Abstract 2788
Background
Deep learning (DL) is one of the best approaches to predict nonlinear behaviors from high dimensional data. Nevertheless predicting the outcome of patients affected by cancers from transcriptomic data has shown limited performance, even with DL (C-index usually <0.65). Transfer learning is a DL two-step method where a model is pre-trained for a basic task on large amount of data, and then fine-tuned on the aimed task. We hypothesized that using TL with RNAseq may improve the performances of cancer patients’ outcome estimation.
Methods
The model was a Multi-Mayer Perceptron (MLP) with 22913 inputs corresponding to genes bulk tumor whole genome RNAseq expression analysis. An important restriction was applied to the number of units at second layer (N = 100), with further linear decrease across subsequent layers. Architecture of the model (number of layers, skip connections), L1 normalization value and learning rate were optimized by grid search on 30 parallel models. Training was performed using Keras package in R. Data were split into 70% training, 15% cross validation, 15% validation for each step, without contamination between the 2 transfer learning steps. The pre-training step consisted in predicting the organs of sample origin using 17.487 public RNAseq data of normal & cancer tissues (GTEX from gtexportal.org & TCGA from cBioportal.org). Fine-tuning on patients survival used 6401 training tumors. The model’s performance on survival prediction was evaluated by C-index and the area under the survival receiver-operating characteristic curve (AUROC).
Results
The pre-training using GTEx and TCGA reached very high performance with validation accuracy of 0.96 to predict organ of origins for the best model (all models had validation accuracy > 0.9). Fine-tuning on survival, the prognostic performance of the best model on the validation cohort was C-index=0.74 and AUROC= 0.81 (80% of models had a C-index > 0.6). The best model had 8 hidden layers and a small penalization value.
Conclusions
Thanks to this original transfer learning method, we achieved a high performance to estimate cancer patients’ prognostic from whole genome expression, a classically challenging task. Learning on public databases is a valuable method of DL for personalized cancer care.
Clinical trial identification
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
E. Angevin: Advisory / Consultancy: Amgen; Advisory / Consultancy: Astellas; Advisory / Consultancy: AstraZeneca; Advisory / Consultancy: Bayer; Advisory / Consultancy: BeiGene; Advisory / Consultancy: BMS; Advisory / Consultancy: Celgene; Advisory / Consultancy: DebioPharma; Advisory / Consultancy: Genentech; Advisory / Consultancy: Ipsen; Advisory / Consultancy: Janssen; Advisory / Consultancy: Lilly; Advisory / Consultancy: MedImmune; Advisory / Consultancy: Novartis; Advisory / Consultancy: Pfizer; Advisory / Consultancy: Roche; Advisory / Consultancy: Sanofi; Advisory / Consultancy: Orion. A. Hollebecque: Advisory / Consultancy: Amgen; Advisory / Consultancy: Spectrum Pharmaceuticals; Advisory / Consultancy: Lilly; Advisory / Consultancy: Debiopharm; Travel / Accommodation / Expenses: Servier; Travel / Accommodation / Expenses: Amgen; Travel / Accommodation / Expenses: Lilly; Travel / Accommodation / Expenses: Incyte; Travel / Accommodation / Expenses: Debiopharm. E. Deutsch: Advisory / Consultancy: Boehringer; Advisory / Consultancy: Medimune; Advisory / Consultancy: Amgen; Research grant / Funding (self): AstraZeneca; Research grant / Funding (self): biotrachea; Research grant / Funding (institution): BristolMyersSquidd; Research grant / Funding (self): Clevelex; Research grant / Funding (self): EDF; Research grant / Funding (self): Lilly; Research grant / Funding (self): GlaxoSmisthKline; Research grant / Funding (self): Merk; Research grant / Funding (self): Nanobiotix; Research grant / Funding (self): Oseo; Research grant / Funding (self): Ray Search Laboratory; Research grant / Funding (self): Roche; Research grant / Funding (self): Ipsen; Research grant / Funding (self): Servier; Research grant / Funding (self): Takeda. C. Massard: Advisory / Consultancy: Amgen; Advisory / Consultancy: Astellas; Advisory / Consultancy: AstraZeneca; Advisory / Consultancy: Bayer; Advisory / Consultancy: BeiGene; Advisory / Consultancy: BMS; Advisory / Consultancy: Celgene; Advisory / Consultancy: DebioPharma; Advisory / Consultancy: Genentech; Advisory / Consultancy: Ipsen; Advisory / Consultancy: Janssen; Advisory / Consultancy: Lilly; Advisory / Consultancy: MedImmune; Advisory / Consultancy: Novartis; Advisory / Consultancy: Pfizer; Advisory / Consultancy: Roche; Advisory / Consultancy: Sanofi; Advisory / Consultancy: Orion. L. Verlingue: Research grant / Funding (self): Bristol-Myers Squibb; Advisory / Consultancy: Pierre Fabre; Advisory / Consultancy: Adaptherapy. All other authors have declared no conflicts of interest.
Resources from the same session
1707 - Clinical utility of precision immunoprofiling and monitoring of the tumor microenvironment using flow cytometry and CyTOF in patients with advanced NSCLC treated with atezolizumab: results from a phase II study for biomarker analysis (EPOC1702)
Presenter: Keisuke Kirita
Session: Poster Display session 3
Resources:
Abstract
3594 - Tumor mutation burden (TMB), PD-L1, IFN-γ signaling identify subgroups of patients (pts) who benefit from durvalumab (D, anti-PDL1) or D and tremelimumab (T, anti-CTLA4) treatment in urothelial bladder cancer (UC)
Presenter: Christophe Massard
Session: Poster Display session 3
Resources:
Abstract
744 - The decrease of TMB, TNB and HLA expression are the Mechanism of Drug Resistance of NSCLC to immunosuppressive PD-1/PD-l1.
Presenter: Sheng Yu
Session: Poster Display session 3
Resources:
Abstract
2350 - Eosinophilia during treatment of immune checkpoint inhibitors (ICIs) predicts succeeding onset of immune-related adverse events (irAEs)
Presenter: Rika Kizawa
Session: Poster Display session 3
Resources:
Abstract
5930 - A transcriptomic immunologic signature predicts favorable outcome in neoadjuvant chemotherapy treated triple negative breast tumors.
Presenter: Javier Pérez-peña
Session: Poster Display session 3
Resources:
Abstract
6127 - Alterations of TMB and TCR repertoires during Chemotherapy in East Asian lung cancer patients without TKI-related driver gene mutations
Presenter: Lele Song
Session: Poster Display session 3
Resources:
Abstract
1310 - Association of SCFA in gut microbiome and clinical response in solid cancer patients treated with andi-PD-1 antibody.
Presenter: Motoo Nomura
Session: Poster Display session 3
Resources:
Abstract
2286 - Extracellular matrix and tissue derived metabolites in a liquid biopsy identifies endotypes of metastatic melanoma patients with differential response to immune checkpoint inhibitor treatment
Presenter: Nicholas Willumsen
Session: Poster Display session 3
Resources:
Abstract
4107 - Pathologic scoring of pre-treatment H&E biopsies predicts overall survival in patients with metastatic clear cell renal cell carcinoma receiving nivolumab monotherapy
Presenter: Julie Stein
Session: Poster Display session 3
Resources:
Abstract
1291 - PD-L1 expression in uncommon EGFR-mutant non-small cell lung cancer and its response to immunotherapy
Presenter: Yun Fan
Session: Poster Display session 3
Resources:
Abstract