Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 15;13(20):e036921.
doi: 10.1161/JAHA.124.036921. Epub 2024 Oct 11.

Performance of a Protein Language Model for Variant Annotation in Cardiac Disease

Aviram Hochstadt  1 , Chirag Barbhaiya  1 , Anthony Aizer  1 , Scott Bernstein  1 , Marina Cerrone  1 , Leonid Garber  1 , Douglas Holmes  1 , Robert J Knotts  1 , Alex Kushnir  1 , Jacob Martin  1 , David Park  1 , Michael Spinelli  1 , Felix Yang  1 , Larry A Chinitz  1 , Lior Jankelson  1
Affiliations

Performance of a Protein Language Model for Variant Annotation in Cardiac Disease

Aviram Hochstadt et al. J Am Heart Assoc. .

Abstract

Background: Genetic testing is a cornerstone in the assessment of many cardiac diseases. However, variants are frequently classified as variants of unknown significance, limiting the utility of testing. Recently, the DeepMind group (Google) developed AlphaMissense, a unique artificial intelligence-based model, based on language model principles, for the prediction of missense variant pathogenicity. We aimed to report on the performance of AlphaMissense, accessed by VarCardio, an open web-based variant annotation engine, in a real-world cardiovascular genetics center.

Methods and results: All genetic variants from an inherited arrhythmia program were examined using AlphaMissense via VarCard.io and compared with the ClinVar variant classification system, as well as another variant classification platform (Franklin by Genoox). The mutation reclassification rate and genotype-phenotype concordance were examined for all variants in the study. We included 266 patients with heritable cardiac diseases, harboring 339 missense variants. Of those, 230 (67.8%) were classified by ClinVar as either variants of unknown significance or nonclassified. Using VarCard.io, 198 variants of unknown significance (86.1%, 95% CI, 80.9-90.3) were reclassified to either likely pathogenic or likely benign. The reclassification rate was significantly higher for VarCard.io than for Franklin (86.1% versus 34.8%, P<0.001). Genotype-phenotype concordance was highly aligned using VarCard.io predictions, at 95.9% (95% CI, 92.8-97.9) concordance rate. For 109 variants classified as pathogenic, likely pathogenic, benign, or likely benign by ClinVar, concordance with VarCard.io was high (90.5%).

Conclusions: AlphaMissense, accessed via VarCard.io, may be a highly efficient tool for cardiac genetic variant interpretation. The engine's notable performance in assessing variants that are classified as variants of unknown significance in ClinVar demonstrates its potential to enhance cardiac genetic testing.

Keywords: AlphaMissense; VarCard.Io; artificial intelligence; genetic testing; genotype; phenotype; variants of unknown significance.

PubMed Disclaimer

Figures

Figure 1
Figure 1. Frequency graph of patients' most frequent phenotypes in the cohort.
BrS indicates Brugada syndrome; CPVT, catecholaminergic polymorphic ventricular tachycardia; HCM, hypertrophic cardiomyopathy; LQTS, long QT syndrome; NICMP, nonischemic cardiomyopathy; PCCD, progressive cardiac conduction defect; and SQTS, short QT syndrome.
Figure 2
Figure 2. Variant frequency and annotation according to (A) VarCard.io and (B) ClinVar.
LB indicates likely benign; LP, likely pathogenic; and VUS, variant of unknown significance.
Figure 3
Figure 3. Sankey diagram showing reclassification of variant reclassification changes from ClinVar to VarCard.io.
VUS indicates variant of unknown significance.
See this image and copyright information in PMC

References

    1. Cirino AL, Harris S, Lakdawala NK, Michels M, Olivotto I, Day SM, Abrams DJ, Charron P, Caleshu C, Semsarian C, et al. Role of genetic testing in inherited cardiovascular disease: a review. JAMA Cardiol. 2017;2:1153–1160. doi: 10.1001/jamacardio.2017.2352 - DOI - PubMed
    1. Behere SP, Weindling SN. Inherited arrhythmias: the cardiac channelopathies. Ann Pediatr Cardiol. 2015;8:210–220. doi: 10.4103/0974-2069.164695 - DOI - PMC - PubMed
    1. Morales A, Hershberger RE. The rationale and timing of molecular genetic testing for dilated cardiomyopathy. Can J Cardiol. 2015;31:1309–1312. doi: 10.1016/j.cjca.2015.06.034 - DOI - PMC - PubMed
    1. Mazzaccara C, Lombardi R, Mirra B, Barretta F, Esposito MV, Uomo F, Caiazza M, Monda E, Losi MA, Limongelli G, et al. Next‐generation sequencing gene panels in inheritable cardiomyopathies and channelopathies: prevalence of pathogenic variants and variants of unknown significance in uncommon genes. Biomolecules. 2022;12:1417. doi: 10.3390/biom12101417 - DOI - PMC - PubMed
    1. van Lint FHM, Mook ORF, Alders M, Bikker H, Lekanne D, Deprez RH, Christiaans I. Large next‐generation sequencing gene panels in genetic heart disease: yield of pathogenic variants and variants of unknown significance. Neth Heart J. 2019;27:304–309. doi: 10.1007/s12471-019-1250-5 - DOI - PMC - PubMed

LinkOut - more resources