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
4822 - Efficiacy of different nutritional intervention on nutritional status and quality of life for local advanced nasopharyngeal carcinoma patients: a prospective clinical trial
Presenter: Yuan-yuan Chen
Session: Poster Display session 3
Resources:
Abstract
2628 - Apatinib in treating patients with platinum-resistant or platinum-refractory recurrent or metastatic nasopharyngeal carcinoma
Presenter: Changjuan Tao
Session: Poster Display session 3
Resources:
Abstract
4887 - Impact of tumor site and adjuvant radiotherapy on survival of adenoid cystic carcinoma: a SEER database analysis
Presenter: Jason Tasoulas
Session: Poster Display session 3
Resources:
Abstract
2634 - Efficacy and safety of anlotinib for patients with recurrent and/or metastatic salivary gland carcinomas
Presenter: Wen Jiang
Session: Poster Display session 3
Resources:
Abstract
3568 - ACCURACY a phase (P) 2 trial of AL101, a pan-Notch inhibitor, in recurrent/metastatic (R/M) adenoid cystic carcinoma (ACC) patients (pts) with Notch activating mutations (Notch act mut): preliminary safety and efficacy data.
Presenter: Renata Ferrarotto
Session: Poster Display session 3
Resources:
Abstract
683 - Pathologic Staging Changes in Oral Cavity Squamous Cell Carcinoma—Stage Migration and Implications for Adjuvant Treatment
Presenter: Zain Husain
Session: Poster Display session 3
Resources:
Abstract
563 - Expression of immune response biomarkers in head and neck squamous cell carcinoma (HNSCC) in irradiated area
Presenter: Carole Pflumio
Session: Poster Display session 3
Resources:
Abstract
4030 - HLA-Ligandome analysis reveals target antigens of oropharyngeal squamous cell carcinoma
Presenter: Simon Laban
Session: Poster Display session 3
Resources:
Abstract
2979 - Topographical distribution of sentinel lymph nodes in early tongue squamous cell carcinomas
Presenter: Hiroyuki Goda
Session: Poster Display session 3
Resources:
Abstract
3517 - Role of follow-up (FU) FDG-PET/CT (FU-FDG-PET/CT) in patients with locoregionally advanced squamous cell carcinoma of the head and neck (LA-HNSCC) treated with chemotherapy and radiotherapy (RT), either concurrent (CRT) or sequential (ST).
Presenter: Bert Van Den Heuvel
Session: Poster Display session 3
Resources:
Abstract