.png){kind=icon}
.png){kind=icon}
Return
Sex-dependent prediction of autism
.png){kind=icon}
OA
AI
C
T
D
J
DOI：10.3389/fgene.2026.1799530.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
IntroductionAutism spectrum disorders (ASD) have a global prevalence of 1%; with a male-to- female diagnosis ratio of roughly 4:1. Several models have been developed to predict ASD using genetic information. However; the influence of biological sex on prediction outcomes remains underexplored.MethodsWe present an ensemble model to predict ASD; which integrates polygenic risk scores (PRSs); common genetic variants; and ASD risk genes with the MSSNG whole genome sequencing (WGS) dataset.ResultsFollowing training; our model achieved an accuracy of 0.68; an area under the receiver operating curve (AUROC) of 0.72; and a recall of 0.77 on the test dataset. Notably; common variants contributed more significantly to ASD prediction in males than females (p < 0.001); with accuracies of 0.69 and 0.66; respectively. The 16p11 locus emerged as particularly predictive for females (p < 0.001). Gene enrichment analysis using the Allen Brain Atlas revealed that expression of ASD risk genes that were significant in females were enriched (FWER < 0.05) in the primary somatosensory cortex; inferior parietal cortex; and parietal neocortex during fetal development. By contrast; male ASD risk gene expression was enriched (FWER < 0.05) in the dorsolateral prefrontal cortex and anterior cingulate cortex across developmental stages (fetal to adult).DiscussionThese findings underscore a sex-dependent role for common genetic variants in the risk of developing ASD. In doing so; they highlight the utility of ensemble models that incorporate common variation and biological sex for ASD prediction.
Keywords:
machine learning
autism
whole genome sequencing
common variants
sex-dependence
Journal
IF:
2.8
Papers:
1.4K
Citations:
4.4W
Organization
Cited Papers