Integrative Whole Exome Sequencing and Machine Learning Analysis of MCPH1, ERCC2, CENPJ, and ERCC6 Variants in Pakistani Families with Primary Microcephaly

Background: Primary microcephaly (MCPH) is a genetically and clinically diverse condition characterized by small head size, structural brain abnormalities, and non-progressive intellectual impairment. To date, variations in 30 genes have been associated with MCPH. Objective: The study aims to identify the genetic variants of MCPH in the Pakistani population, where consanguineous marriages are common, and to explore the functional relationship of MCPH with other neurodevelopmental disorders (NDDs) such as autism spectrum disorder (ASD), intellectual disability (ID), and developmental delay (DD). Methods: Whole-exome sequencing (WES) and Sanger sequencing were applied to identify genetic variants in MCPH patients. The functional relationship between MCPH and other NDD genes was explored using DGH-GO software, employing hierarchical clustering. This cross-sectional study was conducted from September 2023 to October 2024. Results: We identified two novel variants, ERCC2 (c.2255G>A) and ERCC6 (c.1178C>T), and two already reported variants, MCPH1 (c.1254delT) and CENPJ (c.18delC). Machine learning analysis revealed a significant functional overlap between MCPH and other neurodevelopment disorders (NDDs), affected genes. Conclusion: Our study expands the mutational spectrum of MCPH and supports shared genetic etiology between MCPH and other NDDs. These findings provide a deeper understanding of the genetic underpinnings and comorbidities of MCPH, guiding future research toward effective therapeutic strategies.