Reassessment of the NF1 variants of unknown significance found during the 20-year activity of a genetics diagnostic laboratory

The Role of Artificial Intelligence in Identifying NF1 Gene Variants and Improving Diagnosis

Neurofibromatosis type 1 (NF1) is an autosomal dominant disorder caused by mutations in the NF1 gene, typically diagnosed during early childhood and characterized by significant phenotypic heterogeneity. Despite advancements in next-generation sequencing (NGS), the diagnostic process remains challenging due to the gene's complexity, high mutational burden, and frequent identification of variants of uncertain significance (VUS). This review explores the emerging role of artificial intelligence (AI) in enhancing NF1 variant detection, classification, and interpretation. A systematic literature search was conducted across PubMed, IEEE Xplore, Google Scholar, and ResearchGate to identify recent studies applying AI technologies to NF1 genetic analysis, focusing on variant interpretation, structural modeling, tumor classification, and therapeutic prediction. The review highlights the application of AI-based tools such as VEST3, REVEL, ClinPred, and NF1-specific models like DITTO and RENOVO-NF1, which have demonstrated improved accuracy in classifying missense variants and reclassifying VUS. Structural modeling platforms like AlphaFold contribute further insights into the impact of NF1 mutations on neurofibromin structure and function. In addition, deep learning models, such as LTC neural networks, support tumor classification and therapeutic outcome prediction, particularly in NF1-associated complications like congenital pseudarthrosis of the tibia (CPT). The integration of AI methodologies offers substantial potential to improve diagnostic precision, enable early intervention, and support personalized medicine approaches. However, key challenges remain, including algorithmic bias, limited data diversity, and the need for functional validation. Ongoing refinement and clinical validation of these tools are essential to ensure their effective implementation and equitable use in NF1 diagnostics.

Proteomic Profiling Towards a Better Understanding of Genetic Based Muscular Diseases: The Current Picture and a Look to the Future

Proteomics accelerates diagnosis and research of muscular diseases by enabling the robust analysis of proteins relevant for the manifestation of neuromuscular diseases in the following aspects: (i) evaluation of the effect of genetic variants on the corresponding protein, (ii) prediction of the underlying genetic defect based on the proteomic signature of muscle biopsies, (iii) analysis of pathophysiologies underlying different entities of muscular diseases, key for the definition of new intervention concepts, and (iv) patient stratification according to biochemical fingerprints as well as (v) monitoring the success of therapeutic interventions. This review presents-also through exemplary case studies-the various advantages of mass proteomics in the investigation of genetic muscle diseases, discusses technical limitations, and provides an outlook on possible future application concepts. Hence, proteomics is an excellent large-scale analytical tool for the diagnostic workup of (hereditary) muscle diseases and warrants systematic profiling of underlying pathophysiological processes. The steady development may allow to overcome existing limitations including a quenched dynamic range and quantification of different protein isoforms. Future directions may include targeted proteomics in diagnostic settings using not only muscle biopsies but also liquid biopsies to address the need for minimally invasive procedures.

Mutation analysis and clinical profile of South African patients with Neurofibromatosis type 1 (NF1) phenotype

Neurofibromatosis type 1 (NF1) is an autosomal dominant genetic condition with complete age-dependent penetrance, variable expressivity and a global prevalence of ∼1/3,000. It is characteriszed by numerous café-au-lait macules, skin freckling in the inguinal or axillary regions, Lisch nodules of the iris, optic gliomas, neurofibromas, and tumour predisposition. The diagnostic testing strategy for NF1 includes testing for DNA single nucleotide variants (SNVs), copy number variants (CNVs) as well as RNA analysis for deep intronic and splice variants, which can cumulatively identify the causative variant in 95% of patients. In the present study, NF1 patients were screened using a next-generation sequencing (NGS) assay targeting NF1 exons and intron/exon boundaries for SNV and NF1 multiple ligation-dependent probe amplification (MLPA) analysis for CNV detection. Twenty-six unrelated Southern African patients clinically suspected of having NF1, based on the clinical diagnostic criteria developed by the National Institute of Health (NIH), were included in the current study. A detection rate of 58% (15/26) was obtained, with SNVs identified in 80% (12/15) using a targeted gene panel and NF1 gene deletion in 20% (3/15) identified using MLPA. Ten patients (38%) had no variants identified, although they met NF1 diagnostic criteria. One VUS was identified in this study in a patient that met NF1 diagnostic criteria, however there was no sufficient information to classify variant as pathogenic. The clinical features of Southern African patients with NF1 are similar to that of the known NF1 phenotype, with the exception of a lower frequency of plexiform neurofibromas and a higher frequency of developmental/intellectual disability compared to other cohorts. This is the first clinical and molecular characterisation of a Southern African ancestry NF1 cohort using both next-generation sequencing and MLPA analysis. A significant number of patients remained without a diagnosis following DNA-level testing. The current study offers a potential molecular testing strategy for our low resource environment that could benefit a significant proportion of patients who previously only received a clinical diagnosis without molecular confirmation.

Genetic Basis of Breast and Ovarian Cancer: Approaches and Lessons Learnt from Three Decades of Inherited Predisposition Testing

Germline variants occurring in BRCA1 and BRCA2 give rise to hereditary breast and ovarian cancer (HBOC) syndrome, predisposing to breast, ovarian, fallopian tube, and peritoneal cancers marked by elevated incidences of genomic aberrations that correspond to poor prognoses. These genes are in fact involved in genetic integrity, particularly in the process of homologous recombination (HR) DNA repair, a high-fidelity repair system for mending DNA double-strand breaks. In addition to its implication in HBOC pathogenesis, the impairment of HR has become a prime target for therapeutic intervention utilizing poly (ADP-ribose) polymerase (PARP) inhibitors. In the present review, we introduce the molecular roles of HR orchestrated by BRCA1 and BRCA2 within the framework of sensitivity to PARP inhibitors. We examine the genetic architecture underneath breast and ovarian cancer ranging from high- and mid- to low-penetrant predisposing genes and taking into account both germline and somatic variations. Finally, we consider higher levels of complexity of the genomic landscape such as polygenic risk scores and other approaches aiming to optimize therapeutic and preventive strategies for breast and ovarian cancer.