Related Experiment Video
Updated: May 30, 2025
07:15
Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation
Published on: January 16, 2019
10.9K
Noncoding variants and sulcal patterns in congenital heart disease: Machine learning to predict functional impact
Enrique Mondragon-Estrada1,2, Jane W Newburger3,4, Steven R DePalma5
1Division of Newborn Medicine, Department of Pediatrics, Boston Children's Hospital, Boston, MA, USA.
Iscience
|January 29, 2025
Summary
Noncoding variants may disrupt brain development in congenital heart disease (CHD). Deep learning identified variants affecting gene regulation, linked to altered sulcal patterns in the CHD group, suggesting a role in neurodevelopmental impairments.
Area of Science:
- Genetics
- Neuroscience
- Developmental Biology
Background:
- Congenital heart disease (CHD) is linked to neurodevelopmental impairments.
- Brain sulcal pattern formation is crucial for neurodevelopment.
- The role of noncoding de novo variants (ncDNVs) in CHD-associated brain development is unclear.
Purpose of the Study:
- To investigate the association between ncDNVs and sulcal patterns in individuals with CHD.
- To leverage deep learning to predict the functional impact of ncDNVs on gene regulation.
Main Methods:
- Deep learning models predicted the impact of ncDNVs on gene regulatory signals.
- Predicted impacts were compared between CHD and non-CHD cohorts.
- The relationship between predicted ncDNV impact and sulcal folding patterns was assessed.
Main Results:
- ncDNVs predicted to increase H3K9me2 modification correlated with greater disruption in right parietal sulcal patterns in the CHD cohort.
- Genes targeted by these ncDNVs showed enrichment for neuronal development functions.
Conclusions:
- Deep learning can identify potential roles for noncoding variants in brain development.
- ncDNVs impacting H3K9me2 may contribute to neurodevelopmental alterations in CHD.
- This study provides a framework for investigating noncoding variant effects in neurodevelopment.
