Deep learning prediction of attention-deficit hyperactivity disorder in African Americans by copy number variation.

Current understanding of the underlying molecular network and mechanism for attention-deficit hyperactivity disorder (ADHD) is lacking and incomplete. Previous studies suggest that genomic structural variations play an important role in the pathogenesis of ADHD. For effective modeling, deep learning approaches have become a method of choice, with ability to predict the impact of genetic variations involving complicated mechanisms. In this study, we examined copy number variation in whole genome sequencing from 116 African Americans ADHD children and 408 African American controls. We divided the human genome into 150 regions, and the variation intensity in each region was applied as feature vectors for deep learning modeling to classify ADHD patients. The accuracy of deep learning for predicting ADHD diagnosis is consistently around 78% in a two-fold shuffle test, compared with ∼50% by traditional k-mean clustering methods. Additional whole genome sequencing data from 351 European Americans children, including 89 ADHD cases and 262 controls, were applied as independent validation using feature vectors obtained from the African American ethnicity analysis. The accuracy of ADHD labeling was lower in this setting (∼70-75%) but still above the results from traditional methods. The regions with highest weight overlapped with the previously reported ADHD-associated copy number variation regions, including genes such as GRM1 and GRM8, key drivers of metabotropic glutamate receptor signaling. A notable discovery is that structural variations in non-coding genomic (intronic/intergenic) regions show prediction weights that can be as high as prediction weight from variations in coding regions, results that were unexpected.

Food allergen triggers are increased in children with the TSLP risk allele and eosinophilic esophagitis.

OBJECTIVES: TSLP has been shown to be associated with eosinophilic esophagitis (EoE). Specifically, children with EoE often have the nucleotides AA or AG instead of GG at the single nucleotide polymorphism position RS3806932. Presently, the phenotypic characteristics in EoE children with the TSLP EoE risk allele are unknown. METHODS: A retrospective analysis was performed of all children with EoE who had TSLP genotyping at The Children's Hospital of Philadelphia from 2008-2014. EoE food allergen triggers, presence of atopic features, IgE mediated food allergy and skin prick testing results were reviewed. The number and type of EoE food allergen triggers were compared with genotype using chi-square analysis. Primary cell cultures from EoE patients with or without the risk allele were stimulated with ovalbumin and TSLP secretion was measured by ELISA. RESULTS: Fifty three of 309 patients were found to have no copies of the TSLP risk allele, whereas 256 patients were found to have one or more copies of the risk allele. There was an increase in the number of patients with three or more EoE food allergens among those who were either homozygous or heterozygous for the risk allele compared to those without the risk allele (P < 0.0001). This was independent of their atopic background. Primary cultures from patients homozygous for the risk allele had greater TSLP secretion than those isolated from heterozygous patients. CONCLUSIONS: The TSLP risk allele is associated with having multiple EoE food allergen triggers. This novel EoE genotypic-phenotypic correlation may guide future treatment for those with the TSLP risk allele.

Multi-ancestry genome-wide association study of 21,000 cases and 95,000 controls identifies new risk loci for atopic dermatitis.

Genetic association studies have identified 21 loci associated with atopic dermatitis risk predominantly in populations of European ancestry. To identify further susceptibility loci for this common, complex skin disease, we performed a meta-analysis of >15 million genetic variants in 21,399 cases and 95,464 controls from populations of European, African, Japanese and Latino ancestry, followed by replication in 32,059 cases and 228,628 controls from 18 studies. We identified ten new risk loci, bringing the total number of known atopic dermatitis risk loci to 31 (with new secondary signals at four of these loci). Notably, the new loci include candidate genes with roles in the regulation of innate host defenses and T cell function, underscoring the important contribution of (auto)immune mechanisms to atopic dermatitis pathogenesis.

Genetic polymorphisms and associated susceptibility to asthma.

As complex common diseases, asthma and allergic diseases are caused by the interaction of multiple genetic variants with a variety of environmental factors. Candidate-gene studies have examined the involvement of a very large list of genes in asthma and allergy, demonstrating a role for more than 100 loci. These studies have elucidated several themes in the biology and pathogenesis of these diseases. A small number of genes have been associated with asthma or allergy through traditional linkage analyses. The publication of the first asthma-focused genome-wide association (GWA) study in 2007 has been followed by nearly 30 reports of GWA studies targeting asthma, allergy, or associated phenotypes and quantitative traits. GWA studies have confirmed several candidate genes and have identified new, unsuspected, and occasionally uncharacterized genes as asthma susceptibility loci. Issues of results replication persist, complicating interpretation and making conclusions difficult to draw, and much of the heritability of these diseases remains undiscovered. In the coming years studies of complex diseases like asthma and allergy will probably involve the use of high-throughput next-generation sequencing, which will bring a tremendous influx of new information as well as new problems in dealing with vast datasets.

Pharmacogenetics and functional genomics in asthma.

Asthma is a complex phenotype caused by a combination of genetic and environmental factors that remain poorly understood. The common variants involved in the pathogenesis of asthma have proved difficult to identify by candidate gene association studies. As a result, few genetic variants influencing clinical response to asthma and allergy medications have been uncovered. Recently, genome-wide association, which is more robust in identifying common predisposition variants, has been applied to disorders such as asthma. As genome-wide associations are hypothesis-free, they raise the possibility of identifying novel biological pathways that could be translated to the future benefit of patients through improved diagnostic and therapeutic measures in the form of personalized medicine. This review addresses both recent advances in the genetics of asthma and their potential in transforming the treatment of the disorder into more individualized care in the near future.