SEATTLE–(BUSINESS WIRE)–Apr 1, 2019–Fabric Genomics will launch a new solution this week for variant interpretation and clinical reporting, allowing clinical laboratories to dramatically accelerate turnaround times. This new software solution, called Fabric Hereditary Panels with ACE (AI Classification Engine), will debut at the American College of Medical Genetics and Genomics (ACMG) annual meeting in Seattle, Washington. It incorporates an extensively validated, automated ACMG classification engine, enabling laboratories to speed up accurate variant classification and clinical reporting.

ACE is an artificial intelligence inference engine that leverages deep gene and variant annotation, resulting in highly accurate ACMG variant classification. The software is embedded within Fabric Enterprise™, the premier software platform for genomic analysis and reporting that delivers a complete sequence-to-clinical report workflow. ACE enhances the Fabric Enterprise platform, making ACMG classification even faster and easier. It reduces VUS backlogs and grows the lab’s classified variant database more rapidly, cost-effectively and at scale.

Fabric Hereditary Panels with ACE is now available for many common genetic tests: inherited cancer risk including BRCA1 and BRCA2, newborn screening, CDC-Tier 1 and ACMG Incidental Findings testing.

“The biggest challenge to scaling genetic testing is the time spent interpreting and classifying variants,” said Martin G. Reese, PhD, Fabric Genomics’ President and CEO. “Fabric Genomics continues to lead the way in AI-driven insights to scale genome interpretation. Building on our core competency in AI, we have now delivered ACE for rapid and scalable variant classification for genetic panels. With ACE, scientists can focus their time on the hardest-to-classify variants, and labs can sign out many more cases per day.”

ACE has been validated with more than 50,000 variants, drawn from both industry-standard clinical databases such as ClinVar and VariSNP and public datasets including Color Data and the Japanese Hereditary Cancer dataset. The engine shows high concordance with expert interpretation: full classifications from ACE are generated and match those of ClinVar 2-star or 3-star variants for up to 95% of variants. All classifications are the result of answering the 28 ACMG criteria and the engine is fully compliant with ACMG-AMP guidelines for variant interpretation.

To learn more about Fabric Genomics and ACE, visit booth #923 during ACMG’s annual meeting, April 3-5 in Seattle, Washington, and attend Fabric’s poster session #666, “An Artificial Intelligence Engine for High-Throughput Matching of Genetic Variants to their ACMG/AMP Classification for Inherited Disease Gene Panels,” on Friday, April 5 th, from 10:30AM – 12 noon.

About Fabric Genomics

Fabric Genomics is making genomics-driven precision medicine a reality. The company provides clinical-decision support software that enables clinical labs, hospital systems and country-sequencing programs to gain actionable genomic insights, resulting in faster and more accurate diagnoses and reduced turnaround time. Fabric’s end-to-end genomic analysis platform incorporates proven AI algorithms, and has applications in both hereditary disease and oncology. Headquartered in Oakland, California, Fabric Genomics was founded by industry veterans and innovators with a deep understanding of bioinformatics, large-scale genomics and clinical diagnostics. To learn more, visit www.fabricgenomics.com, and follow us on Twitter and LinkedIn.

View source version on businesswire.com:https://www.businesswire.com/news/home/20190401005976/en/

CONTACT: Gaetan Fraikin, 510-595-0800

gfraikin@fabricgenomics.com

KEYWORD: UNITED STATES NORTH AMERICA WASHINGTON

INDUSTRY KEYWORD: TECHNOLOGY DATA MANAGEMENT SOFTWARE HEALTH GENETICS ONCOLOGY RESEARCH SCIENCE

SOURCE: Fabric Genomics

Copyright Business Wire 2019.

PUB: 04/01/2019 10:02 PM/DISC: 04/01/2019 10:01 PM

http://www.businesswire.com/news/home/20190401005976/en

(Excerpt) Read more Here | 2019-04-02 02:22:11
Image credit: source

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.