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
2743 - The Impact of Targeted Therapies and Immunotherapy in Melanoma Brain Metastases: a Systematic Review and Meta-Analysis
Presenter: Mario Mandala
Session: Poster Display session 3
Resources:
Abstract
5479 - Intracranial Anti-Tumor Activity in Melanoma Brain Metastases with Encorafenib Plus Binimetinib: A Multicenter, Retrospective Analysis
Presenter: Jose Lutzky
Session: Poster Display session 3
Resources:
Abstract
3560 - Outcomes of Patients with Melanoma Brain Metastases (MBM) Treated with Standard of Care Therapy After Being Excluded from MBM-Specific Clinical Trials
Presenter: Kourtney Holbrook
Session: Poster Display session 3
Resources:
Abstract
3175 - The analysis of current treatment outcomes in melanoma patients with brain metastases
Presenter: Joanna Placzke
Session: Poster Display session 3
Resources:
Abstract
4550 - A multivariate model to define prognostic groups among patients with melanoma brain metastases: a 10-year retrospective cohort study
Presenter: Giacomo Pelizzari
Session: Poster Display session 3
Resources:
Abstract
4191 - The immune landscape of melanoma significantly influences survival in patients with highly mutated tumors.
Presenter: Robert Ferguson
Session: Poster Display session 3
Resources:
Abstract
1625 - Final Results from Phase II of Combination with Canerpaturev (formerly HF10), an Oncolytic Viral Immunotherapy, and Ipilimumab in Unresectable or Metastatic Melanoma in 2nd-or later line treatment
Presenter: Kenji Yokota
Session: Poster Display session 3
Resources:
Abstract
5346 - Evaluating polygenic risk score prediction model for melanoma prognosis
Presenter: Miriam Potrony
Session: Poster Display session 3
Resources:
Abstract
5477 - Impact of sarcopenia in patients with metastatic melanoma treated with immunotherapy
Presenter: Maria Grazia Vitale
Session: Poster Display session 3
Resources:
Abstract
3469 - Ancillary evaluation of systemic immune antitumor response (SIAR) and tumor growth rate (TGR) of patients (pts) with metastatic melanoma (MM) treated with radiotherapy (RT) combined with ipilimumab (ipi) in the phase 1 study Mel-Ipi-Rx.
Presenter: Celine Boutros
Session: Poster Display session 3
Resources:
Abstract