Challenges and approaches to calibrating patient phenotype as evidence for cancer gene variant classification under ACMG/AMP guidelines.

Since first publication of the American College of Medical Genetics and Genomics/Association for Medical Pathology (ACMG/AMP) variant classification guidelines, additional recommendations for application of certain criteria have been released (https://clinicalgenome.org/docs/), to improve their application in the diagnostic setting. However, none have addressed use of the PS4 and PP4 criteria, capturing patient presentation as evidence towards pathogenicity. Application of PS4 can be done through traditional case-control studies, or "proband counting" within or across clinical testing cohorts. Review of the existing PS4 and PP4 specifications for Hereditary Cancer Gene Variant Curation Expert Panels revealed substantial differences in the approach to defining specifications. Using BRCA1, BRCA2 and TP53 as exemplar genes, we calibrated different methods proposed for applying the "PS4 proband counting" criterion. For each approach, we considered limitations, non-independence with other ACMG/AMP criteria, broader applicability, and variability in results for different datasets. Our findings highlight inherent overlap of proband-counting methods with ACMG/AMP frequency codes, and the importance of calibration to derive dataset-specific code weights that can account for potential between-dataset differences in ascertainment and other factors. Our work emphasizes the advantages and generalizability of logistic regression analysis over simple proband-counting approaches to empirically determine the relative predictive capacity and weight of various personal clinical features in the context of multigene panel testing, for improved variant interpretation. We also provide a general protocol, including instructions for data formatting and a web-server for analysis of personal history parameters, to facilitate dataset-specific calibration analyses required to use such data for germline variant classification.

The Clinical Genome Resource (ClinGen) Familial Hypercholesterolemia Variant Curation Expert Panel consensus guidelines for LDLR variant classification.

PURPOSE: In 2015, the American College of Medical Genetics and Genomics (ACMG) and the Association for Molecular Pathology (AMP) published consensus standardized guidelines for sequence-level variant classification in Mendelian disorders. To increase accuracy and consistency, the Clinical Genome Resource Familial Hypercholesterolemia (FH) Variant Curation Expert Panel was tasked with optimizing the existing ACMG/AMP framework for disease-specific classification in FH. In this study, we provide consensus recommendations for the most common FH-associated gene, LDLR, where >2300 unique FH-associated variants have been identified. METHODS: The multidisciplinary FH Variant Curation Expert Panel met in person and through frequent emails and conference calls to develop LDLR-specific modifications of ACMG/AMP guidelines. Through iteration, pilot testing, debate, and commentary, consensus among experts was reached. RESULTS: The consensus LDLR variant modifications to existing ACMG/AMP guidelines include (1) alteration of population frequency thresholds, (2) delineation of loss-of-function variant types, (3) functional study criteria specifications, (4) cosegregation criteria specifications, and (5) specific use and thresholds for in silico prediction tools, among others. CONCLUSION: Establishment of these guidelines as the new standard in the clinical laboratory setting will result in a more evidence-based, harmonized method for LDLR variant classification worldwide, thereby improving the care of patients with FH.

Harmonizing variant classification for return of results in the All of Us Research Program.

The All of Us Research Program (AoURP) is a historic effort to accelerate research and improve healthcare by generating and collating data from one million people in the United States. Participants will have the option to receive results from their genome analysis, including actionable findings in 59 gene-disorder pairs for which disorder-associated variants are recommended for return by the American College of Medical Genetics and Genomics. To ensure consistent reporting across the AoURP, in a prelaunch study the four participating clinical laboratories shared all variant classifications in the 59 genes of interest from their internal databases. Of the 11,813 unique variants classified by at least two of the four laboratories, classifications were concordant with regard to reportability for 99.1% (11,711), with only 0.9% (102) having reportability differences. Through variant reassessment, data sharing, and discussion of rationale, participating laboratories resolved all 102 reportable differences. These approaches will be maintained during routine AoU reporting to ensure continuous classification harmonization and consistent reporting within AoURP.

LEAP: Using machine learning to support variant classification in a clinical setting.

Advances in genome sequencing have led to a tremendous increase in the discovery of novel missense variants, but evidence for determining clinical significance can be limited or conflicting. Here, we present Learning from Evidence to Assess Pathogenicity (LEAP), a machine learning model that utilizes a variety of feature categories to classify variants, and achieves high performance in multiple genes and different health conditions. Feature categories include functional predictions, splice predictions, population frequencies, conservation scores, protein domain data, and clinical observation data such as personal and family history and covariant information. L2-regularized logistic regression and random forest classification models were trained on missense variants detected and classified during the course of routine clinical testing at Color Genomics (14,226 variants from 24 cancer-related genes and 5,398 variants from 30 cardiovascular-related genes). Using 10-fold cross-validated predictions, the logistic regression model achieved an area under the receiver operating characteristic curve (AUROC) of 97.8% (cancer) and 98.8% (cardiovascular), while the random forest model achieved 98.3% (cancer) and 98.6% (cardiovascular). We demonstrate generalizability to different genes by validating predictions on genes withheld from training (96.8% AUROC). High accuracy and broad applicability make LEAP effective in the clinical setting as a high-throughput quality control layer.