A review of genetic variant databases and machine learning tools for predicting the pathogenicity of breast cancer

Knowledge of the genetics of human pain gained over the last decade from next-generation sequencing

Next-generation sequencing (NGS) technologies have revolutionized pain research by providing comprehensive insights into genetic variation across the genome. Recent studies have expanded the known spectrum of mutations in genes such as SCN9A and NTRK1, which are commonly mutated in hereditary sensory neuropathies. NGS has uncovered critical alternative splicing events and facilitated single-cell transcriptomics, revealing cellular heterogeneity within tissues. An NGS-based classifier predicted extremely high opioid requirements with 80 % accuracy, highlighting the importance of tailoring opioid therapy based on genetic profiles. Key genes such as GDF5, COL11A1, and TRPV1 have been linked to osteoarthritis risk and pain sensitivity, while HLA-DRB1, TNF, and P2X7 play critical roles in inflammation and pain modulation in rheumatoid arthritis. Innovative tools, such as an atlas of the somatosensory system in neuropathic pain, have been developed based on NGS data, focusing on the dorsal root and trigeminal ganglia. This approach allows the analysis of cellular changes during the development of chronic pain. In the study of rare variants, NGS outperforms single nucleotide variant candidate studies and classical genome-wide association approaches. The complex data generated by NGS enables integrated multi-omics approaches, allowing deeper exploration of the molecular and cellular basis of pain perception. In addition, the characterization of non-coding RNAs has opened new therapeutic avenues. NGS-based pain research faces challenges related to complex data analysis and interpretation of rare genetic variants with unknown biological functions. Nevertheless, NGS offers significant potential for improving personalized pain management and highlights the need for interdisciplinary collaboration to translate findings into clinical practice.

A graph neural network approach for accurate prediction of pathogenicity in multi-type variants

Accurate prediction of pathogenic variants in human disease-associated genes would have a profound effect on clinical decision-making; however, it remains a significant challenge due to the overwhelming number of these variants. We propose graph neural network for multimodal annotation-based pathogenicity prediction (GNN-MAP), a novel deep learning framework that effectively integrates multimodal annotations and similarity relationships among variants to predict the pathogenicity of multi-type variants. Trained on the ClinVar dataset, GNN-MAP exhibits superior predictive performance in internal validation and orthogonal test datasets, accurately predicting variant pathogenicity. Notably, GNN-MAP enables accurate prediction of the pathogenicity of rare variants and highly imbalanced datasets. Furthermore, it achieves high performance in the pathogenicity prediction of inherited retinal disease-specific variants, highlighting its effectiveness in disease-specific variant prediction. These findings suggest that the robust capability of GNN-MAP to predict pathogenicity across multiple variant types and datasets holds significant potential for applications in research and clinical settings.

AI-derived comparative assessment of the performance of pathogenicity prediction tools on missense variants of breast cancer genes

Single nucleotide variants (SNVs) can exert substantial and extremely variable impacts on various cellular functions, making accurate predictions of their consequences challenging, albeit crucial especially in clinical settings such as in oncology. Laboratory-based experimental methods for assessing these effects are time-consuming and often impractical, highlighting the importance of in-silico tools for variant impact prediction. However, the performance metrics of currently available tools on breast cancer missense variants from benchmarking databases have not been thoroughly investigated, creating a knowledge gap in the accurate prediction of pathogenicity. In this study, the benchmarking datasets ClinVar and HGMD were used to evaluate 21 Artificial Intelligence (AI)-derived in-silico tools. Missense variants in breast cancer genes were extracted from ClinVar and HGMD professional v2023.1. The HGMD dataset focused on pathogenic variants only, to ensure balance, benign variants for the same genes were included from the ClinVar database. Interestingly, our analysis of both datasets revealed variants across genes with varying penetrance levels like low and moderate in addition to high, reinforcing the value of disease-specific tools. The top-performing tools on ClinVar dataset identified were MutPred (Accuracy = 0.73), Meta-RNN (Accuracy = 0.72), ClinPred (Accuracy = 0.71), Meta-SVM, REVEL, and Fathmm-XF (Accuracy = 0.70). While on HGMD dataset they were ClinPred (Accuracy = 0.72), MetaRNN (Accuracy = 0.71), CADD (Accuracy = 0.69), Fathmm-MKL (Accuracy = 0.68), and Fathmm-XF (Accuracy = 0.67). These findings offer clinicians and researchers valuable insights for selecting, improving, and developing effective in-silico tools for breast cancer pathogenicity prediction. Bridging this knowledge gap contributes to advancing precision medicine and enhancing diagnostic and therapeutic approaches for breast cancer patients with potential implications for other conditions.

Incorporating functional genomics into the pathology-supported genetic testing framework implemented in South Africa: A future view of precision medicine for breast carcinomas

A pathology-supported genetic testing (PSGT) framework was established in South Africa to improve access to precision medicine for patients with breast carcinomas. Nevertheless, the frequent identification of variants of uncertain significance (VUSs) with the use of genome-scale next-generation sequencing has created a bottleneck in the return of results to patients. This review highlights the importance of incorporating functional genomics into the PSGT framework as a proposed initiative. Here, we explore various model systems and experimental methods available for conducting functional studies in South Africa to enhance both variant classification and clinical interpretation. We emphasize the distinct advantages of using in vitro, in vivo, and translational ex vivo models to improve the effectiveness of precision oncology. Moreover, we highlight the relevance of methodologies such as protein modelling and structural bioinformatics, multi-omics, metabolic activity assays, flow cytometry, cell migration and invasion assays, tube-formation assays, multiplex assays of variant effect, and database mining and machine learning models. The selection of the appropriate experimental approach largely depends on the molecular mechanism of the gene under investigation and the predicted functional effect of the VUS. However, before making final decisions regarding the pathogenicity of VUSs, it is essential to assess the functional evidence and clinical outcomes under current variant interpretation guidelines. The inclusion of a functional genomics infrastructure within the PSGT framework will significantly advance the reclassification of VUSs and enhance the precision medicine pipeline for patients with breast carcinomas in South Africa.