A deep learning approach for improved detection of homologous recombination deficiency from shallow genomic profiles

Abstract

Homologous Recombination Deficiency (HRD) is a predictive biomarker of poly-ADP ribose polymerase 1 inhibitors (PARPi) response. Most HRD detection methods are based on genome wide enumeration of scarring events and require deep genome sequence profiles (> 30x). The cost and workflow-specific biases introduced by these genome profiling methods currently limits clinical adoption of HRD testing. We introduce the Genomic Integrity Index (GII), a Convolutional Neuronal Network, that leverages features from low pass (1x) Whole Genome Sequencing data to distinguish HRD positive and negative samples. In a cohort of 230 ovarian and breast cancer, we found GII supports accurate stratification of samples yielding results that are highly concordant with state-of-the-art HRD detection methods (0.865<AUC<0.996) which require 50x deeper coverage. We conclude that the deep learning framework supporting GII allows accurate detection of HRD from shallow genome profiles, reducing biases and data generation costs making it uniquely suited for clinical applications.

Prediction of homologous recombination deficiency from Oncomine Comprehensive Assay Plus correlating with SOPHiA DDM HRD Solution

“…The SOPHiA DDM HRD Solution is an HRD test that identifies HRR mutations through targeted sequencing and measures genomic instability (GI) through a combination of low-pass whole-genome sequencing and a deep-learning algorithm [ 17 ]. The GI index is a measure of genomic stability of the SOPHiA DDM HRD Solution.…”

“…This index is based on the analysis of the genome-wide patterns of copy number variations (CNVs) and is used to determine the level of GI in a tumor sample. A high GI index is associated with HRD tumors [ 17 ].…”

Prediction of Homologous Recombination Deficiency from Oncomine Comprehensive Assay Plus Correlating with SOPHiA DDM HRD Solution

“…The SOPHiA DDM HRD Solution is a HRD test that identifies HRR mutations through targeted sequencing and measures genomic instability (GI) through a combination of low-pass whole-genome sequencing and a deep-learning algorithm 17 . The GI index is a measure of genomic stability of the SOPHiA DDM HRD Solution.…”

“…This index is based on the analysis of the genome-wide patterns of copy number variations (CNVs) and is used to determine the level of GI in a tumor sample. A high GI index indicates a high level of GI and is associated with HRD tumors 17 .…”