IntSplice2: Prediction of the Splicing Effects of Intronic Single-Nucleotide Variants Using LightGBM Modeling.

Prediction of the effect of a single-nucleotide variant (SNV) in an intronic region on aberrant pre-mRNA splicing is challenging except for an SNV affecting the canonical GU/AG splice sites (ss). To predict pathogenicity of SNVs at intronic positions -50 (Int-50) to -3 (Int-3) close to the 3' ss, we developed light gradient boosting machine (LightGBM)-based IntSplice2 models using pathogenic SNVs in the human gene mutation database (HGMD) and ClinVar and common SNVs in dbSNP with 0.01 ≤ minor allelic frequency (MAF) < 0.50. The LightGBM models were generated using features representing splicing cis-elements. The average recall/sensitivity and specificity of IntSplice2 by fivefold cross-validation (CV) of the training dataset were 0.764 and 0.884, respectively. The recall/sensitivity of IntSplice2 was lower than the average recall/sensitivity of 0.800 of IntSplice that we previously made with support vector machine (SVM) modeling for the same intronic positions. In contrast, the specificity of IntSplice2 was higher than the average specificity of 0.849 of IntSplice. For benchmarking (BM) of IntSplice2 with IntSplice, we made a test dataset that was not used to train IntSplice. After excluding the test dataset from the training dataset, we generated IntSplice2-BM and compared it with IntSplice using the test dataset. IntSplice2-BM was superior to IntSplice in all of the seven statistical measures of accuracy, precision, recall/sensitivity, specificity, F1 score, negative predictive value (NPV), and matthews correlation coefficient (MCC). We made the IntSplice2 web service at https://www.med.nagoya-u.ac.jp/neurogenetics/IntSplice2.

Congenital myasthenic syndrome-associated agrin variants affect clustering of acetylcholine receptors in a domain-specific manner.

Congenital myasthenic syndromes (CMS) are caused by mutations in molecules expressed at the neuromuscular junction. We report clinical, structural, ultrastructural, and electrophysiologic features of 4 CMS patients with 6 heteroallelic variants in AGRN, encoding agrin. One was a 7.9-kb deletion involving the N-terminal laminin-binding domain. Another, c.4744G>A - at the last nucleotide of exon 26 - caused skipping of exon 26. Four missense mutations (p.S1180L, p.R1509W, p.G1675S, and p.Y1877D) expressed in conditioned media decreased AChR clusters in C2C12 myotubes. The agrin-enhanced phosphorylation of MuSK was markedly attenuated by p.Y1877D in the LG3 domain and moderately attenuated by p.R1509W in the LG1 domain but not by the other 2 mutations. The p.S1180L mutation in the SEA domain facilitated degradation of secreted agrin. The p.G1675S mutation in the LG2 domain attenuated anchoring of agrin to the sarcolemma by compromising its binding to heparin. Anchoring of agrin with p.R1509W in the LG1 domain was similarly attenuated. Mutations of agrin affect AChR clustering by enhancing agrin degradation or by suppressing MuSK phosphorylation and/or by compromising anchoring of agrin to the sarcolemma of the neuromuscular junction.