Machine Learning for Better Prognostic Stratification and Driver Gene Identification Using Somatic Copy Number Variations in Anaplastic Oligodendroglioma

Shai Rosenberg (1) , Francois Ducray , Agusti Alentorn (1) , Caroline Dehais (2) , Nabila Elarouci (3) , Aurelie Kamoun , Yannick Marie (4) , Marie-Laure Tanguy , Aurélien de Reynies , Karima Mokhtari (4) , Dominique Figarella‑branger (5, 6) , Jean-Yves Delattre , Ahmed Idbaih (4)

1 ICM - Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute
2 CHU Pitié-Salpêtrière [AP-HP]
3 CIT - (le programme) Cartes d'identité des tumeurs
4 Biologie des Interactions Neurones / Glie
5 INP - Institut de neurophysiopathologie
6 Laboratoire d'Anatomie Pathologique-Neuropathologique [AP-HM Hôpital La Timone]

1p/19q-codeleted anaplastic gliomas have variable clinical behavior. We have recently shown that the common 9p21.3 allelic loss is an independent prognostic factor in this tumor type. The aim of this study is to identify less frequent genomic copy number variations (CNVs) with clinical importance that may shed light on molecular oncogenesis of this tumor type.

Keywords: Genomics; Glioma; Machine learning; Oligodendroglioma; Survival

Domains: Life Sciences [q-bio]

Shai Rosenberg, Francois Ducray, Agusti Alentorn, Caroline Dehais, Nabila Elarouci, et al.. Machine Learning for Better Prognostic Stratification and Driver Gene Identification Using Somatic Copy Number Variations in Anaplastic Oligodendroglioma. Oncologist, 2018, ⟨10.1634/theoncologist.2017-0495⟩. ⟨hal-01858235⟩