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
1242 - Monalizumab in combination with cetuximab in patients (pts) with recurrent or metastatic (R/M) head and neck cancer (SCCHN) previously treated or not with PD-(L)1 inhibitors (IO): 1-year survival data.
Presenter: Roger Cohen
Session: Poster Display session 3
Resources:
Abstract
4703 - Updated results of a phase II study evaluating accelerator-based boron neutron capture therapy (AB-BNCT) with borofalan(10B) (SPM-011) in recurrent squamous cell carcinoma (R-SCC-HN) and recurrent and locally advanced non-SCC (R/LA-nSCC-HN) of the head and neck
Presenter: Katsumi Hirose
Session: Poster Display session 3
Resources:
Abstract
3638 - Phase 3 KEYNOTE-048 Study of First-Line (1L) Pembrolizumab (P) for Recurrent/Metastatic (R/M) Head and Neck Squamous Cell Carcinoma (HNSCC): Asia vs Non-Asia Subgroup (subgrp) Analysis
Presenter: Makoto Tahara
Session: Poster Display session 3
Resources:
Abstract
2954 - Integrated data review evaluating safety, pharmacokinetics (PK) and immunogenicity of RM-1929 photoimmunotherapy (PIT) in subjects with locoregional, recurrent head and neck squamous cell carcinoma (rHNSCC).
Presenter: Jennifer Johnson
Session: Poster Display session 3
Resources:
Abstract
3629 - First line versus second line immunotherapy in recurrent/metastatic squamous cell carcinoma of the head and neck
Presenter: Caroline Even
Session: Poster Display session 3
Resources:
Abstract
767 - Sensitizing HRAS overexpressing head and neck squamous cell carcinoma (HNSCC) to chemotherapy
Presenter: Theodoros Rampias
Session: Poster Display session 3
Resources:
Abstract
4985 - A Single-Arm, Open-Label, Multicenter, Phase IIIb Clinical Trial with Nivolumab in Subjects with Recurrent or Metastatic Platinum-refractory Squamous Cell Carcinoma of the Head and Neck.
Presenter: Paolo Bossi
Session: Poster Display session 3
Resources:
Abstract
1564 - Long-term Results of Phase 2 Trial of Reduced Modified Clinical Target Volume in Low-risk Nasopharyngeal Carcinoma Treated with Intensity Modulated Radiotherapy
Presenter: Jingjing Miao
Session: Poster Display session 3
Resources:
Abstract
3356 - To compare two oral mucosa contouring methods in predicting acute oral mucocitis in nasopharyngeal carcinoma treated with helical tomotherapy
Presenter: Yuan-Yuan Chen
Session: Poster Display session 3
Resources:
Abstract
1984 - Induction chemotherapy (IC) followed by concurrent chemoradiotherapy (CCRT) in nasopharyngeal carcinoma (NPC)
Presenter: Gizem Kaval
Session: Poster Display session 3
Resources:
Abstract