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
5071 - Expression of estrogen receptor and programmed cell death-ligand 1 can be complementary prognostic factors in HPV-positive oropharyngeal squamous cell carcinoma
Presenter: Soohyeon Kwon
Session: Poster Display session 3
Resources:
Abstract
5306 - Real-world data of clinicopathologic characteristics of young oropharyngeal cancer patients.
Presenter: Maria Nieva
Session: Poster Display session 3
Resources:
Abstract
3407 - The clinical significance and biological mechanisms of miR-499a in high-tobacco exposed head and neck squamous cell carcinoma
Presenter: Shiqi Gong
Session: Poster Display session 3
Resources:
Abstract
3310 - Liquid biopsy for mutational profiling of locoregional recurrent and/or metastatic squamous cell carcinoma of the head and neck
Presenter: Rachel Galot
Session: Poster Display session 3
Resources:
Abstract
2362 - Blood-based testing of mutations in patients with Head and neck squamous cell carcinoma (HNSCC) using highly sensitive SafeSEQ technology
Presenter: Florentia Fostira
Session: Poster Display session 3
Resources:
Abstract
4533 - The head and neck Lung Immune Prognostic Index (HN-LIPI): a prognostic Score for Immune Checkpoint Inhibitors (ICI) in Recurrent or Metastatic Squamous Cell Carcinoma of the Head and Neck (R/M SCCHN) patients.
Presenter: Ruth Gabriela Herrera Gomez
Session: Poster Display session 3
Resources:
Abstract
5262 - Immune-related adverse events (irAEs) and outcome in recurrent/metastatic (R/M) Head and Neck Squamous Cell Carcinoma (HNSCC) patients (pts) treated by immune-checkpoints inhibitors (ICI)
Presenter: Neus Baste Rotllan
Session: Poster Display session 3
Resources:
Abstract
3725 - Intratumoral and peripheral exploratory biomarker analysis in patients with locoregional, recurrent head and neck squamous cell carcinoma (rHNSCC) treated with RM-1929 photoimmunotherapy
Presenter: Jack Bui
Session: Poster Display session 3
Resources:
Abstract
2533 - A nomogram based prognostic score to predict overall survival (OS) in recurrent-metastatic (R/M) head and neck squamous cell carcinoma (HNSCC) patients (pts) treated with immune checkpoint inhibitors (ICI).
Presenter: Luay Mousa
Session: Poster Display session 3
Resources:
Abstract
2929 - Changes of the Commensal Microbiome during Treatment are Associated with Clinical Response in the Nasopharyngeal Carcinoma Patients
Presenter: Tingting Huang
Session: Poster Display session 3
Resources:
Abstract