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
5877 - Efficacy of anti-PD(L)1 treatment in patients with metastatic urothelial cancer based on mRNA- and protein- based PD-L1 determination: Results from the multicentric, retrospective FOsMIC trial
Presenter: Jonas Jarczyk
Session: Poster Display session 3
Resources:
Abstract
5204 - A differential bladder microbiota composition is associated with tumor grade in bladder cancer.
Presenter: Monica Parra-Grande
Session: Poster Display session 3
Resources:
Abstract
4904 - Molecular characterization of metastatic urothelial carcinoma (mUC) in prior or current smokers (PCS) vs non-smokers (NS)
Presenter: Victor Sacristan Santos
Session: Poster Display session 3
Resources:
Abstract
5370 - Evaluation of different diagnostic methods for identification of FGFR alteration in advanced urothelial carcinomas: Proficiency Results based on multiple RNA extraction kits and mutation detection methods
Presenter: Veronika Weyerer
Session: Poster Display session 3
Resources:
Abstract
2579 - Title: Genomic characterization of non-schistosomiasis-related squamous cell carcinoma (NSR-SCC) of the urinary bladder: a retrospective study of potential prognostic and predictive biomarkers
Presenter: Esmail Al-ezzi
Session: Poster Display session 3
Resources:
Abstract
2203 - TiNivo: Tivozanib combined with nivolumab results in prolonged progression free survival in patients with metastatic renal cell carcinoma (mRCC). Final Results.
Presenter: Philippe Barthelemy
Session: Poster Display session 3
Resources:
Abstract
4712 - First-Line Pembrolizumab (pembro) Monotherapy for Advanced Non‒Clear Cell Renal Cell Carcinoma (nccRCC): Updated Follow-Up for KEYNOTE-427 Cohort B
Presenter: Cristina Suárez
Session: Poster Display session 3
Resources:
Abstract
2091 - First-Line Pembrolizumab (pembro) Monotherapy in Advanced Clear Cell Renal Cell Carcinoma (ccRCC): Updated Follow-Up For KEYNOTE-427 Cohort A
Presenter: James Larkin
Session: Poster Display session 3
Resources:
Abstract
2368 - Association Between Depth of Response and Overall Survival: Exploratory Analysis in Patients With Previously Untreated Advanced Renal Cell Carcinoma (aRCC) in CheckMate 214
Presenter: Viktor Grünwald
Session: Poster Display session 3
Resources:
Abstract
6008 - Quality of life in previously untreated patients with advanced renal cell carcinoma (aRCC) in CheckMate 214: updated results
Presenter: David Cella
Session: Poster Display session 3
Resources:
Abstract