1186P - A novel gene expression signature that robustly predicts the outcome of patients diagnosed with stage 1 NSCLC

Date 29 September 2014
Event ESMO 2014
Session Poster Display session
Topics Non-Small Cell Lung Cancer
Translational Research
Basic Principles in the Management and Treatment (of cancer)
Presenter Mathilde Bateson
Citation Annals of Oncology (2014) 25 (suppl_4): iv409-iv416. 10.1093/annonc/mdu347
Authors M. Bateson1, C. Ferte2, Y. Gaston-Mathé1, J. Armand3, J. Soria3
  • 1Life Science, HyperCube Research, 92800 - Puteaux/FR
  • 2Hopital De Jour, Centre Oscar Lambret, Paris/FR
  • 3Siric, Institut Gustave Roussy, 94805 - Villejuif/FR



Although the management of metastatic lung adenocarcinoma has been profoundly modified by the identification of actionable molecular aberrations, the decision making for early-stage NSCLC still relies on the tumor stage (TNM) only. Stage 1 patients are considered of good prognosis and do not receive adjuvant therapy. However a significant proportion of those patients recur within 5 years after tumor resection. The identification of those high-risk patients through high performing molecular signature would enable to treat them preventively in order to avoid or reduce the rate of recurrence and premature death.


Datasets were selected from public repositories (Director's challenge (DC) n = 402, Rousseaux n = 200, Hou n = 90, Zhu n = 143; Raponi: n = 120; Bhattacharjee; n = 125) upon the following criteria: NSCLC, stage IA-IB, no adjuvant therapy, R0 tumor resection, min 3-year follow-up. Gene expression data from various data sets were normalized using RMA and rescaled. To generate robust predictors of 3-year overall survival, an iterative feature selection framework based on predictive multivariate rules was applied on DC and on a pool of data sets composed of Hou, Zhu and Raponi (Pool) (Development sets). Only highly predictive rules in both datasets were then included in a subsequent predictive model and finally assessed for external validation in Bhattacharjee and Rousseaux (Validation sets). The predictive performances of the models were evaluated by ROC-AUC and by Kaplan Meier curves.


Our best model was robust across three independent datasets (all AUC > 0.50, p <0.05). Kaplan Meier estimates of overall survival in the validation datasets were discriminated according to the high- and low-risk groups predicted by our model (all P values <0.05). The identification of putative drugs suitable for high-risk patients is ongoing through the leverage of large drug sensitivity panels of cell lines (Cancer Cell Line Encyclopedia, GDSC-Sanger Panels).


We developed a robust and highly performing gene expression predictive signature of 3-year overall survival for stage I NSCLC regardless of histology. These promising results have the potential to change the decision making at bedside for early stage lung NSCLC patients by allowing high-risk patients to receive adjuvant therapy and prevent future recurrence and death.


All authors have declared no conflicts of interest.