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
1885 - Factors associated with disease progression in patients treated with trametinib in combination with dabrafenib for unresectable advanced BRAFV600-mutant melanoma: an open label, non randomized study
Presenter: Philippe Saiag
Session: Poster Display session 3
Resources:
Abstract
5259 - Integrative RNAseq and Target panel sequencing reveals common and distinct innate and adaptive resistance mechanisms to BRAF inhibitors
Presenter: Phil Cheng
Session: Poster Display session 3
Resources:
Abstract
5619 - Effective treatment with T-VEC monotherapy in Stage IIIB/C-IVM1a Melanoma of the Head & Neck Region
Presenter: Viola Franke
Session: Poster Display session 3
Resources:
Abstract
5666 - Re-introduction of T-VEC Monotherapy in Recurrent Stage IIIB/C-IVM1a melanoma is effective
Presenter: Viola Franke
Session: Poster Display session 3
Resources:
Abstract
4117 - Efficacy of talimogene laherparepvec (T-VEC) in melanoma patients (pts) with locoregional (LR) recurrence, including in-transit metastases (ITM): subgroup analysis of the phase 3 OPTiM study
Presenter: Mark Middleton
Session: Poster Display session 3
Resources:
Abstract
5303 - Real Life Use of Talimogene Laherparepvec in Melanoma in Centers in Austria and Switzeland
Presenter: Christoph Hoeller
Session: Poster Display session 3
Resources:
Abstract
4130 - Outcomes of advanced melanoma patients who discontinued pembrolizumab (pembro) after complete response (CR) in the French early access program (EAP)
Presenter: Philippe Saiag
Session: Poster Display session 3
Resources:
Abstract
2050 - Outcome of patients with elevated LDH treated with first-line targeted therapy (TT) or PD-1 based immune checkpoint inhibitors (ICI)
Presenter: Sarah Knispel
Session: Poster Display session 3
Resources:
Abstract
1618 - Comparative-Effectiveness of Pembrolizumab vs. Nivolumab for Patients with Metastatic Melanoma
Presenter: Justin Moser
Session: Poster Display session 3
Resources:
Abstract
3556 - Long-term efficacy of combination nivolumab and ipilimumab for first-line treatment of advanced melanoma: a network meta-analysis
Presenter: Peter Mohr
Session: Poster Display session 3
Resources:
Abstract