Detection of Pathogenic Variants With Germline Genetic Testing in Patients With Prostate Cancer and Melanoma | Dermatology | JN Learning | AMA Ed Hub [Skip to Content]
[Skip to Content Landing]

Detection of Pathogenic Variants With Germline Genetic Testing Using Deep Learning vs Standard Methods in Patients With Prostate Cancer and Melanoma

Educational Objective
To understand the evaluation of patients with cancer to identify pathogenic germline alterations.
1 Credit CME
Key Points

Question  In patients with cancer, is the detection of pathogenic germline genetic variation improved by incorporation of automated deep learning technology compared with standard methods?

Findings  In this cross-sectional analysis of 2 retrospectively collected convenience cohorts of patients with prostate cancer and melanoma, more pathogenic variants in 118 cancer-predisposition genes were found using deep learning technology compared with a standard genetic analysis method (198 vs 182 variants identified in 1072 patients with prostate cancer; 93 vs 74 variants identified in 1295 patients with melanoma).

Meaning  The number of cancer-predisposing pathogenic variants identified in patients with prostate cancer and melanoma depends partially on the automated approach used to analyze sequence data, but further research is needed to understand possible implications for clinical management and patient outcomes.

Abstract

Importance  Less than 10% of patients with cancer have detectable pathogenic germline alterations, which may be partially due to incomplete pathogenic variant detection.

Objective  To evaluate if deep learning approaches identify more germline pathogenic variants in patients with cancer.

Design, Setting, and Participants  A cross-sectional study of a standard germline detection method and a deep learning method in 2 convenience cohorts with prostate cancer and melanoma enrolled in the US and Europe between 2010 and 2017. The final date of clinical data collection was December 2017.

Exposures  Germline variant detection using standard or deep learning methods.

Main Outcomes and Measures  The primary outcomes included pathogenic variant detection performance in 118 cancer-predisposition genes estimated as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The secondary outcomes were pathogenic variant detection performance in 59 genes deemed actionable by the American College of Medical Genetics and Genomics (ACMG) and 5197 clinically relevant mendelian genes. True sensitivity and true specificity could not be calculated due to lack of a criterion reference standard, but were estimated as the proportion of true-positive variants and true-negative variants, respectively, identified by each method in a reference variant set that consisted of all variants judged to be valid from either approach.

Results  The prostate cancer cohort included 1072 men (mean [SD] age at diagnosis, 63.7 [7.9] years; 857 [79.9%] with European ancestry) and the melanoma cohort included 1295 patients (mean [SD] age at diagnosis, 59.8 [15.6] years; 488 [37.7%] women; 1060 [81.9%] with European ancestry). The deep learning method identified more patients with pathogenic variants in cancer-predisposition genes than the standard method (prostate cancer: 198 vs 182; melanoma: 93 vs 74); sensitivity (prostate cancer: 94.7% vs 87.1% [difference, 7.6%; 95% CI, 2.2% to 13.1%]; melanoma: 74.4% vs 59.2% [difference, 15.2%; 95% CI, 3.7% to 26.7%]), specificity (prostate cancer: 64.0% vs 36.0% [difference, 28.0%; 95% CI, 1.4% to 54.6%]; melanoma: 63.4% vs 36.6% [difference, 26.8%; 95% CI, 17.6% to 35.9%]), PPV (prostate cancer: 95.7% vs 91.9% [difference, 3.8%; 95% CI, –1.0% to 8.4%]; melanoma: 54.4% vs 35.4% [difference, 19.0%; 95% CI, 9.1% to 28.9%]), and NPV (prostate cancer: 59.3% vs 25.0% [difference, 34.3%; 95% CI, 10.9% to 57.6%]; melanoma: 80.8% vs 60.5% [difference, 20.3%; 95% CI, 10.0% to 30.7%]). For the ACMG genes, the sensitivity of the 2 methods was not significantly different in the prostate cancer cohort (94.9% vs 90.6% [difference, 4.3%; 95% CI, –2.3% to 10.9%]), but the deep learning method had a higher sensitivity in the melanoma cohort (71.6% vs 53.7% [difference, 17.9%; 95% CI, 1.82% to 34.0%]). The deep learning method had higher sensitivity in the mendelian genes (prostate cancer: 99.7% vs 95.1% [difference, 4.6%; 95% CI, 3.0% to 6.3%]; melanoma: 91.7% vs 86.2% [difference, 5.5%; 95% CI, 2.2% to 8.8%]).

Conclusions and Relevance  Among a convenience sample of 2 independent cohorts of patients with prostate cancer and melanoma, germline genetic testing using deep learning, compared with the current standard genetic testing method, was associated with higher sensitivity and specificity for detection of pathogenic variants. Further research is needed to understand the relevance of these findings with regard to clinical outcomes.

Sign in to take quiz and track your certificates

Buy This Activity

JN Learning™ is the home for CME and MOC from the JAMA Network. Search by specialty or US state and earn AMA PRA Category 1 CME Credit™ from articles, audio, Clinical Challenges and more. Learn more about CME/MOC

Article Information

Corresponding Author: Eliezer M. Van Allen, MD, Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, 360 Longwood Ave, LC9329, Boston, MA 02215 (eliezerm_vanallen@dfci.harvard.edu).

Accepted for Publication: October 6, 2020.

Author Contributions: Drs AlDubayan and Van Allen had full access to all of the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis.

Concept and design: AlDubayan, Conway, Al-Rubaish, Al-Sulaiman, Al-Ali, Taylor-Weiner, Van Allen.

Acquisition, analysis, or interpretation of data: AlDubayan, Conway, Camp, Witkowski, Kofman, Reardon, Han, Moore, Elmarakeby, Salari, Choudhry, Al-Sulaiman, Taylor-Weiner, Van Allen.

Drafting of the manuscript: AlDubayan, Conway, Camp, Han, Taylor-Weiner, Van Allen.

Critical revision of the manuscript for important intellectual content: AlDubayan, Conway, Witkowski, Kofman, Reardon, Moore, Elmarakeby, Salari, Choudhry, Al-Rubaish, Al-Sulaiman, Al-Ali, Taylor-Weiner, Van Allen.

Statistical analysis: AlDubayan, Conway, Camp, Kofman, Reardon, Han, Elmarakeby, Salari, Choudhry, Taylor-Weiner, Van Allen.

Obtained funding: AlDubayan, Van Allen.

Administrative, technical, or material support: Moore, Al-Rubaish, Al-Sulaiman, Al-Ali, Van Allen.

Supervision: AlDubayan, Taylor-Weiner, Van Allen.

Conflict of Interest Disclosures: Dr Moore reported receiving personal fees from Immunity Health. Dr Van Allen reported serving on advisory boards or as a consultant to Tango Therapeutics, Genome Medical, Invitae, Illumina, Manifold Bio, Monte Rosa Therapeutics, and Enara Bio; receiving personal fees from Invitae, Tango Therapeutics, Genome Medical, Ervaxx, Roche/Genentech, and Janssen; receiving research support from Novartis and Bristol-Myers Squibb; having equity in Tango Therapeutics, Genome Medical, Syapse, Enara Bio, Manifold Bio, and Microsoft; receiving travel reimbursement from Roche and Genentech; and filing institutional patents (for ERCC2 variants and chemotherapy response, chromatin variants and immunotherapy response, and methods for clinical interpretation). No other disclosures were reported.

Funding/Support: This work was supported by Conquer Cancer Foundation Career Development Award 13167 from the American Society of Clinical Oncology (awarded to Dr AlDubayan), Young Investigator Award 18YOUN02 from the Prostate Cancer Foundation (awarded to Dr AlDubayan), the Challenge Award from the PCF-V Foundation (awarded to Dr Van Allen), the Emerging Leader Award from the Mark Foundation (awarded to Dr Van Allen), grant R01CA222574 from the National Institutes of Health (awarded to Dr Van Allen), and grant 12-MED2224-46 (for science and technology) from King Abdulaziz City (awarded to Drs Al-Rubaish, Al-Sulaiman, and Al-Ali).

Role of the Funder/Sponsor: The funders/sponsors had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.

Additional Contributions: We thank all the individuals who participated in this study. We also thank Eric Banks, PhD (data sciences platform, Broad Institute of Massachusetts Institute of Technology and Harvard University; no compensation was received), for his valuable insight into the underlying model of the Genome Analysis Toolkit and for his comments on the results of this study. We also thank Jeff Kohlwes, MD, MPH (general internal medicine, University of California, San Francisco; no compensation was received), Aaron Neinstein, MD (endocrinology and clinical informatics, University of California, San Francisco; no compensation was received), and Tara Vijayan, MD (infectious disease, University of California, Los Angeles; no compensation was received), for their feedback on the content in the manuscript.

Additional Information: The results are based, in part, on data generated by the Cancer Genome Atlas managed by the National Cancer Institute and the National Human Genome Research Institute. Information about the Cancer Genome Atlas can be found at http://cancergenome.nih.gov. The raw sequence data can be obtained through dbGaP (https://www.ncbi.nlm.nih.gov/gap) or as described in the original articles (details appear in the Methods section). All software tools used in this study are publicly available.

References
1.
Rebbeck  TR , Friebel  T , Lynch  HT ,  et al.  Bilateral prophylactic mastectomy reduces breast cancer risk in BRCA1 and BRCA2 mutation carriers: the PROSE Study Group.   J Clin Oncol. 2004;22(6):1055-1062. doi:10.1200/JCO.2004.04.188PubMedGoogle ScholarCrossref
2.
AlDubayan  SH .  Leveraging clinical tumor-profiling programs to achieve comprehensive germline-inclusive precision cancer medicine.   JCO Precision Oncology. 2019;3:1-3. doi:10.1200/PO.19.00108Google ScholarCrossref
3.
Litton  JK , Rugo  HS , Ettl  J ,  et al.  Talazoparib in patients with advanced breast cancer and a germline BRCA mutation.   N Engl J Med. 2018;379(8):753-763. doi:10.1056/NEJMoa1802905PubMedGoogle ScholarCrossref
4.
Le  DT , Durham  JN , Smith  KN ,  et al.  Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade.   Science. 2017;357(6349):409-413. doi:10.1126/science.aan6733PubMedGoogle ScholarCrossref
5.
AlDubayan  SH , Pyle  LC , Gamulin  M ,  et al; Regeneron Genetics Center (RGC) Research Team.  Association of inherited pathogenic variants in checkpoint kinase 2 (CHEK2) with susceptibility to testicular germ cell tumors.   JAMA Oncol. 2019;5(4):514-522. doi:10.1001/jamaoncol.2018.6477PubMedGoogle ScholarCrossref
6.
Kemp  Z , Turnbull  A , Yost  S ,  et al.  Evaluation of cancer-based criteria for use in mainstream BRCA1 and BRCA2 genetic testing in patients with breast cancer.   JAMA Netw Open. 2019;2(5):e194428. doi:10.1001/jamanetworkopen.2019.4428PubMedGoogle Scholar
7.
AlDubayan  SH , Giannakis  M , Moore  ND ,  et al.  Inherited DNA-repair defects in colorectal cancer.   Am J Hum Genet. 2018;102(3):401-414. doi:10.1016/j.ajhg.2018.01.018PubMedGoogle ScholarCrossref
8.
Huang  K-L , Mashl  RJ , Wu  Y ,  et al; Cancer Genome Atlas Research Network.  Pathogenic germline variants in 10,389 adult cancers.   Cell. 2018;173(2):355-370.e14. doi:10.1016/j.cell.2018.03.039PubMedGoogle ScholarCrossref
9.
DePristo  MA , Banks  E , Poplin  R ,  et al.  A framework for variation discovery and genotyping using next-generation DNA sequencing data.   Nat Genet. 2011;43(5):491-498. doi:10.1038/ng.806PubMedGoogle ScholarCrossref
10.
Gurovich  Y , Hanani  Y , Bar  O ,  et al.  Identifying facial phenotypes of genetic disorders using deep learning.   Nat Med. 2019;25(1):60-64. doi:10.1038/s41591-018-0279-0PubMedGoogle ScholarCrossref
11.
Esteva  A , Robicquet  A , Ramsundar  B ,  et al.  A guide to deep learning in healthcare.   Nat Med. 2019;25(1):24-29. doi:10.1038/s41591-018-0316-zPubMedGoogle ScholarCrossref
12.
Wu  Y , Schuster  M , Chen  Z ,  et al. Google’s Neural Machine Translation system: bridging the gap between human and machine translation. Published September 26, 2016. Accessed October 13, 2020. https://arxiv.org/abs/1609.08144
13.
Poplin  R , Chang  P-C , Alexander  D ,  et al.  A universal SNP and small-indel variant caller using deep neural networks.   Nat Biotechnol. 2018;36(10):983-987. doi:10.1038/nbt.4235PubMedGoogle ScholarCrossref
14.
Armenia  J , Wankowicz  SAM , Liu  D ,  et al; PCF/SU2C International Prostate Cancer Dream Team.  The long tail of oncogenic drivers in prostate cancer.   Nat Genet. 2018;50(5):645-651. doi:10.1038/s41588-018-0078-zPubMedGoogle ScholarCrossref
15.
Poplin  R , Ruano-Rubio  V , DePristo  MA ,  et al.  Scaling accurate genetic variant discovery to tens of thousands of samples.  Accessed October 13, 2020. https://www.biorxiv.org/content/10.1101/201178v3
16.
Bohannan  ZS , Mitrofanova  A .  Calling variants in the clinic: informed variant calling decisions based on biological, clinical, and laboratory variables.   Comput Struct Biotechnol J. 2019;17:561-569. doi:10.1016/j.csbj.2019.04.002PubMedGoogle ScholarCrossref
17.
Lek  M , Karczewski  KJ , Minikel  EV ,  et al; Exome Aggregation Consortium.  Analysis of protein-coding genetic variation in 60,706 humans.   Nature. 2016;536(7616):285-291. doi:10.1038/nature19057PubMedGoogle ScholarCrossref
18.
Tennessen  JA , Bigham  AW , O’Connor  TD ,  et al; Broad GO; Seattle GO; NHLBI Exome Sequencing Project.  Evolution and functional impact of rare coding variation from deep sequencing of human exomes.   Science. 2012;337(6090):64-69. doi:10.1126/science.1219240PubMedGoogle ScholarCrossref
19.
Zook  JM , Chapman  B , Wang  J ,  et al.  Integrating human sequence data sets provides a resource of benchmark SNP and indel genotype calls.   Nat Biotechnol. 2014;32(3):246-251. doi:10.1038/nbt.2835PubMedGoogle ScholarCrossref
20.
Github website. Best practices for multi-sample variant calling with DeepVariant. Accessed July 3, 2020. https://github.com/google/deepvariant
21.
Geraldine_VdAuwera. GATK best practices for variant discovery in DNAseq: GATK forum. Published September 13, 2013. Accessed July 3, 2020. https://gatkforums.broadinstitute.org/gatk/discussion/3238/best-practices-for-variant-discovery-in-dnaseq
22.
Richards  S , Aziz  N , Bale  S ,  et al; ACMG Laboratory Quality Assurance Committee.  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):405-424. doi:10.1038/gim.2015.30PubMedGoogle ScholarCrossref
23.
Barnell  EK , Ronning  P , Campbell  KM ,  et al.  Standard operating procedure for somatic variant refinement of sequencing data with paired tumor and normal samples.   Genet Med. 2019;21(4):972-981. doi:10.1038/s41436-018-0278-zPubMedGoogle ScholarCrossref
24.
Robinson  JT , Thorvaldsdóttir  H , Wenger  AM , Zehir  A , Mesirov  JP .  Variant review with the integrative genomics viewer.   Cancer Res. 2017;77(21):e31-e34. doi:10.1158/0008-5472.CAN-17-0337PubMedGoogle ScholarCrossref
25.
Loveday  C , Turnbull  C , Ramsay  E ,  et al; Breast Cancer Susceptibility Collaboration (UK).  Germline mutations in RAD51D confer susceptibility to ovarian cancer.   Nat Genet. 2011;43(9):879-882. doi:10.1038/ng.893PubMedGoogle ScholarCrossref
26.
Ramus  SJ , Song  H , Dicks  E ,  et al; AOCS Study Group; Ovarian Cancer Association Consortium.  Germline mutations in the BRIP1, BARD1, PALB2, and NBN genes in women with ovarian cancer.   J Natl Cancer Inst. 2015;107(11):djv214. doi:10.1093/jnci/djv214PubMedGoogle Scholar
27.
Helgason  H , Rafnar  T , Olafsdottir  HS ,  et al.  Loss-of-function variants in ATM confer risk of gastric cancer.   Nat Genet. 2015;47(8):906-910. doi:10.1038/ng.3342PubMedGoogle ScholarCrossref
28.
Bausch  B , Schiavi  F , Ni  Y ,  et al; European-American-Asian Pheochromocytoma-Paraganglioma Registry Study Group.  Clinical characterization of the pheochromocytoma and paraganglioma susceptibility genes SDHA, TMEM127, MAX, and SDHAF2 for gene-informed prevention.   JAMA Oncol. 2017;3(9):1204-1212. doi:10.1001/jamaoncol.2017.0223PubMedGoogle ScholarCrossref
29.
National Comprehensive Cancer Network. NCCN guidelines for genetic/familial high-risk assessment: breast and ovarian. Accessed October 13, 2020. https://www.nccn.org/about/news/ebulletin/ebulletindetail.aspx?ebulletinid=535
30.
European Association for Study of Liver.  EASL clinical practice guidelines: Wilson’s disease.   J Hepatol. 2012;56(3):671-685. doi:10.1016/j.jhep.2011.11.007PubMedGoogle ScholarCrossref
31.
1000 Genomes Project Consortium.  A global reference for human genetic variation.   Nature. 2015;526(7571):68-74.Google ScholarCrossref
32.
Sherry  ST , Ward  M , Sirotkin  K .  dbSNP—database for single nucleotide polymorphisms and other classes of minor genetic variation.   Genome Res. 1999;9:677-679.Google Scholar
33.
Kobayashi  Y , Yang  S , Nykamp  K , Garcia  J , Lincoln  SE , Topper  SE .  Pathogenic variant burden in the ExAC database: an empirical approach to evaluating population data for clinical variant interpretation.   Genome Med. 2017;9(1):13. doi:10.1186/s13073-017-0403-7PubMedGoogle ScholarCrossref
34.
Karczewski  KJ , Francioli  LC , Tiao  G ,  et al. The mutational constraint spectrum quantified from variation in 141,456 humans. Accessed October 13, 2020. https://www.biorxiv.org/content/10.1101/531210v4
If you are not a JN Learning subscriber, you can either:
Subscribe to JN Learning for one year
Buy this activity
jn-learning_Modal_LoginSubscribe_Purchase
Close
If you are not a JN Learning subscriber, you can either:
Subscribe to JN Learning for one year
Buy this activity
jn-learning_Modal_LoginSubscribe_Purchase
Close
With a personal account, you can:
  • Access free activities and track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
Education Center Collection Sign In Modal Right
Close

Name Your Search

Save Search
Close
With a personal account, you can:
  • Track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
jn-learning_Modal_SaveSearch_NoAccess_Purchase
Close

Lookup An Activity

or

Close

My Saved Searches

You currently have no searches saved.

Close
With a personal account, you can:
  • Access free activities and track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
Education Center Collection Sign In Modal Right
Close