Scientific publications
GIInger predicts homologous recombination deficiency and patient response to PARPi treatment from shallow genomic profiles. Scientific Publication
Christian Pozzorini 1 , Gregoire Andre 1 , Tommaso Coletta 1 , Adrien Buisson 2 , Jonathan Bieler 1 , Loïc Ferrer 1 , Rieke Kempfer 1 , Pierre Saintigny 3 , Alexandre Harlé 4 , Davide Vacirca 5 , Massimo Barberis 5 , Pauline Gilson 4 , Cristin Roma 6 , Alexandra Saitta 1 , Ewan Smith 1 , Floriane Consales Barras 1 , Lucia Ripol 1 , Martin Fritzsche 1 , Ana Claudia Marques 1 , Amjad Alkodsi 1 , Ray Marin 1 , Nicola Normanno 6 , Christoph Grimm 7 , Leonhard Müllauer 7 , Philipp Harter 8 , Sandro Pignata 9 , Antonio Gonzalez-Martin 10 , Ursula Denison 11 , Keiichi Fujiwara 12 , Ignace Vergote 13 , Nicoletta Colombo 5 , Adrian Willig 1 , Eric Pujade-Lauraine 14 , Pierre-Alexandre Just 15 , Isabelle Ray-Coquard 16 , Zhenyu Xu 17
Abstract
Homologous recombination deficiency (HRD) is a predictive biomarker for poly(ADP-ribose) polymerase 1 inhibitor (PARPi) sensitivity. Routine HRD testing relies on identifying BRCA mutations, but additional HRD-positive patients can be identified by measuring genomic instability (GI), a consequence of HRD. However, the cost and complexity of available solutions hamper GI testing.
We introduce a deep learning framework, GIInger, that identifies GI from HRD-induced scarring observed in low-pass whole-genome sequencing data. GIInger seamlessly integrates into standard BRCA testing workflows and yields reproducible results concordant with a reference method in a multisite study of 327 ovarian cancer samples. Applied to a BRCA wild-type enriched subgroup of 195 PAOLA-1 clinical trial patients,
GIInger identified HRD-positive patients who experienced significantly extended progression-free survival when treated with PARPi. GIInger is, therefore, a cost-effective and easy-to-implement method for accurately stratifying patients with ovarian cancer for first-line PARPi treatment.
CITATION Cell Rep Med. 2023 Dec 19;4(12):101344. doi: 10.1016/j.xcrm.2023.101344
Our authors
