Real life evaluation of AlphaMissense predictions in hematological malignancies.
Kaddour ChabaneCarole CharlotDan GugenheimThomas SimonetDavid ArmisenPierre-Julien ViaillyGuillaume Codet de BoisseSarah HuetSandrine HayetteVincent AlcazerPierre SujobertPublished in: Leukemia (2023)
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.
Keyphrases
- machine learning
- intellectual disability
- end stage renal disease
- high throughput sequencing
- ejection fraction
- newly diagnosed
- chronic kidney disease
- big data
- peritoneal dialysis
- prognostic factors
- electronic health record
- autism spectrum disorder
- copy number
- artificial intelligence
- emergency department
- patient reported outcomes
- adverse drug