AI Article Synopsis
- High-throughput sequencing is crucial for diagnosing blood cancers, but understanding missense mutations is still difficult.
- This study used the AlphaMissense database to evaluate how well machine learning can help predict the effects of these mutations for better interpretation.
- Analysis of 2073 variants from 686 patients showed that AlphaMissense predictions were highly accurate (AUC of ROC curve 0.95) and highlighted discrepancies with current clinical interpretation methods.
Article Abstract
High-throughput sequencing plays a pivotal role in hematological malignancy diagnostics, but interpreting missense mutations remains challenging. In this study, we used the newly available AlphaMissense database to assess the efficacy of machine learning to predict missense mutation effects and its impact to improve our ability to interpret them. Based on the analysis of 2073 variants from 686 patients analyzed for clinical purpose, we confirmed the very high accuracy of AlphaMissense predictions in a large real-life data set of missense mutations (AUC of ROC curve 0.95), and provided a comprehensive analysis of the discrepancies between AlphaMissense predictions and state of the art clinical interpretation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1038/s41375-023-02116-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
GeniePool 2.0: advancing variant analysis through CHM13-T2T, AlphaMissense, gnomAD V4 integration, and variant co-occurrence queries.
Database (Oxford)
December 2024
The Morris Kahn Laboratory of Human Genetics at the National Institute of Biotechnology in the Negev and Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer Sheva 84105, Israel.
Originally developed to meet the challenges of genomic data deluge, GeniePool emerged as a pioneering platform, enabling efficient storage, accessibility, and analysis of vast genomic datasets, enabled due to its data lake architecture. Building on this foundation, GeniePool 2.0 advances genomic analysis through the integration of cutting-edge variant databases, such as CHM13-T2T, AlphaMissense, and gnomAD V4, coupled with the capability for variant co-occurrence queries.
View Article and Find Full Text PDFComprehensive evaluation of AlphaMissense predictions by evidence quantification for variants of uncertain significance.
Front Genet
December 2024
Genomenon, Ann Arbor, MI, United States.
Accurate variant classification is critical for genetic diagnosis. Variants without clear classification, known as "variants of uncertain significance" (VUS), pose a significant diagnostic challenge. This study examines AlphaMissense performance in variant classification, specifically for VUS.
View Article and Find Full Text PDFMaking sense of missense: challenges and opportunities in variant pathogenicity prediction.
Dis Model Mech
December 2024
The Steve and Cindy Rasmussen Institute for Genomic Medicine, Abigail Wexner Research Institute at Nationwide Children's Hospital, Columbus, OH 43215, USA.
Computational tools for predicting variant pathogenicity are widely used to support clinical variant interpretation. Recently, several models, which do not rely on known variant classifications during training, have been developed. These approaches can potentially overcome biases of current clinical databases, such as misclassifications, and can potentially better generalize to novel, unclassified variants.
View Article and Find Full Text PDFGPTrans: A Biological Language Model-Based Approach for Predicting Disease-Associated Mutations in G Protein-Coupled Receptors.
J Chem Inf Model
December 2024
State Key Laboratory of Organic Electronics and Information Displays & Institute of Advanced Materials (IAM), Nanjing University of Posts & Telecommunications, 9 Wenyuan Road, Nanjing 210023, China.
Accurately predicting mutations in G protein-coupled receptors (GPCRs) is critical for advancing disease diagnosis and drug discovery. In response to this imperative, GPTrans has emerged as a highly accurate predictor of disease-related mutations in GPCRs. The core innovation of GPTrans resides in the design of a novel feature extraction network, that is capable of integrating features from both wildtype and mutant protein variant sites, utilizing multifeature connections within a transformer framework to ensure comprehensive feature extraction.
View Article and Find Full Text PDFAssessing the Utility of ColabFold and AlphaMissense in Determining Missense Variant Pathogenicity for Congenital Myasthenic Syndromes.
Biomedicines
November 2024
Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford OX3 9DS, UK.
Background/objectives: Congenital myasthenic syndromes (CMSs) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next-generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagnosis and treatment initiation. The recently developed protein structure prediction software AlphaFold2/ColabFold has revolutionized structural biology; such predictions have also been leveraged in AlphaMissense, which predicts ClinVar variant pathogenicity with 90% accuracy.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!