the epigenetic basis of autism and identification of early biomarkers for disease prediction. Infinium HumanMethylation450 BeadChip assay was performed to measure DNA methylation level in 14 autism cases and 10 controls. The accuracy of cytosine methylation for autism detection using six different Machine Learning/Artificial Intelligence (AI) approaches including Deep-Learning (DL) was determined. Ingenuity Pathway Analysis (IPA) was further used to interrogate autism pathogenesis by identifying over-represented biological pathways. We found highly significant dysregulation of CpG methylation in 230 loci (249 genes). DL yielded an AUC (95% CI) = 1.00 (0.80–1.00) with 97.5% sensitivity and 100.0% specificity for autism detection. Epigenetic dysregulation was identified in several important candidate genes including some previously linked to autism development e.g.: EIF4E, FYN, SHANK1, VIM, LMX1B, GABRB1, SDHAP3 and PACS2. We observed significant enrichment of molecular pathways involved in neuroinflammation signaling, synaptic long term potentiation, serotonin degradation, mTOR signaling and signaling by Rho-Family GTPases. Our findings suggest significant epigenetic role in autism development and epigenetic markers appeared highly accurate for newborn prediction.

KW - Artificial intelligence

KW - Autism

KW - DNA methylation

KW - Epigenetics

KW - Newborns

UR - http://www.scopus.com/inward/record.url?scp=85072262542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072262542&partnerID=8YFLogxK

U2 - 10.1016/j.brainres.2019.146457

DO - 10.1016/j.brainres.2019.146457

M3 - Article

VL - 1724

JO - Brain Research

JF - Brain Research

SN - 0006-8993

M1 - 146457

ER -