FOR IMMEDIATE RELEASE
January 26, 2021 Ann Arbor, MI

Genomenon Announces Publication of Scientific Paper in Frontiers in Genetics

Peer-Reviewed Paper Demonstrates the Utility and Superiority of Mastermind for Clinical Diagnostic Variant Interpretation

Genomenon Inc., an AI-driven genomics company that connects the world’s genomic knowledge with patient DNA, announced that a seminal paper written by its team of scientists has been published in the Computational Genomics section of Frontiers in Genetics. Frontiers in Genetics is an open-access journal that publishes rigorously peer-reviewed research on genes and genomes relating to all domains of life.

The paper, entitled “Mastermind: A Comprehensive Genomic Association Search Engine for Empirical Evidence Curation and Genetic Variant Interpretation”, demonstrates how this widely used bioinformatic platform has automatically identified and annotated over 6.8 million unique genetic variants across the published genetic evidence, a more than 22-fold increase compared to the largest manually curated alternative. The paper shows how a computationally intelligent approach to building a search engine for genetic evidence has quickly surpassed two decades of manual effort in building static genetic databases.

The study shows how the Mastermind Genomic Search Engine benefits clinical diagnostic laboratories by significantly improving the sensitivity and reproducibility of clinical variant interpretation. Mastermind data is also used to produce comprehensive genomic landscapes of genetic variants, which drive pharmaceutical research.

“It is highly rewarding to have the work we have been doing for the past six years be validated in such an unequivocal way” said Dr. Mark Kiel, Co-founder and Chief Science Officer of Genomenon. “This is just the first chapter in our journey to save and improve lives by making genomic information actionable.”

Key results of the study include an examination of the sensitivity of Mastermind for variant interpretation. Compared to alternate methods in clinically-encountered genetic variants, Mastermind demonstrated a sensitivity of 98.4% compared to 4.4%, 45.6%, and 37.4% for alternatives PubMed, Google Scholar, and ClinVar respectively, and a specificity of 98.5% compared to 45.1%, 57.6%, and 68.8%, as well as an increase in content yield of 22.6-, 2.2-, and 2.6-fold.

Mastermind was shown to have significantly more data than the alternatives. When curated for clinical significance, Mastermind identified more than 4.9-fold more pathogenic genetic variants than ClinVar for representative genes and demonstrated a 4.0- to 43.9-fold increase in references for specific Copy Number Variations (CNVs) compared to PubMed, as well as 5.4-fold more fusion genes when compared with COSMIC’s curated database. Mastermind also produced an 8.0-fold increase in reference citations for fusion events.

Taken together, the results shown in the study demonstrate the utility and superiority of Mastermind in terms of both sensitivity and specificity of automated results for clinical diagnostic variant interpretation for multiple genetic variant types, and highlight the potential benefit in informing pharmaceutical research.

Free access to the publication is available at: https://www.frontiersin.org/articles/10.3389/fgene.2020.577152/full