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
2607 - Single cycle induction treatment with Cisplatin/Docetaxel plus Durvalumab/Tremelimumab in Stage III-IVB head and neck squamous cell cancer (CheckRad-CD8 trial)
Presenter: Markus Hecht
Session: Poster Display session 3
Resources:
Abstract
1388 - Radiotherapy plus cisplatin (CDDP) or cetuximab (C225) in human papilloma-virus (HPV)-associated oropharyngeal cancer (OPC)? A dillema finally resolved. An updated meta-analysis.
Presenter: Petar Suton
Session: Poster Display session 3
Resources:
Abstract
1478 - Treatment outcomes of head and neck cancer patients 70 years and older receiving different chemo-radiation combinations.
Presenter: Majd Issa
Session: Poster Display session 3
Resources:
Abstract
3985 - Brachytherapy and non-cancer mortality in patients with oral cavity and oropharynx SCCs
Presenter: Jovian Yu
Session: Poster Display session 3
Resources:
Abstract
4036 - Final results of a phase II study of induction chemotherapy (CT) with paclitaxel (PTX) and panitumumab (P) followed by radiotherapy (RT) and P in patients (pts) with locally advanced head and neck cancer (LAHNC) no candidates to platinum: study PANTERA
Presenter: Javier Martinez Trufero
Session: Poster Display session 3
Resources:
Abstract
4779 - Window of Opportunity for Durvalumab (MEDI4736) plus Metformin Trial in Squamous Cell Carcinoma of the Head and Neck (SCCHN): interim safety analysis
Presenter: Tony Richa
Session: Poster Display session 3
Resources:
Abstract
2757 - Severe Oral Mucositis (SOM) Mitigation by Genetically Modified Lactococcus Lactis Bacteria (LLB) Producing Human Trefoil Factor 1 (hTFF1; AG013) in Patients Being Treated With Concomitant Chemoradiation (CRT) for Oral and Oropharyngeal Cancers (OCOPC)
Presenter: Suraj Singh
Session: Poster Display session 3
Resources:
Abstract
5559 - Transcriptome signatures of treatment responses in a preoperative window of opportunity trial of nivolumab and tadalafil in resectable squamous cell carcinoma of the head and neck
Presenter: Sanket Shukla
Session: Poster Display session 3
Resources:
Abstract
3263 - Risk and Impact of Renal Impairment of Locally Advanced Head and Neck Squamous Cell Carcinoma Patients Who Received Chemoradiotherapy with Cisplatin
Presenter: Thana Patimarattananan
Session: Poster Display session 3
Resources:
Abstract
3128 - Systemic bevacizumab for the treatment of recurrent respiratory papillomatosis: A retrospective analysis from an academic tertiary care center
Presenter: Sumita Trivedi
Session: Poster Display session 3
Resources:
Abstract