Dataset Information

Diagnostic Classification and Prognostic Prediction Using Common Genetic Variants in Autism Spectrum Disorder: Genotype-Based Deep Learning.

ABSTRACT:

Background

In the United States, about 3 million people have autism spectrum disorder (ASD), and around 1 out of 59 children are diagnosed with ASD. People with ASD have characteristic social communication deficits and repetitive behaviors. The causes of this disorder remain unknown; however, in up to 25% of cases, a genetic cause can be identified. Detecting ASD as early as possible is desirable because early detection of ASD enables timely interventions in children with ASD. Identification of ASD based on objective pathogenic mutation screening is the major first step toward early intervention and effective treatment of affected children.

Objective

Recent investigation interrogated genomics data for detecting and treating autism disorders, in addition to the conventional clinical interview as a diagnostic test. Since deep neural networks perform better than shallow machine learning models on complex and high-dimensional data, in this study, we sought to apply deep learning to genetic data obtained across thousands of simplex families at risk for ASD to identify contributory mutations and to create an advanced diagnostic classifier for autism screening.

Methods

After preprocessing the genomics data from the Simons Simplex Collection, we extracted top ranking common variants that may be protective or pathogenic for autism based on a chi-square test. A convolutional neural network-based diagnostic classifier was then designed using the identified significant common variants to predict autism. The performance was then compared with shallow machine learning-based classifiers and randomly selected common variants.

Results

The selected contributory common variants were significantly enriched in chromosome X while chromosome Y was also discriminatory in determining the identification of autistic individuals from nonautistic individuals. The ARSD, MAGEB16, and MXRA5 genes had the largest effect in the contributory variants. Thus, screening algorithms were adapted to include these common variants. The deep learning model yielded an area under the receiver operating characteristic curve of 0.955 and an accuracy of 88% for identifying autistic individuals from nonautistic individuals. Our classifier demonstrated a considerable improvement of ~13% in terms of classification accuracy compared to standard autism screening tools.

Conclusions

Common variants are informative for autism identification. Our findings also suggest that the deep learning process is a reliable method for distinguishing the diseased group from the control group based on the common variants of autism.

SUBMITTER: Wang H

PROVIDER: S-EPMC8060867 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially in the domain of computer vision. The application of deep learning to early detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention, as rapid progress in neuroimaging techniques has generated large-scale multimodal neuroimaging data. A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD was performed. A PubMed and Google Scholar search was used to identify deep learning papers on AD published between January 2013 and July 2018. These papers were reviewed, evaluated, and classified by algorithm and neuroimaging type, and the findings were summarized. Of 16 studies meeting full inclusion criteria, 4 used a combination of deep learning and traditional machine learning approaches, and 12 used only deep learning approaches. The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8% for AD classification and 83.7% for prediction of conversion from mild cognitive impairment (MCI), a prodromal stage of AD, to AD. Deep learning approaches, such as convolutional neural network (CNN) or recurrent neural network (RNN), that use neuroimaging data without pre-processing for feature selection have yielded accuracies of up to 96.0% for AD classification and 84.2% for MCI conversion prediction. The best classification performance was obtained when multimodal neuroimaging and fluid biomarkers were combined. Deep learning approaches continue to improve in performance and appear to hold promise for diagnostic classification of AD using multimodal neuroimaging data. AD research that uses deep learning is still evolving, improving performance by incorporating additional hybrid data types, such as-omics data, increasing transparency with explainable approaches that add knowledge of specific disease-related features and mechanisms.

Project description:Amygdala dysfunction has been implicated in numerous neurodevelopmental disorders, including autism spectrum disorder (ASD). Previous studies in mice and humans, respectively, have linked Pac1r/PAC1R function to social behavior and PTSD-susceptibility. Based on this connection to social and emotional processing and the central role played by the amygdala in ASD, we examined a putative role for PAC1R in social deficits in ASD and determined the pattern of gene expression in the developing mouse and human amygdala. We reveal that Pac1r/PAC1R is expressed in both mouse and human amygdala from mid-neurogenesis through early postnatal stages, critical time points when altered brain trajectories are hypothesized to unfold in ASD. We further find that parents of autistic children carrying a previously identified PTSD-risk genotype (CC) report greater reciprocal social deficits compared to those carrying the non-risk GC genotype. Additionally, by exploring resting-state functional connectivity differences in a subsample of the larger behavioral sample, we find higher functional connectivity between the amygdala and right middle temporal gyrus in individuals with the CC risk genotype. Thus, using multimodal approaches, our data reveal that the amygdala-expressed PAC1R gene may be linked to severity of ASD social phenotype and possible alterations in brain connectivity, therefore potentially acting as a modifier of amygdala-related phenotypes. Autism Res 2019, 12: 200-211 © 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: In this multimodal study across mouse and human, we examined expression patterns of Pac1r/PAC1R, a gene implicated in social behavior, and further explored whether a previously identified human PTSD-linked mutation in PAC1R can predict brain connectivity and social deficits in ASD. We find that PAC1R is highly expressed in the both the mouse and human amygdala. Furthermore, our human data suggest that PAC1R genotype is linked to severity of social deficits and functional amygdala connectivity in ASD.

Project description:Epileptic encephalopathies represent a particularly severe form of epilepsy, associated with cognitive and behavioral deficits, including impaired social-communication and restricted, repetitive behaviors that are the hallmarks of autism spectrum disorder (ASD). With the advent of next-generation sequencing, the genetic landscape of epileptic encephalopathies is growing and demonstrates overlap with genes separately implicated in ASD. However, many questions remain about this connection, including whether epileptiform activity itself contributes to the development of ASD symptomatology. In this review, we compiled a database of genes associated with both epileptic encephalopathy and ASD, limiting our purview to Mendelian disorders not including inborn errors of metabolism, and we focused on the connection between ASD and epileptic encephalopathy rather than epilepsy broadly. Our review has four goals: to (1) discuss the overlapping presentations of ASD and monogenic epileptic encephalopathies; (2) examine the impact of the epilepsy itself on neurocognitive features, including ASD, in monogenic epileptic encephalopathies; (3) outline many of the genetic causes responsible for both ASD and epileptic encephalopathy; (4) provide an illustrative example of a final common pathway that may be implicated in both ASD and epileptic encephalopathy. We demonstrate that autistic features are a common association with monogenic epileptic encephalopathies. Certain epileptic encephalopathy syndromes, like infantile spasms, are especially linked to the development of ASD. The connection between seizures themselves and neurobehavioral deficits in these monogenic encephalopathies remains open to debate. Finally, advances in genetics have revealed many genes that overlap in ties to both ASD and epileptic encephalopathy and that play a role in diverse central nervous system processes. Increased attention to the autistic features of monogenic epileptic encephalopathies is warranted for both researchers and clinicians alike.