Going beyond HRR mutations: A deep-learning approach on HRD detection in ovarian cancer
Homologous recombination deficiency (HRD) is an important prognostic and predictive biomarker in ovarian cancer. It is assessed by combining information from homologous recombination repair (HRR) gene mutations, the “cause” of HRD, with a measure of genomic scarring, the “effect” of HRD. However, implementing HRD analysis in-house can be challenging due to technical limitations, such as the requirement for deep genomic profiling data. Deep learning-based approaches that leverage low-pass whole genome sequencing (WGS) can help overcome limitations and maximize insights from raw NGS data for accurate in-house HRD detection.
In this webinar, Dr. Nicola Normanno (Director, Translational Research, National Cancer Institute, Italy Pascale Foundation) presents analytical performance results from an in-house evaluation of HRD status in ovarian cancer samples using the deep learning-based SOPHiA DDM™ HRD Solution.
SOPHiA DDM™ HRD Solution is for research use only, not for use in diagnostic procedures.