MARGINAL: An Automatic Classification of Variants in BRCA1 and BRCA2 Genes Using a Machine Learning Model

Abstract

Implementation of next-generation sequencing (NGS) for the genetic analysis of hereditary diseases has resulted in a vast number of genetic variants identified daily, leading to inadequate variant interpretation and, consequently, a lack of useful clinical information for treatment decisions. Herein, we present MARGINAL 1.0.0, a machine learning (ML)-based software for the interpretation of rare BRCA1 and BRCA2 germline variants. MARGINAL software classifies variants into three categories, namely, (likely) pathogenic, of uncertain significance and (likely) benign, implementing the criteria established by the American College of Medical Genetics and Genomics and the Association for Molecular Pathology (ACMG-AMP). We first annotated BRCA1 and BRCA2 variants using various sources. Then, we automatically implemented the ACMG-AMP criteria, and we finally constructed the ML model for variant classification. To maximize accuracy, we compared the performance of eight different ML algorithms in a classification scheme based on a serial combination of two classifiers. The model showed high predictive abilities with maximum accuracy of 92% and 98%, recall of 92% and 98% and specificity of 90% and 98% for the first and second classifiers, respectively. Our results indicate that using a gene and disease-specific ML automated software for clinical variant evaluation can minimize conflicting interpretations.

Gene-specific machine learning for pathogenicity prediction of rare BRCA1 and BRCA2 missense variants

“…In this sense, it is likely to perform poorly due to high variance. Crockett et al 22 , Padilla et al 25 , Hart et al 18 , Aljarf et al 14 , Khandakji and Mifsud 24 , and Karalidou et al 23 have developed gene-specific variant pathogenicity predictors for disease-associated genes, including BRCA1 and BRCA2 . Most of these studies showed that gene-specific predictors performed better than or comparable to genome-wide predictors.…”

“…First, they did not compare the gene-specific and disease-specific approaches. They compared the gene-specific approach with the genome-wide approach 14 , 18 , 22 , 24 , 25 or did not make any comparison 23 . The comparison between gene-specific and disease-specific approaches is meaningful because there is a trade-off between specificity and training sample size.…”

Do All Patients Diagnosed With Cancer Deserve Germline Testing?

“…These considerations have been discussed and debated in recent JCO articles and are nicely reviewed by Subbiah and Kurzrock. [2][3][4][5][6][7][8][9] Whether every patient deserves germline testing should not be confused with the above considerations. The question of whether every patient diagnosed with cancer has the right to germline testing, regardless of the likelihood of uncovering a pathogenic germline variant and irrespective of their reason for wanting the information that the test result provides, even if that information has no implications for their management or that of family members, is not answered by the data derived from any of the trials described by Subbiah and Kurzrock.…”