Artificial intelligence enables comprehensive genome interpretation and nomination of candidate diagnoses for rare genetic diseases

Francisco M De La Vega,Barry Moore,Matt Huentelman,Braden Boone,Vinodh Narayanan,Jeanette Mccarthy,Katrin Õunap,Erwin Frise,Casie A Genetti,B S Löscher ,Alan H Beggs,Catherine A Brownstein,Keri Ramsey,Shawn Levy ,Lucia Guidugli,Sander Pajusalu,Pankaj B Agrawal,Narayanan Veeraraghavan,Edgar Javier Hernández ,Terence C Wong ,Kiely N James ,André Franke ,Paul R Billings ,Shimul Chowdhury,Marcus Naymik,Mark Yandell,Martin G Reese,Stephen F Kingsmore

doi:10.1186/s13073-021-00965-0

Abstract

BackgroundClinical 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.MethodsWe 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.ResultsGEM 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.ConclusionsGEM 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.

Highlights

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
Fabric GEM (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 clinical natural language processing (CNLP)-derived phenotype descriptions
In 17 of 20 cases with diagnostic structural variants (SV), 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

Summary

Introduction

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. The translation of that knowledge, in conjunction with major improvements in WES and WGS and downstream analytical pipelines, has enabled increased rates of diagnosis, from about 10%, with single gene tests, to over 50% [4]. Clinical interpretation of genetic variants in the context of the patient’s phenotype remains largely manual and extremely labor-intensive, requiring highly trained expert input. This remains a major barrier to widespread adoption and contributes to continued low rates of genomic testing for patients with suspected genetic disorders despite strong evidence for diagnostic and clinical utility and cost effectiveness [8]

Objectives

Methods

Results

Conclusion