Phenotypic Evaluation of Deep Learning Models for Classifying Germline Variant Pathogenicity

Overview

Journal NPJ Precis Oncol

Publisher Springer Nature

Specialty Oncology

Date 2024 Oct 19

PMID 39427061

Authors

Ryan D Chow

Katherine L Nathanson

Ravi B Parikh

Affiliations

Soon will be listed here.

Abstract

Deep learning models for predicting variant pathogenicity have not been thoroughly evaluated on real-world clinical phenotypes. Here, we apply state-of-the-art pathogenicity prediction models to hereditary breast cancer gene variants in UK Biobank participants. Model predictions for missense variants in BRCA1, BRCA2 and PALB2, but not ATM and CHEK2, were associated with breast cancer risk. However, deep learning models had limited clinical utility when specifically applied to variants of uncertain significance.

References

Venner E, Patterson K, Kalra D, Wheeler M, Chen Y, Kalla S . The frequency of pathogenic variation in the All of Us cohort reveals ancestry-driven disparities. Commun Biol. 2024; 7(1):174. PMC: 10876563. DOI: 10.1038/s42003-023-05708-y. View

Owens D, Davidson K, Krist A, Barry M, Cabana M, Caughey A . Risk Assessment, Genetic Counseling, and Genetic Testing for BRCA-Related Cancer: US Preventive Services Task Force Recommendation Statement. JAMA. 2019; 322(7):652-665. DOI: 10.1001/jama.2019.10987. View

Hanson H, Astiazaran-Symonds E, Amendola L, Balmana J, Foulkes W, James P . Management of individuals with germline pathogenic/likely pathogenic variants in CHEK2: A clinical practice resource of the American College of Medical Genetics and Genomics (ACMG). Genet Med. 2023; 25(10):100870. PMC: 10623578. DOI: 10.1016/j.gim.2023.100870. View

Chen Z, Chen J, Collins R, Guo Y, Peto R, Wu F . China Kadoorie Biobank of 0.5 million people: survey methods, baseline characteristics and long-term follow-up. Int J Epidemiol. 2011; 40(6):1652-66. PMC: 3235021. DOI: 10.1093/ije/dyr120. View

Dorling L, Carvalho S, Allen J, Gonzalez-Neira A, Luccarini C, Wahlstrom C . Breast Cancer Risk Genes - Association Analysis in More than 113,000 Women. N Engl J Med. 2021; 384(5):428-439. PMC: 7611105. DOI: 10.1056/NEJMoa1913948. View

Sohail M, Palma-Martinez M, Chong A, Quinto-Cortes C, Barberena-Jonas C, Medina-Munoz S . Mexican Biobank advances population and medical genomics of diverse ancestries. Nature. 2023; 622(7984):775-783. PMC: 10600006. DOI: 10.1038/s41586-023-06560-0. View

Boonen R, Vreeswijk M, van Attikum H . CHEK2 variants: linking functional impact to cancer risk. Trends Cancer. 2022; 8(9):759-770. DOI: 10.1016/j.trecan.2022.04.009. View

Cingolani P, Patel V, Coon M, Nguyen T, Land S, Ruden D . Using Drosophila melanogaster as a Model for Genotoxic Chemical Mutational Studies with a New Program, SnpSift. Front Genet. 2012; 3:35. PMC: 3304048. DOI: 10.3389/fgene.2012.00035. View

Richards S, Aziz N, Bale S, Bick D, Das S, Gastier-Foster J . Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med. 2015; 17(5):405-24. PMC: 4544753. DOI: 10.1038/gim.2015.30. View

10.

Hu C, Hart S, Gnanaolivu R, Huang H, Lee K, Na J . A Population-Based Study of Genes Previously Implicated in Breast Cancer. N Engl J Med. 2021; 384(5):440-451. PMC: 8127622. DOI: 10.1056/NEJMoa2005936. View

11.

Cingolani P, Platts A, Wang L, Coon M, Nguyen T, Wang L . A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3. Fly (Austin). 2012; 6(2):80-92. PMC: 3679285. DOI: 10.4161/fly.19695. View

12.

Auton A, Brooks L, Durbin R, Garrison E, Kang H, Korbel J . A global reference for human genetic variation. Nature. 2015; 526(7571):68-74. PMC: 4750478. DOI: 10.1038/nature15393. View

13.

Szustakowski J, Balasubramanian S, Kvikstad E, Khalid S, Bronson P, Sasson A . Advancing human genetics research and drug discovery through exome sequencing of the UK Biobank. Nat Genet. 2021; 53(7):942-948. DOI: 10.1038/s41588-021-00885-0. View

14.

Landrum M, Lee J, Riley G, Jang W, Rubinstein W, Church D . ClinVar: public archive of relationships among sequence variation and human phenotype. Nucleic Acids Res. 2013; 42(Database issue):D980-5. PMC: 3965032. DOI: 10.1093/nar/gkt1113. View

15.

Couch F, Nathanson K, Offit K . Two decades after BRCA: setting paradigms in personalized cancer care and prevention. Science. 2014; 343(6178):1466-70. PMC: 4074902. DOI: 10.1126/science.1251827. View

16.

Johnson R, Ding Y, Bhattacharya A, Knyazev S, Chiu A, Lajonchere C . The UCLA ATLAS Community Health Initiative: Promoting precision health research in a diverse biobank. Cell Genom. 2023; 3(1):100243. PMC: 9903668. DOI: 10.1016/j.xgen.2022.100243. View

17.

Dorling L, Carvalho S, Allen J, Parsons M, Fortuno C, Gonzalez-Neira A . Breast cancer risks associated with missense variants in breast cancer susceptibility genes. Genome Med. 2022; 14(1):51. PMC: 9116026. DOI: 10.1186/s13073-022-01052-8. View

18.

Brandes N, Goldman G, Wang C, Ye C, Ntranos V . Genome-wide prediction of disease variant effects with a deep protein language model. Nat Genet. 2023; 55(9):1512-1522. PMC: 10484790. DOI: 10.1038/s41588-023-01465-0. View

19.

Frazer J, Notin P, Dias M, Gomez A, Min J, Brock K . Disease variant prediction with deep generative models of evolutionary data. Nature. 2021; 599(7883):91-95. DOI: 10.1038/s41586-021-04043-8. View

20.

. Genomic data in the All of Us Research Program. Nature. 2024; 627(8003):340-346. PMC: 10937371. DOI: 10.1038/s41586-023-06957-x. View