In this idiopathic majority of ASD, the risk is likely associated with many inherited common and rare risk variants in each individual child. Thus, an estimated 80% or more of ASD individuals are considered ‘idiopathic’, wherein little is known about the genes and/or environmental factors causing their disorder. For 80–90% of patients, such mutations are not found. While syndromic risk mutations have been described for >200 genes in ASD, each occurs only rarely in ASD. Since ASD’s heritability is 81%, initial attempts have focused on genetics to develop clinically useful biomarkers for precision medicine and causal explanations for ASD pathogenesis. Thus, there is a need for early-age molecular diagnostics of ASD that robustly surmount this heterogeneity obstacle. Moreover, the heterogeneity of ASD genetics and clinical characteristics impose barriers to identifying early-age molecular diagnostics that accurately diagnose the majority of those with this heterogeneous disorder. The long delay between ASD’s prenatal onset and eventual diagnosis is a missed opportunity for treatment. Indeed, ASD diagnosis remains behavior-based and the median age of the first diagnosis remains at ~52 months, which is nearly 5 years after its first trimester origin. Despite this prenatal and strongly genetic beginning, robust and replicable early-age biological ASD diagnostic markers useful at the individual level have not been found. Our ensemble ASD gene expression classifier is diagnostically predictive and replicable across different toddler ages, races, and ethnicities out-performs a risk gene mutation classifier and has potential for clinical translation.ĪSD is a prenatal, highly heritable disorder that considerably impacts a child’s ability to perceive and react to social information. By contrast, the leukocyte ensemble gene expression classifier correctly diagnostically classified 88% of TD and ASD toddlers with ASD risk gene mutations. This DNA sequencing found about the same percentage of SFARI Level 1 and 2 ASD risk gene mutations in TD (12 of 105) as in ASD (13 of 112) toddlers, and classification based only on the presence of mutation in these risk genes performed at a chance level of 49%. We additionally collected targeted DNA sequencing smMIPs data on a subset of ASD risk genes from 217 of the 240 ASD and TD toddlers. Ensemble model feature genes were involved in cell cycle, inflammation/immune response, transcriptional gene regulation, cytokine response, and PI3K-AKT, RAS and Wnt signaling pathways. ASD toddlers with ensemble scores above and below the overall ASD ensemble mean of 0.723 (on a scale of 0 to 1) had similar diagnostic and psychometric scores, but those below this ASD ensemble mean had more prenatal risk events than TD toddlers. Weighted Bayesian model averaging of these 742 models yielded an ensemble classifier model with accurate performance in Training and Test gene expression datasets with ASD diagnostic classification AUC-ROC scores of 85–89% and AUC-PR scores of 84–92%. We found that 742 models had AUC-ROC ≥ 0.8 on both Training and Test sets. To identify gene expression ASD diagnostic classifiers, we developed 42,840 models composed of 3570 gene expression feature selection sets and 12 classification methods. Here we collected clinical, diagnostic, and leukocyte RNA data from 240 ASD and typically developing (TD) toddlers (175 toddlers for training and 65 for test). Accurate and clinically-translatable early-age diagnostics do not exist due to ASD genetic and clinical heterogeneity. Autism Spectrum Disorder (ASD) diagnosis remains behavior-based and the median age of diagnosis is ~52 months, nearly 5 years after its first-trimester origin.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |