Artificial intelligence enables comprehensive genome interpretation and nomination of candidate diagnoses for rare genetic diseases.
Journal
Genome medicine
ISSN: 1756-994X
Titre abrégé: Genome Med
Pays: England
ID NLM: 101475844
Informations de publication
Date de publication:
14 10 2021
14 10 2021
Historique:
received:
22
03
2021
accepted:
27
08
2021
entrez:
14
10
2021
pubmed:
15
10
2021
medline:
22
2
2022
Statut:
epublish
Résumé
Clinical interpretation of genetic variants in the context of the patient's phenotype is becoming the largest component of cost and time expenditure for genome-based diagnosis of rare genetic diseases. Artificial intelligence (AI) holds promise to greatly simplify and speed genome interpretation by integrating predictive methods with the growing knowledge of genetic disease. Here we assess the diagnostic performance of Fabric GEM, a new, AI-based, clinical decision support tool for expediting genome interpretation. We benchmarked GEM in a retrospective cohort of 119 probands, mostly NICU infants, diagnosed with rare genetic diseases, who received whole-genome or whole-exome sequencing (WGS, WES). We replicated our analyses in a separate cohort of 60 cases collected from five academic medical centers. For comparison, we also analyzed these cases with current state-of-the-art variant prioritization tools. Included in the comparisons were trio, duo, and singleton cases. Variants underpinning diagnoses spanned diverse modes of inheritance and types, including structural variants (SVs). Patient phenotypes were extracted from clinical notes by two means: manually and using an automated clinical natural language processing (CNLP) tool. Finally, 14 previously unsolved cases were reanalyzed. GEM ranked over 90% of the causal genes among the top or second candidate and prioritized for review a median of 3 candidate genes per case, using either manually curated or CNLP-derived phenotype descriptions. Ranking of trios and duos was unchanged when analyzed as singletons. In 17 of 20 cases with diagnostic SVs, GEM identified the causal SVs as the top candidate and in 19/20 within the top five, irrespective of whether SV calls were provided or inferred ab initio by GEM using its own internal SV detection algorithm. GEM showed similar performance in absence of parental genotypes. Analysis of 14 previously unsolved cases resulted in a novel finding for one case, candidates ultimately not advanced upon manual review for 3 cases, and no new findings for 10 cases. GEM enabled diagnostic interpretation inclusive of all variant types through automated nomination of a very short list of candidate genes and disorders for final review and reporting. In combination with deep phenotyping by CNLP, GEM enables substantial automation of genetic disease diagnosis, potentially decreasing cost and expediting case review.
Sections du résumé
BACKGROUND
Clinical interpretation of genetic variants in the context of the patient's phenotype is becoming the largest component of cost and time expenditure for genome-based diagnosis of rare genetic diseases. Artificial intelligence (AI) holds promise to greatly simplify and speed genome interpretation by integrating predictive methods with the growing knowledge of genetic disease. Here we assess the diagnostic performance of Fabric GEM, a new, AI-based, clinical decision support tool for expediting genome interpretation.
METHODS
We benchmarked GEM in a retrospective cohort of 119 probands, mostly NICU infants, diagnosed with rare genetic diseases, who received whole-genome or whole-exome sequencing (WGS, WES). We replicated our analyses in a separate cohort of 60 cases collected from five academic medical centers. For comparison, we also analyzed these cases with current state-of-the-art variant prioritization tools. Included in the comparisons were trio, duo, and singleton cases. Variants underpinning diagnoses spanned diverse modes of inheritance and types, including structural variants (SVs). Patient phenotypes were extracted from clinical notes by two means: manually and using an automated clinical natural language processing (CNLP) tool. Finally, 14 previously unsolved cases were reanalyzed.
RESULTS
GEM ranked over 90% of the causal genes among the top or second candidate and prioritized for review a median of 3 candidate genes per case, using either manually curated or CNLP-derived phenotype descriptions. Ranking of trios and duos was unchanged when analyzed as singletons. In 17 of 20 cases with diagnostic SVs, GEM identified the causal SVs as the top candidate and in 19/20 within the top five, irrespective of whether SV calls were provided or inferred ab initio by GEM using its own internal SV detection algorithm. GEM showed similar performance in absence of parental genotypes. Analysis of 14 previously unsolved cases resulted in a novel finding for one case, candidates ultimately not advanced upon manual review for 3 cases, and no new findings for 10 cases.
CONCLUSIONS
GEM enabled diagnostic interpretation inclusive of all variant types through automated nomination of a very short list of candidate genes and disorders for final review and reporting. In combination with deep phenotyping by CNLP, GEM enables substantial automation of genetic disease diagnosis, potentially decreasing cost and expediting case review.
Identifiants
pubmed: 34645491
doi: 10.1186/s13073-021-00965-0
pii: 10.1186/s13073-021-00965-0
pmc: PMC8515723
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
153Subventions
Organisme : NICHD NIH HHS
ID : P50 HD105351
Pays : United States
Organisme : NICHD NIH HHS
ID : U54 HD090255
Pays : United States
Organisme : NHGRI NIH HHS
ID : R01 HG009141
Pays : United States
Organisme : NHGRI NIH HHS
ID : UM1 HG008900
Pays : United States
Informations de copyright
© 2021. The Author(s).
Références
Gut. 2016 Aug;65(8):1306-13
pubmed: 25994218
Am J Hum Genet. 2020 Sep 3;107(3):403-417
pubmed: 32755546
NPJ Genom Med. 2020 Aug 11;5:33
pubmed: 32821428
Am J Hum Genet. 2018 Jul 5;103(1):58-73
pubmed: 29961570
Genet Med. 2018 Dec;20(12):1635-1643
pubmed: 29790872
N Engl J Med. 2017 Nov 16;377(20):1909-1911
pubmed: 29141159
Am J Hum Genet. 2019 Sep 5;105(3):448-455
pubmed: 31491408
Genet Med. 2017 Feb;19(2):209-214
pubmed: 27441994
Nature. 2012 Nov 1;491(7422):56-65
pubmed: 23128226
Appl Clin Genet. 2016 Jul 11;9:93-100
pubmed: 27468247
Blood. 2018 Sep 20;132(12):1318-1331
pubmed: 29914977
J Clin Invest. 2015 Jan;125(1):456-7
pubmed: 25654555
Nat Rev Genet. 2017 Oct;18(10):599-612
pubmed: 28804138
Nat Genet. 2014 Sep;46(9):944-50
pubmed: 25086666
Nat Genet. 2012 Oct;44(10):1080-3
pubmed: 22961002
Genet Med. 2021 Apr;23(4):669-678
pubmed: 33402738
Eur J Hum Genet. 2019 May;27(5):747-759
pubmed: 30664714
Elife. 2019 Sep 24;8:
pubmed: 31549960
Nat Med. 2014 Dec;20(12):1410-1416
pubmed: 25329329
Brief Bioinform. 2022 Jul 18;23(4):
pubmed: 35753701
Gut. 2015 Dec;64(12):1889-97
pubmed: 25367873
Nature. 2015 Oct 1;526(7571):82-90
pubmed: 26367797
Hum Mutat. 2009 Sep;30(9):1267-77
pubmed: 19562689
Genome Biol. 2016 Jun 06;17(1):122
pubmed: 27268795
Nature. 2020 May;581(7809):434-443
pubmed: 32461654
Am J Hum Genet. 2020 Nov 5;107(5):942-952
pubmed: 33157007
Biol Psychiatry. 2020 Jan 15;87(2):100-112
pubmed: 31443933
J Mol Diagn. 2019 Jan;21(1):38-48
pubmed: 30577886
Nucleic Acids Res. 2016 Jan 4;44(D1):D862-8
pubmed: 26582918
JAMA. 2014 Nov 12;312(18):1870-9
pubmed: 25326635
Nat Methods. 2015 Sep;12(9):841-3
pubmed: 26192085
Sci Transl Med. 2019 Apr 24;11(489):
pubmed: 31019026
Bioinformatics. 2012 Oct 1;28(19):2520-2
pubmed: 22908215
Genome Res. 2014 Feb;24(2):340-8
pubmed: 24162188
Sci Transl Med. 2020 May 20;12(544):
pubmed: 32434849
NPJ Genom Med. 2018 Apr 4;3:10
pubmed: 29644095
Am J Hum Genet. 2010 May 14;86(5):749-64
pubmed: 20466091
Nature. 2016 Aug 17;536(7616):285-91
pubmed: 27535533
Hum Mol Genet. 2012 Oct 15;21(R1):R37-44
pubmed: 22962312
Cold Spring Harb Mol Case Stud. 2018 Jun 1;4(3):
pubmed: 29437776
Cold Spring Harb Mol Case Stud. 2018 Dec 17;4(6):
pubmed: 30559311
Nucleic Acids Res. 2010 Sep;38(16):e164
pubmed: 20601685
Genome Med. 2017 May 30;9(1):43
pubmed: 28554332
Hum Mol Genet. 2015 Dec 1;24(23):6614-23
pubmed: 26358773
Bioinformatics. 2016 Apr 15;32(8):1220-2
pubmed: 26647377
N Engl J Med. 2019 Jun 20;380(25):2478-2480
pubmed: 31216405
Mol Genet Genomic Med. 2017 Nov;5(6):678-691
pubmed: 29178646
Nat Methods. 2014 Sep;11(9):935-7
pubmed: 25086502
Bioinformatics. 2019 Oct 1;35(19):3559-3566
pubmed: 30843052
Brief Bioinform. 2016 Jul;17(4):713-27
pubmed: 26330577
Genome Med. 2019 Nov 19;11(1):70
pubmed: 31744524
Am J Hum Genet. 2013 Jul 11;93(1):6-18
pubmed: 23746549
Gut. 2015 Jan;64(1):66-76
pubmed: 24572142
Am J Hum Genet. 2019 Oct 3;105(4):719-733
pubmed: 31564432
Mol Genet Metab Rep. 2018 Mar 15;15:80-89
pubmed: 30009132
Nat Rev Genet. 2018 May;19(5):325
pubmed: 29456250
Genes (Basel). 2020 Apr 23;11(4):
pubmed: 32340307
Genet Med. 2020 Feb;22(2):362-370
pubmed: 31467448
Nat Genet. 2011 Aug 14;43(9):838-46
pubmed: 21841781
Genet Med. 2021 Apr;23(4):777-781
pubmed: 33244164
Eur J Gastroenterol Hepatol. 2018 Dec;30(12):1491-1496
pubmed: 30199474
JAMA. 2018 Dec 4;320(21):2199-2200
pubmed: 30398550
Am J Hum Genet. 2016 Oct 6;99(4):877-885
pubmed: 27666373
J Clin Invest. 2017 Nov 1;127(11):4090-4103
pubmed: 28972538
Nature. 2015 Oct 1;526(7571):68-74
pubmed: 26432245
Am J Hum Genet. 2014 Apr 3;94(4):599-610
pubmed: 24702956
Genome Med. 2010 Nov 26;2(11):84
pubmed: 21114804
BMC Bioinformatics. 2017 May 31;18(1):286
pubmed: 28569140
NPJ Genom Med. 2018 Jul 9;3:16
pubmed: 30002876
Cold Spring Harb Mol Case Stud. 2018 Dec 17;4(6):
pubmed: 30404926
Cold Spring Harb Mol Case Stud. 2017 Sep 1;3(5):
pubmed: 28550066
Nature. 2020 Jul;583(7814):96-102
pubmed: 32581362
Genet Med. 2016 Sep;18(9):906-13
pubmed: 26866580
Genome Res. 2011 Jun;21(6):974-84
pubmed: 21324876
Nat Med. 2019 Jan;25(1):44-56
pubmed: 30617339
Psychol Methods. 2019 Oct;24(5):539-556
pubmed: 30742472
Cold Spring Harb Mol Case Stud. 2016 Sep;2(5):a001008
pubmed: 27626066
Hum Mutat. 2014 Dec;35(12):1418-26
pubmed: 25205138
Nat Protoc. 2015 Dec;10(12):2004-15
pubmed: 26562621
Cold Spring Harb Mol Case Stud. 2017 Sep 1;3(5):
pubmed: 28864462
N Engl J Med. 2013 Oct 17;369(16):1502-11
pubmed: 24088041
Am J Hum Genet. 2018 Sep 6;103(3):319-327
pubmed: 30193136
Genome Res. 2011 Sep;21(9):1529-42
pubmed: 21700766
BMC Bioinformatics. 2018 Feb 20;19(1):57
pubmed: 29463208
Genet Med. 2019 Jul;21(7):1585-1593
pubmed: 30514889
Nat Commun. 2021 Jan 21;12(1):510
pubmed: 33479230
Am J Hum Genet. 2015 Jul 2;97(1):111-24
pubmed: 26119816
Curr Protoc Hum Genet. 2013 Oct 18;79:6.13.1-6.13.19
pubmed: 24510651
Nature. 2020 Oct;586(7831):749-756
pubmed: 33087929
Nucleic Acids Res. 2019 Jan 8;47(D1):D1038-D1043
pubmed: 30445645
FEBS Lett. 2020 Feb;594(4):717-727
pubmed: 31627256
Nat Rev Genet. 2002 Aug;3(8):601-10
pubmed: 12154383
Nature. 2021 Feb;590(7845):290-299
pubmed: 33568819
Nat Genet. 2016 Dec;48(12):1581-1586
pubmed: 27776117
JAMA. 2014 Mar 12;311(10):1035-45
pubmed: 24618965
Clin Genet. 2019 Aug;96(2):183-185
pubmed: 31236915