Thu. Jan 9th, 2025
Coronary Artery Disease: Rare Genetic Variants Using Machine Learning Models

Coronary artery disease: rare genetic variants using machine learning models

MedicalResearch.com Interview:

Ben Petrazzini

Ben Omega Petrazzini, Bachelor of Science
Associate Bioinformatician
Ron de Laboratoire

Dr. Ron Do Professor, Department of Genetics and Genomic Sciences Director, Center for Genomic Data Analysis Associate Director for Academic Affairs, Charles Bronfman Institute for Personalized Medicine Charles Bronfman Professor of Personalized Medicine

Dr. Long Du

Dr. Ron Do.
Professor, Department of Genetics and Genome Sciences
Director of the Genome Data Analysis Center
Associate Director of Academic Affairs, Charles Bronfman Institute for Precision Medicine
Charles Bronfman Professor of Personalized Medicine
Icahn School of Medicine at Mount Sinai

MedicalResearch.com: What is the background to this study?

response: Rare coding variants can directly affect protein function and inform the role of genes in disease.

Discovery of rare coding variant associations with coronary artery disease (CAD) has met with limited success to date. Genetic studies typically use standard phenotyping approaches to classify CAD cases and controls. However, this phenotyping approach does not capture disease progression or severity in individuals.

We have recently introduced the in-silico score for CAD (ISCAD) that tracks CAD progression, severity, underdiagnosis, and mortality (Forrest et al. Lancet2023, PMID 36563696). ISCAD was built using a machine learning model trained on clinical data from electronic health records (EHRs). Importantly, ISCAD is a quantitative score that measures CAD across a spectrum. The quantitative nature of the score provides an opportunity to discover additional rare coding variant associations that may not have been detected using standard case-control phenotypic approaches.

In this study, we conducted a large-scale rare variant association study in exome sequences of 604,915 individuals for ISCAD, a machine learning-based score for CAD.

MedicalResearch.com: Is this a model that can be integrated into existing genetic profiles and medical records?

response: ISCAD uses diagnosis codes, medication prescriptions, lab test results, and vital sign measurements from the EHR to calculate a prediction of CAD diagnosis.

Therefore, ISCAD can be calculated for any biobank with EHR data. Once ISCAD is calculated, it can be used to perform genetic association analysis.

MedicalResearch.com: What should readers take away from your report?

response: This study identified rare or ultra-rare coding variants in 17 genes associated with ISCAD. Some of these genes are known and have been linked to lipid and lipoprotein properties; however, others are novel. Further investigation of these genes will provide biological and mechanistic insights into their role in disease.

MedicalResearch.com: Given the results of this study, what recommendations do you have for future research?

response: This study suggests that machine learning-based scores are a complementary phenotyping approach for genetic association studies. Future studies will include further functional characterization of the novel genes discovered in this study and conducting association testing for rare variants using ISCAD in additional EHR-linked biobanks of diverse ancestry.

No disclosure

Quote:

Petrazzini, B.O., Forrest, I.S., Rochereau, G. etc Exome sequencing identified rare coding variants associated with machine learning-based markers of coronary artery disease. Nat Junett (2024). https://doi.org/10.1038/s41588-024-01791-x

The information on MedicalResearch.com is provided for educational purposes only and is not intended to diagnose, treat or cure any medical or other condition.

Some links may be sponsored. Products are not endorsed.

Always seek the advice of your physician or other qualified health care provider and ask your physician if you have any questions regarding a medical condition.In addition to all other limitations and disclaimers set forth in this Agreement, Service Provider and its third party providers disclaim any liability or loss in connection with any content provided on this Website.

Last updated: June 14, 2024 Marie Benz MD FAAD


56