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
5705 - External validation and longitudinal extension of the LIPI (Lung Immune Prognostic Index) for immunotherapy outcomes in advanced non-small cell lung cancer.
Presenter: Jakob Riedl
Session: Poster Display session 3
Resources:
Abstract
5758 - Changes of TCR Repertoire in Metastatic Renal Cell Carcinoma and Metastatic Melanoma Patients Treated with Nivolumab
Presenter: Martin Klabusay
Session: Poster Display session 3
Resources:
Abstract
1743 - Expression of MHC class I, HLA-A and HLA-B identifies immune activated breast tumors with favorable outcome
Presenter: María Del Mar Noblejas López
Session: Poster Display session 3
Resources:
Abstract
2219 - Prognostic Significance of Tumor Tissue NeuGcGM3 Ganglioside Expression and Predictive Value of Circulating Tumor Cell Count Monitoring in Patients Receiving Racotumomab Immunotherapy
Presenter: Necdet Üskent
Session: Poster Display session 3
Resources:
Abstract
2996 - Evolution of Myeloid-Derived Suppressor Cells and Objective Response Rate in Relapsed/Refractory Diffuse Large B Cell Lymphoma (R/R DLBCL) patients after receiving immunotherapy
Presenter: Carlos Jiménez Cortegana
Session: Poster Display session 3
Resources:
Abstract
2110 - A Phase Ia/Ib trial of the anti-programmed death-ligand 1 (PD-L1) human monoclonal antibody (mAb), CS1001, in patients (pts) with advanced solid tumors or lymphomas
Presenter: Lin Shen
Session: Poster Display session 3
Resources:
Abstract
3515 - Results from a randomised Phase 1/2 trial evaluating the safety and antitumour activity of anti-PD-1 (MEDI0680)/anti-PD-L1 (durvalumab) vs anti-PD-1 (nivolumab) alone in metastatic clear cell renal cell carcinoma (ccRCC)
Presenter: Martin Voss
Session: Poster Display session 3
Resources:
Abstract
3566 - Pembrolizumab in Advanced Rare Cancers
Presenter: Aung Naing
Session: Poster Display session 3
Resources:
Abstract
3567 - High clinical benefit rates of pembrolizumab in very rare sarcoma histotypes: first results of the AcSé Pembrolizumab study
Presenter: Jean-Yves Blay
Session: Poster Display session 3
Resources:
Abstract
2421 - Lenvatinib plus PD-1 blockade in advanced bile tract carcinoma.
Presenter: Jianzhen Lin
Session: Poster Display session 3
Resources:
Abstract