Abstract
Copy number variants (CNVs) have been shown to play a significant role in the pathogenesis of various human diseases. Although several tools have been developed for detecting CNVs based on whole-exome sequencing (WES) data, their performance remains suboptimal for small exon-level CNVs (exCNVs). This is primarily due to multiple technical variabilities, including probe capture efficiency, mappability, exon size, batch effects, experimental background noise bias, and control sample selection, all of which can lead to false negatives and false positives in exCNV detection. To address these challenges, we developed ML-ExonCNV, which innovatively integrates the XGBoost machine learning model with a multi-expert ensemble approach. The model was trained using 14 features derived from 22 364 real-world, quantitative polymerase chain reaction-validated rare exCNVs. Evaluation on a test set of 492 real WES and the NA12878 gold-standard dataset demonstrated that ML-ExonCNV outperformed widely used tools such as GATK-gCNV, ExomeDepth, and CNVkit. Notably, ML-ExonCNV can detect large segmental CNVs, mosaic CNVs, and breakpoint CNVs on exon region. Furthermore, our analysis revealed recurrent exCNV-associated genes and their phenotypic correlations. Neurodevelopmental and musculoskeletal abnormalities were identified as the most frequently associated phenotypes with high-recurrence exCNVs.