FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137777421> ?p ?o ?g. }

• W3137777421 endingPage "632.e9" @default.
• W3137777421 startingPage "611" @default.
• W3137777421 abstract "Reordering of start-lost, stop-lost, and in-frame indel variants in ACMG/AMP guidelinesExtraction of damaging stop-lost and in-frame indel variants based on existing knowledgePrediction of pathogenicity of start-lost variants by machine learningRefinement of clinical variant interpretation framework by a data-driven approach The American College of Medical Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP) guideline is an organized framework for interpretation of variant pathogenicity used widely in clinical genetics. To further refine this knowledge-based framework, the authors first point out that the classification of start-lost, stop-lost, and in-frame insertion and deletion (indel) variants in the ACMG/AMP guidelines is discordant with the average deleteriousness estimated from statistical analysis of large-scale population data. Subsequently, the authors show ways to extract deleterious subtypes of stop-lost and in-frame indel variants using existing tools and biological knowledge and develop a machine learning-based model predicting the pathogenicity of start-lost variants. These results are an example of how knowledge-based clinical genetics guidelines could be further refined with data-driven approaches. BackgroundAlthough the American College of Medical Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP) guidelines for variant interpretation are used widely in clinical genetics, there is room for improvement of these knowledge-based guidelines.MethodsStatistical assessment of average deleteriousness of start-lost, stop-lost, and in-frame insertion and deletion (indel) variants and extraction of deleterious subsets was performed, being informed by proportions of rare variants in the general population of the Genome Aggregation Database (gnomAD). A machine learning-based model scoring the pathogenicity of start-lost variants (the PoStaL model) was constructed by predicting possible translation initiation sites on transcripts by deep learning and training a random forest on known pathogenic and likely benign variants.FindingsThe proportion of rare variants was highest in stop-lost variants, followed by in-frame indels and start-lost variants, suggesting that the criteria in the ACMG/AMP guidelines assigning PVS (pathogenic very strong) to start-lost variants and PM (pathogenic moderate) to stop-lost and in-frame indel variants would not be appropriate. Regarding deleterious subsets, stop-lost variants introducing extensions of more than 30 amino acids and in-frame indels computationally predicted to be damaging are enriched for rare and known pathogenic variants. For start-lost variants, we developed the PoStaL model, which outperforms existing tools. We also provide comprehensive lists of the PoStaL scores for start-lost variants and the length of extended amino acids by stop-lost variants.ConclusionsOur study could contribute to refinement of the ACMG/AMP guidelines, provides resources for future investigation, and provides an example of how to improve knowledge-based frameworks by data-driven approaches.FundingThe study was supported by grants from the Japan Agency for Medical Research and Development (AMED) and the Japan Society for the Promotion of Science (JSPS). Although the American College of Medical Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP) guidelines for variant interpretation are used widely in clinical genetics, there is room for improvement of these knowledge-based guidelines. Statistical assessment of average deleteriousness of start-lost, stop-lost, and in-frame insertion and deletion (indel) variants and extraction of deleterious subsets was performed, being informed by proportions of rare variants in the general population of the Genome Aggregation Database (gnomAD). A machine learning-based model scoring the pathogenicity of start-lost variants (the PoStaL model) was constructed by predicting possible translation initiation sites on transcripts by deep learning and training a random forest on known pathogenic and likely benign variants. The proportion of rare variants was highest in stop-lost variants, followed by in-frame indels and start-lost variants, suggesting that the criteria in the ACMG/AMP guidelines assigning PVS (pathogenic very strong) to start-lost variants and PM (pathogenic moderate) to stop-lost and in-frame indel variants would not be appropriate. Regarding deleterious subsets, stop-lost variants introducing extensions of more than 30 amino acids and in-frame indels computationally predicted to be damaging are enriched for rare and known pathogenic variants. For start-lost variants, we developed the PoStaL model, which outperforms existing tools. We also provide comprehensive lists of the PoStaL scores for start-lost variants and the length of extended amino acids by stop-lost variants. Our study could contribute to refinement of the ACMG/AMP guidelines, provides resources for future investigation, and provides an example of how to improve knowledge-based frameworks by data-driven approaches." @default.
• W3137777421 created "2021-03-29" @default.
• W3137777421 creator A5040436106 @default.
• W3137777421 creator A5071402049 @default.
• W3137777421 creator A5085467135 @default.
• W3137777421 date "2021-05-01" @default.
• W3137777421 modified "2023-10-17" @default.
• W3137777421 title "Refinement of the clinical variant interpretation framework by statistical evidence and machine learning" @default.
• W3137777421 cites W1533942137 @default.
• W3137777421 cites W1964547306 @default.
• W3137777421 cites W1969381388 @default.
• W3137777421 cites W1980740976 @default.
• W3137777421 cites W1989621875 @default.
• W3137777421 cites W2001126413 @default.
• W3137777421 cites W2006617902 @default.
• W3137777421 cites W2042962536 @default.
• W3137777421 cites W2051978340 @default.
• W3137777421 cites W2059145105 @default.
• W3137777421 cites W2076357933 @default.
• W3137777421 cites W2089335658 @default.
• W3137777421 cites W2091605994 @default.
• W3137777421 cites W2094832220 @default.
• W3137777421 cites W2096791516 @default.
• W3137777421 cites W2101412130 @default.
• W3137777421 cites W2102619694 @default.
• W3137777421 cites W2106578986 @default.
• W3137777421 cites W2111326065 @default.
• W3137777421 cites W2140290389 @default.
• W3137777421 cites W2145187337 @default.
• W3137777421 cites W2152974197 @default.
• W3137777421 cites W2160995259 @default.
• W3137777421 cites W2167852161 @default.
• W3137777421 cites W2174602966 @default.
• W3137777421 cites W2225726427 @default.
• W3137777421 cites W2256016639 @default.
• W3137777421 cites W2306137721 @default.
• W3137777421 cites W2417483443 @default.
• W3137777421 cites W2520188071 @default.
• W3137777421 cites W2529263373 @default.
• W3137777421 cites W2560641002 @default.
• W3137777421 cites W2562038667 @default.
• W3137777421 cites W2588302396 @default.
• W3137777421 cites W2599110791 @default.
• W3137777421 cites W2604078450 @default.
• W3137777421 cites W2783019319 @default.
• W3137777421 cites W2801771300 @default.
• W3137777421 cites W2892391774 @default.
• W3137777421 cites W2905962174 @default.
• W3137777421 cites W2914278830 @default.
• W3137777421 cites W2948953603 @default.
• W3137777421 cites W2950890882 @default.
• W3137777421 cites W2951621382 @default.
• W3137777421 cites W2952728907 @default.
• W3137777421 cites W2955503846 @default.
• W3137777421 cites W3008726958 @default.
• W3137777421 cites W3029661147 @default.
• W3137777421 cites W3031073114 @default.
• W3137777421 cites W3100417366 @default.
• W3137777421 doi "https://doi.org/10.1016/j.medj.2021.02.003" @default.
• W3137777421 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35590234" @default.
• W3137777421 hasPublicationYear "2021" @default.
• W3137777421 type Work @default.
• W3137777421 sameAs 3137777421 @default.
• W3137777421 citedByCount "1" @default.
• W3137777421 countsByYear W31377774212023 @default.
• W3137777421 crossrefType "journal-article" @default.
• W3137777421 hasAuthorship W3137777421A5040436106 @default.
• W3137777421 hasAuthorship W3137777421A5071402049 @default.
• W3137777421 hasAuthorship W3137777421A5085467135 @default.
• W3137777421 hasBestOaLocation W31377774211 @default.
• W3137777421 hasConcept C104317684 @default.
• W3137777421 hasConcept C119054055 @default.
• W3137777421 hasConcept C135763542 @default.
• W3137777421 hasConcept C141231307 @default.
• W3137777421 hasConcept C153209595 @default.
• W3137777421 hasConcept C189206191 @default.
• W3137777421 hasConcept C2908647359 @default.
• W3137777421 hasConcept C41008148 @default.
• W3137777421 hasConcept C54355233 @default.
• W3137777421 hasConcept C555299818 @default.
• W3137777421 hasConcept C64474127 @default.
• W3137777421 hasConcept C70721500 @default.
• W3137777421 hasConcept C71924100 @default.
• W3137777421 hasConcept C86803240 @default.
• W3137777421 hasConcept C99454951 @default.
• W3137777421 hasConceptScore W3137777421C104317684 @default.
• W3137777421 hasConceptScore W3137777421C119054055 @default.
• W3137777421 hasConceptScore W3137777421C135763542 @default.
• W3137777421 hasConceptScore W3137777421C141231307 @default.
• W3137777421 hasConceptScore W3137777421C153209595 @default.
• W3137777421 hasConceptScore W3137777421C189206191 @default.
• W3137777421 hasConceptScore W3137777421C2908647359 @default.
• W3137777421 hasConceptScore W3137777421C41008148 @default.
• W3137777421 hasConceptScore W3137777421C54355233 @default.
• W3137777421 hasConceptScore W3137777421C555299818 @default.
• W3137777421 hasConceptScore W3137777421C64474127 @default.
• W3137777421 hasConceptScore W3137777421C70721500 @default.
• W3137777421 hasConceptScore W3137777421C71924100 @default.

• next