Development and validation of AI-assisted transcriptomic signatures to personalize adjuvant chemotherapy in patients with pancreatic ductal adenocarcinoma.

Autor:	Fraunhoffer N; Centre de Recherche en Cancérologie de Marseille (CRCM), INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Marseille, France; Laboratory of Immunomodulators, School of Medicine, Centro de Estudios Farmacológicos y Botánicos (CEFYBO), Consejo Nacional de Investigaciones Científicas y Tecnológicas (CONICET), University of Buenos Aires, Buenos Aires, Argentina., Hammel P; Digestive and Medical Oncology, Paul Brousse Hospital, Assistance Publique-Hôpitaux de Paris (AP-HP), Université Paris-Saclay, Villejuif., Conroy T; Medical Oncology Department, Institut de Cancérologie de Lorraine, Vandœuvre-lès-Nancy; Université de Lorraine, INSERM, INSPIIRE, Nancy., Nicolle R; Université Paris Cité, Centre de Recherche sur l'Inflammation (CRI), INSERM, U1149, CNRS, ERL 8252, Paris., Bachet JB; Service d'Hépato-Gastro-Entérologie, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (AP-HP), Sorbonne Université, Paris., Harlé A; Service de Biopathologie, Institut de Cancérologie de Lorraine, Université de Lorraine, CNRS UMR 7039 CRAN, Vandoeuvre-lès-Nancy, France., Rebours V; Université Paris Cité, Centre de Recherche sur l'Inflammation (CRI), INSERM, U1149, CNRS, ERL 8252, Paris; Pancreatology and Digestive Oncology Department, Beaujon Hospital-AP-HP, Clichy., Turpin A; Department of Oncology, Lille University Hospital, Lille; CNRS UMR9020, INSERM UMR1277, University of Lille, Institut Pasteur, Lille., Ben Abdelghani M; Department of Medical Oncology, Institut de Cancérologie Strasbourg Europe, Strasbourg., Mitry E; Centre de Recherche en Cancérologie de Marseille (CRCM), INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Marseille, France; Department of Medical Oncology, Paoli-Calmettes Institute, Marseille, France., Biagi J; Department of Oncology, Queen's University, Kingston, Canada., Chanez B; Centre de Recherche en Cancérologie de Marseille (CRCM), INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Marseille, France; Department of Medical Oncology, Paoli-Calmettes Institute, Marseille, France., Bigonnet M; PredictingMed, Luminy Science and Technology Park, Marseille., Lopez A; Hepatogastroenterology Department, University Hospital of Nancy, Nancy., Evesque L; Department of Medical Oncology, Antoine Lacassagne Center, Nice., Lecomte T; Hepatogastroenterology Department, Hôpital Trousseau, Tours; INSERM UMR 1069, Tours University, Tours., Assenat E; Medical Oncology Department, Centre Hospitalier Universitaire de Saint-Eloi, Montpellier., Bouché O; Université Reims Champagne Ardenne, CHU Reims, Reims, France., Renouf DJ; Division of Medical Oncology, BC Cancer, Vancouver; Department of Medicine, University of British Columbia, Vancouver, Canada., Lambert A; Medical Oncology Department, Institut de Cancérologie de Lorraine, Vandœuvre-lès-Nancy; Université de Lorraine, INSERM, INSPIIRE, Nancy., Monard L; R&D Unicancer, Paris., Mauduit M; R&D Unicancer, Paris., Cros J; Université Paris Cité, Centre de Recherche sur l'Inflammation (CRI), INSERM, U1149, CNRS, ERL 8252, Paris; Université Paris Cité, Department of Pathology, FHU MOSAIC, Beaujon/Bichat University Hospital (AP-HP), Paris, France., Iovanna J; Centre de Recherche en Cancérologie de Marseille (CRCM), INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Marseille, France; Hospital de Alta Complejidad El Cruce, Florencio Varela, Buenos Aires; University Arturo Jauretche, Florencio Varela, Buenos Aires, Argentina. Electronic address: juan.iovanna@inserm.fr., Dusetti N; Centre de Recherche en Cancérologie de Marseille (CRCM), INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Marseille, France. Electronic address: nelson.dusetti@inserm.fr.
Jazyk:	angličtina
Zdroj:	Annals of oncology : official journal of the European Society for Medical Oncology [Ann Oncol] 2024 Sep; Vol. 35 (9), pp. 780-791. Date of Electronic Publication: 2024 Jun 19.
DOI:	10.1016/j.annonc.2024.06.010
Abstrakt:	Background: After surgical resection of pancreatic ductal adenocarcinoma (PDAC), patients are predominantly treated with adjuvant chemotherapy, commonly consisting of gemcitabine (GEM)-based regimens or the modified FOLFIRINOX (mFFX) regimen. While mFFX regimen has been shown to be more effective than GEM-based regimens, it is also associated with higher toxicity. Current treatment decisions are based on patient performance status rather than on the molecular characteristics of the tumor. To address this gap, the goal of this study was to develop drug-specific transcriptomic signatures for personalized chemotherapy treatment. Patients and Methods: We used PDAC datasets from preclinical models, encompassing chemotherapy response profiles for the mFFX regimen components. From them we identified specific gene transcripts associated with chemotherapy response. Three transcriptomic artificial intelligence signatures were obtained by combining independent component analysis and the least absolute shrinkage and selection operator-random forest approach. We integrated a previously developed GEM signature with three newly developed ones. The machine learning strategy employed to enhance these signatures incorporates transcriptomic features from the tumor microenvironment, leading to the development of the 'Pancreas-View' tool ultimately clinically validated in a cohort of 343 patients from the PRODIGE-24/CCTG PA6 trial. Results: Patients who were predicted to be sensitive to the administered drugs (n = 164; 47.8%) had longer disease-free survival (DFS) than the other patients. The median DFS in the mFFX-sensitive group treated with mFFX was 50.0 months [stratified hazard ratio (HR) 0.31, 95% confidence interval (CI) 0.21-0.44, P < 0.001] and 33.7 months (stratified HR 0.40, 95% CI 0.17-0.59, P < 0.001) in the GEM-sensitive group when treated with GEM. Comparatively patients with signature predictions unmatched with the treatments (n = 86; 25.1%) or those resistant to all drugs (n = 93; 27.1%) had shorter DFS (10.6 and 10.8 months, respectively). Conclusions: This study presents a transcriptome-based tool that was developed using preclinical models and machine learning to accurately predict sensitivity to mFFX and GEM. (Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu