false
OasisLMS
zh-CN,zh-TW,en,fr,de,ja,ko,pt,es,th,vi
Catalog
2021 ACMG Annual Clinical Genetics Meeting - Produ ...
Rapid identification of pathogenic structural vari ...
Rapid identification of pathogenic structural variants in whole genome sequence data from 60+ rare disease cases – Fully integrated into an industry leading AI clinical decision support system, Fabric Enterprise
Back to course
[Please upgrade your browser to play this video content]
Video Transcription
Video Summary
The video is a virtual presentation by Jeanette McCarthy from Fabric Genomics as part of the 2021 ACMG Annual Conference. She discusses the ongoing benchmarking study of their new gene prioritization algorithm, GEM. The talk focuses on GEM's ability to identify pathogenic structural variants in whole genome sequence data for diagnosing rare genetic diseases in NICU patients. Fabric Genomics is known for their software for interpreting genomic data and offers a cloud-based sequence analysis platform. They provide clinical analysis, reporting, and sign-out services to labs. Fabric supports gene panels and whole genome, whole exome sequencing. GEM is the latest prioritization algorithm that integrates artificial intelligence and clinical knowledge from databases like ClinVar and OMIM. It calculates a GEM score to determine the likelihood of a gene variant being disease-causing. GEM can also infer structural variants and rank them alongside single nucleotide variants. Benchmarking and retrospective studies have shown GEM's high sensitivity in identifying causal structural variants, with scores above zero indicating candidate genes for evaluation. Overall, GEM has demonstrated its ability to accurately identify both single nucleotide variants and structural variants, improving the diagnostic yield of genetic tests. The presentation includes examples of GEM's performance and features in the Fabric Enterprise software.
Asset Subtitle
Fabric Genomics
Keywords
GEM
gene prioritization algorithm
pathogenic structural variants
whole genome sequence data
rare genetic diseases
diagnostic yield
×