Performance Evaluation of SpliceAI for the Prediction of Splicing of <i>NF1</i> Variants

• Main Authors: Changhee Ha, Jong-Won Kim, Ja-Hyun Jang
• Format: Article
• Language: English
• Published: MDPI AG 2021-08-01
• Series: Genes
• Subjects: neurofibromatosis type 1; <i>NF1</i>; SpliceAI; <i>in silico</i> prediction; splice variants
• Online Access: https://www.mdpi.com/2073-4425/12/9/1308

Neurofibromatosis type 1, characterized by neurofibromas and café-au-lait macules, is one of the most common genetic disorders caused by pathogenic <i>NF1</i> variants. Because of the high proportion of splicing mutations in <i>NF1</i>, identifying variants that alter splicing may be an essential issue for laboratories. Here, we investigated the sensitivity and specificity of SpliceAI, a recently introduced <i>in silico</i> splicing prediction algorithm in conjunction with other <i>in silico</i> tools. We evaluated 285 <i>NF1</i> variants identified from 653 patients. The effect on variants on splicing alteration was confirmed by complementary DNA sequencing followed by genomic DNA sequencing. For <i>in silico</i> prediction of splicing effects, we used SpliceAI, MaxEntScan (MES), and Splice Site Finder-like (SSF). The sensitivity and specificity of SpliceAI were 94.5% and 94.3%, respectively, with a cut-off value of Δ Score > 0.22. The area under the curve of SpliceAI was 0.975 (<i>p</i> < 0.0001). Combined analysis of MES/SSF showed a sensitivity of 83.6% and specificity of 82.5%. The concordance rate between SpliceAI and MES/SSF was 84.2%. SpliceAI showed better performance for the prediction of splicing alteration for <i>NF1</i> variants compared with MES/SSF. As a convenient web-based tool, SpliceAI may be helpful in clinical laboratories conducting DNA-based <i>NF1</i> sequencing.