Fiche publication
Date publication
décembre 2023
Journal
Cell reports. Medicine
Auteurs
Membres identifiés du Cancéropôle Est :
Pr HARLE Alexandre
,
Dr GILSON Pauline
Tous les auteurs :
Pozzorini C, Andre G, Coletta T, Buisson A, Bieler J, Ferrer L, Kempfer R, Saintigny P, Harlé A, Vacirca D, Barberis M, Gilson P, Roma C, Saitta A, Smith E, Consales Barras F, Ripol L, Fritzsche M, Marques AC, Alkodsi A, Marin R, Normanno N, Grimm C, Müllauer L, Harter P, Pignata S, Gonzalez-Martin A, Denison U, Fujiwara K, Vergote I, Colombo N, Willig A, Pujade-Lauraine E, Just PA, Ray-Coquard I, Xu Z
Lien Pubmed
Résumé
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.
Mots clés
HRD, PARPi, biomarker, breast cancer, cancer, convolutional neural network, homologous recombination deficiency, low-pass whole-genome sequencing, lpWGS, ovarian cancer
Référence
Cell Rep Med. 2023 12 19;4(12):101344
