Learning the Literature: Genomenon, Veritas Collaborate on Next-Gen Publication Prioritization Engine

May 22, 2018
Learning the Literature: Genomenon, Veritas Collaborate on Next-Gen Publication Prioritization Engine
The Genomenon-Veritas Collaboration will leverage machine learning and artificial intelligence to help create a literature prioritization engine with the promise of more accurate and cost-efficient variant interpretation.

Alex Philippidis

Genomenon has announced it will partner with Veritas Genetics to develop a next-generation literature prioritization engine the companies said will further scale the global adoption of whole-genome sequencing by reducing the time and cost of variant interpretation. The engine will incorporate proprietary genomic language processing (GLP), machine learning (ML), and artificial intelligence (AI) tools—while following the American College of Medical Genetics (ACMG) and Association for Medical Pathology (AMP) variant classification frameworks, Genomenon said.

“As opposed to creating targeted panels for a specific disease, the interpretation challenge greatly increases when you’re looking across the entire genome without a diagnosis,” Genomenon CEO Mike Klein said. “The challenge gets even more daunting when you think about how to scale to meet the increasing demand, from hundreds of whole genomes per month to hundreds of thousands of whole genomes in the next three years.

“The ability to scale the clinical interpretation of whole genome sequencing by several orders of magnitude is what prompted us to partner with Veritas,” Klein added. “Veritas is on the leading edge of sequencing whole genomes directly for individuals.”

Veritas offers consumers whole-genome sequencing and interpretation services under the myGenome brand. The services are designed to yield insights on inherited disease risks, carrier status, drug sensitivities, traits, and ancestry for $999. They were the first such services to be offered for under $1,000 when launched in 2016, according to the company. Veritas says myGenome delivers for customers clinically relevant findings on more than 1,200 conditions—including some cancers, cardiovascular diseases, immune disorders, endocrine/metabolic disorders, neurological disorders, organ health or multisystem disorders, and reproductive/ carrier screening. Also included are findings on the 59 medicallyactionable genes recommended by ACMG for return in clinical genomic sequencing.

Under its collaboration with Genomenon, Veritas has agreed to integrate into its current workflow and interpretation tools Genomenon’s Mastermind Genomic Search Engine. According to Genomenon, Mastermind is the world’s first search engine to connect genomic data from patients with evidence retrieved from scientific literature. Mastermind aims to comprehensively identify all clinically relevant and prioritized articles and is designed to link data on DNA mutations from patients with citations from scientific publications, with the goal of understanding the clinical impact of each mutation. To date, Mastermind has indexed nearly 6 million scientific articles covering every disease, gene and variant, out of the 30 million titles and abstracts in PubMed. The indexed articles contain data on more than 1.5 million variants, according to Genomenon.

Click here to access the rest of this article.