Comprehensive Genomic Association Data for Genetic Variant Interpretation: A Computational Approach

Design and interpretation of genome sequencing assays and data in both clinical diagnostics and research labs is complicated by an inability to identify information from the medical literature and related databases quickly, comprehensively and reproducibly. This challenge is due in part to the complexity and heterogeneity of nomenclatures used by authors to describe diseases, genes, and genetic variants including single nucleotide changes, indels, and structural alterations like fusion genes and copy number variants (CNVs). Mastermind is a unique bioinformatic platform that employs a high-throughput computational technique known as Genomics Language Processing (GLP) to index more than 7.5M full-text articles and 2.5M supplemental datasets associated with such publications. It has automatically identified, disambiguated, and annotated more than 6.0M distinct genetic variants, and identified >50K disease-gene associations. In this webinar, Dr. Kiel will demonstrate how Genomenon’s approach to Big Data and Artificial Intelligence using GLP can connect single-nucleotide variants, in/dels, CNVs, and gene fusions with diseases, phenotypes, and drugs to allow the variant scientist to understand genomic associations across the entirety of the empirical evidence from the medical literature. Taken together, these results will demonstrate the suitability and superiority of GLP for evidence collection and clinical diagnostic variant interpretation for multiple genetic variant types, and highlight the potential benefit in informing both clinical practice and biomedical research.

Learning Objectives:

1. How GLP can improve the sensitivity and specificity of genetic variant searches for single nucleotide and indel variants compared with conventional approaches

2. How GLP can improve the efficiency and accuracy of evidence search for structural variants like CNVs and fusion genes

3. How the evidence resulting from GLP can be used to increase the speed and diagnostic utility of genetic variant interpretation