Combinatorial approach for complex disorder prediction: Case study of neurodevelopmental disorders

Research output: Contribution to journalArticle

Abstract

Early prediction of complex disorders (e.g., autism and other neurodevelopmental disorders) is one of the fundamental goals of precision medicine and personalized genomics. An early prediction of complex disorders can improve the prognosis, increase the effectiveness of interventions and treatments, and enhance the life quality of affected patients. Considering the genetic heritability of neurodevelopmental disorders, we are proposing a novel framework for utilizing rare coding variation for early prediction of these disorders in subset of affected samples. We provide a combinatorial framework for addressing this problem, denoted as Odin (Oracle for DIsorder predictioN), to make a prediction for a small, yet significant, subset of affected cases while having very low false positive rate (FPR) prediction for unaffected samples. Odin also takes advantage of the available functional information (e.g., pairwise coex-pression of genes during brain development) to increase the prediction power beyond genes with recurrent variants. Application of our method accurately recovers an additional 8% of autism cases without any severe variant in known recurrent mutated genes with a <1% FPR. Furthermore, Odin predicted a set of 391 genes that severe variants in these genes can cause autism or other developmental delay disorders. Approaches such as the one presented in this paper are needed to translate the biomedical discoveries into actionable items by clinicians. Odin is publicly available at https://github.com/HormozdiariLab/Odin.

Original languageEnglish (US)
Pages (from-to)1483-1495
Number of pages13
JournalGenetics
Volume210
Issue number4
DOIs
StatePublished - Dec 1 2018

Fingerprint

Autistic Disorder
Genes
Developmental Disabilities
Precision Medicine
Genomics
Quality of Life
Neurodevelopmental Disorders
Brain

Keywords

  • Autism
  • Complex disorder
  • De novo mutation
  • Early disease prediction
  • Neurodevelopmental disorder
  • Rare coding variant

ASJC Scopus subject areas

  • Genetics

Cite this

Combinatorial approach for complex disorder prediction : Case study of neurodevelopmental disorders. / Huynh, Linh; Hormozdiari, Fereydoun.

In: Genetics, Vol. 210, No. 4, 01.12.2018, p. 1483-1495.

Research output: Contribution to journalArticle

@article{b43f0da3060a462eb7c196329cca9512,
title = "Combinatorial approach for complex disorder prediction: Case study of neurodevelopmental disorders",
abstract = "Early prediction of complex disorders (e.g., autism and other neurodevelopmental disorders) is one of the fundamental goals of precision medicine and personalized genomics. An early prediction of complex disorders can improve the prognosis, increase the effectiveness of interventions and treatments, and enhance the life quality of affected patients. Considering the genetic heritability of neurodevelopmental disorders, we are proposing a novel framework for utilizing rare coding variation for early prediction of these disorders in subset of affected samples. We provide a combinatorial framework for addressing this problem, denoted as Odin (Oracle for DIsorder predictioN), to make a prediction for a small, yet significant, subset of affected cases while having very low false positive rate (FPR) prediction for unaffected samples. Odin also takes advantage of the available functional information (e.g., pairwise coex-pression of genes during brain development) to increase the prediction power beyond genes with recurrent variants. Application of our method accurately recovers an additional 8{\%} of autism cases without any severe variant in known recurrent mutated genes with a <1{\%} FPR. Furthermore, Odin predicted a set of 391 genes that severe variants in these genes can cause autism or other developmental delay disorders. Approaches such as the one presented in this paper are needed to translate the biomedical discoveries into actionable items by clinicians. Odin is publicly available at https://github.com/HormozdiariLab/Odin.",
keywords = "Autism, Complex disorder, De novo mutation, Early disease prediction, Neurodevelopmental disorder, Rare coding variant",
author = "Linh Huynh and Fereydoun Hormozdiari",
year = "2018",
month = "12",
day = "1",
doi = "10.1534/genetics.118.301280",
language = "English (US)",
volume = "210",
pages = "1483--1495",
journal = "Genetics",
issn = "0016-6731",
publisher = "Genetics Society of America",
number = "4",

}

TY - JOUR

T1 - Combinatorial approach for complex disorder prediction

T2 - Case study of neurodevelopmental disorders

AU - Huynh, Linh

AU - Hormozdiari, Fereydoun

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Early prediction of complex disorders (e.g., autism and other neurodevelopmental disorders) is one of the fundamental goals of precision medicine and personalized genomics. An early prediction of complex disorders can improve the prognosis, increase the effectiveness of interventions and treatments, and enhance the life quality of affected patients. Considering the genetic heritability of neurodevelopmental disorders, we are proposing a novel framework for utilizing rare coding variation for early prediction of these disorders in subset of affected samples. We provide a combinatorial framework for addressing this problem, denoted as Odin (Oracle for DIsorder predictioN), to make a prediction for a small, yet significant, subset of affected cases while having very low false positive rate (FPR) prediction for unaffected samples. Odin also takes advantage of the available functional information (e.g., pairwise coex-pression of genes during brain development) to increase the prediction power beyond genes with recurrent variants. Application of our method accurately recovers an additional 8% of autism cases without any severe variant in known recurrent mutated genes with a <1% FPR. Furthermore, Odin predicted a set of 391 genes that severe variants in these genes can cause autism or other developmental delay disorders. Approaches such as the one presented in this paper are needed to translate the biomedical discoveries into actionable items by clinicians. Odin is publicly available at https://github.com/HormozdiariLab/Odin.

AB - Early prediction of complex disorders (e.g., autism and other neurodevelopmental disorders) is one of the fundamental goals of precision medicine and personalized genomics. An early prediction of complex disorders can improve the prognosis, increase the effectiveness of interventions and treatments, and enhance the life quality of affected patients. Considering the genetic heritability of neurodevelopmental disorders, we are proposing a novel framework for utilizing rare coding variation for early prediction of these disorders in subset of affected samples. We provide a combinatorial framework for addressing this problem, denoted as Odin (Oracle for DIsorder predictioN), to make a prediction for a small, yet significant, subset of affected cases while having very low false positive rate (FPR) prediction for unaffected samples. Odin also takes advantage of the available functional information (e.g., pairwise coex-pression of genes during brain development) to increase the prediction power beyond genes with recurrent variants. Application of our method accurately recovers an additional 8% of autism cases without any severe variant in known recurrent mutated genes with a <1% FPR. Furthermore, Odin predicted a set of 391 genes that severe variants in these genes can cause autism or other developmental delay disorders. Approaches such as the one presented in this paper are needed to translate the biomedical discoveries into actionable items by clinicians. Odin is publicly available at https://github.com/HormozdiariLab/Odin.

KW - Autism

KW - Complex disorder

KW - De novo mutation

KW - Early disease prediction

KW - Neurodevelopmental disorder

KW - Rare coding variant

UR - http://www.scopus.com/inward/record.url?scp=85058364835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058364835&partnerID=8YFLogxK

U2 - 10.1534/genetics.118.301280

DO - 10.1534/genetics.118.301280

M3 - Article

C2 - 30297454

AN - SCOPUS:85058364835

VL - 210

SP - 1483

EP - 1495

JO - Genetics

JF - Genetics

SN - 0016-6731

IS - 4

ER -