Combinatorial Approach for Complex Disorder Prediction: Case Study of Neurodevelopmental Disorders. Issue 4 (8th October 2018)

• Record Type: Journal Article
• Authors: Huynh, Linh; Hormozdiari, Fereydoun
• Is Part Of: Genetics. Volume 210:Issue 4(2018)
• Page Start: 1483
• Page End: 1495
• Publication Date: 2018-10-08
• Subjects: Autism -- early disease prediction -- complex disorder -- neurodevelopmental disorder -- de novo mutation -- rare coding variant; Genetics -- Periodicals; 576.5
• DOI: 10.1534/genetics.118.301280
• Languages: English
• ISSNs: 0016-6731

Abstract

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 coexpression 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 .