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
5389 - Two-weekly accelerated BEP (aBEP) regimen as induction chemotherapy (CT) in intermediate and poor prognosis patients (pts) with nonseminomatous germ cell tumors (NSGCT): final results of phase II trial.
Presenter: Alexey Tryakin
Session: Poster Display session 3
Resources:
Abstract
2934 - Differential expression of circulating miR375 and miR371 to detect teratoma and viable germ cell malignancy
Presenter: Lucia Nappi
Session: Poster Display session 3
Resources:
Abstract
3585 - Prognosis of anaemia in disseminated testicular germ cell tumours. On behalf of the Spanish Germ Cell Cancer Group (SGCCG)
Presenter: Esmeralda Garcia Torralba
Session: Poster Display session 3
Resources:
Abstract
2254 - The Effects Of Primary Testicular Tumor Localization On Prognosis In Patients With Nonseminomatous Testis Cancer
Presenter: Birol Yildiz
Session: Poster Display session 3
Resources:
Abstract
4505 - Initial Results of a Phase II study of Nivolumab and Ipilimumab in Metastatic Adrenal Tumors.
Presenter: Matthew Campbell
Session: Poster Display session 3
Resources:
Abstract
3369 - NEMIO: a randomized phase II trial evaluating efficacy and safety of dose dense MVAC (ddMVAC) + durvalumab +/- tremelimumab as neoadjuvant treatment in patients with bladder muscle-invasive urothelial carcinoma
Presenter: Constance Thibault
Session: Poster Display session 3
Resources:
Abstract
2075 - KEYNOTE-866: Phase 3 Study of Perioperative Pembrolizumab (pembro) or Placebo (pbo) in Combination With Neoadjuvant Chemotherapy in Cisplatin (cis)-Eligible Patients (pts) With Muscle-Invasive Bladder Cancer (MIBC)
Presenter: Arlene Siefker-Radtke
Session: Poster Display session 3
Resources:
Abstract
4824 - KEYNOTE-905: A Phase 3 Study of Cystectomy Plus Perioperative Pembrolizumab Versus Cystectomy Alone in Cisplatin (cis)-Ineligible Patients (pts) With Muscle-Invasive Bladder Cancer (MIBC)
Presenter: Matthew Galsky
Session: Poster Display session 3
Resources:
Abstract
2253 - Phase 3 LEAP-011 trial: First-Line Pembrolizumab With Lenvatinib in Patients With Advanced Urothelial Carcinoma Ineligible to Receive Platinum-Based Chemotherapy
Presenter: Yohann Loriot
Session: Poster Display session 3
Resources:
Abstract
4310 - PULSE : A Single Arm Trial Assessing The Activity and Safety of Avelumab Immunotherapy Maintenance among Patients With Locally Advanced or Metastatic Squamous Cell Penile Carcinoma (mSCPC).
Presenter: Noemie Gassian
Session: Poster Display session 3
Resources:
Abstract