Abstract
Genomic variant interpretation is a critical step of the diagnostic procedure, often supported by the application of tools that may predict the damaging impact of each variant or provide a guidelines-based classification. We propose the application of Machine Learning methodologies, in particular Penalized Logistic Regression, to support variant classification and prioritization. Our approach combines ACMG/AMP guidelines for germline variant interpretation as well as variant annotation features and provides a probabilistic score of pathogenicity, thus supporting the prioritization and classification of variants that would be interpreted as uncertain by the ACMG/AMP guidelines. We compared different approaches in terms of variant prioritization and classification on different datasets, showing that our data-driven approach is able to solve more variant of uncertain significance (VUS) cases in comparison with guidelines-based approaches and in silico prediction tools.
Highlights
Genomic variant interpretation is a critical step of the diagnostic procedure, often supported by the application of tools that may predict the damaging impact of each variant or provide a guidelinesbased classification
While the first type of tools is mainly data-driven, meaning that they learn or infer knowledge from the huge amount of genomic data that have been published over the years, pathogenicity assessment has been standardized in 2015 in a set of rules made from ACMG/Association for Molecular Pathology (AMP) e xperts[1]
Automatic tools for pathogenicity assessment can be guidelines-based, i.e. they implement the ACMG/AMP guidelines in a software/web tool[14–17,19,20] or convert the ACMG/AMP guidelines in a probabilistic framework[21], or they could be data-driven, such as Machine Learning approaches trained to distinguish pathogenic from benign variations[26–28,30]
Summary
Genomic variant interpretation is a critical step of the diagnostic procedure, often supported by the application of tools that may predict the damaging impact of each variant or provide a guidelinesbased classification. Abbreviations ACMG American College of Medical Genetics and Genomics AMP American Association of Molecular Pathology ML Machine learning LR Logistic regression PS Pathogenicity score BS Bayesian score. In order to identify them, clinical laboratory geneticists often leverage on in silico functional tools that are able to assess protein variant intolerance, splicing or gene regulatory alterations[3]. Several of these prediction tools with different characteristics and scope have been developed so far[4–7]. To convey a standard procedure for the integration of all different sources of information in a variant interpretation pipeline, the American College of Medical Genetics and Genomics (ACMG), along with the Association for Molecular Pathology (AMP) published their guidelines in 20151. ACMG/ AMP criteria are hierarchically organized in groups of different levels of evidence to support pathogenic or Scientific Reports | (2022) 12:2517
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
