Spatiotemporal AI-based modeling of gene regulation and variant effects in the developing human brain using Seal.

Seal uncovers a significant burden of de novo regulatory variants in transient fetal excitatory neurons in autism, revealing cell-type- and stage-specific effects.

• Why it matters: Understanding how genetic variation influences gene regulation during human brain development is limited by data scarcity in transient cell types and stages, hindering insights into neuropsychiatric disorders.
• What they did: Seal, an interpretable AI transfer learning framework, models gene expression and variant effects across 26 regions, 30 cell types, and 7 developmental stages, providing mechanistic insights into regulatory architecture.
• The result: Applying Seal to autism genome data, it identifies a significant burden of de novo regulatory variants in fetal excitatory neurons, enabling a better understanding of developmental mechanisms underlying neuropsychiatric conditions.