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
5368 - Durvalumab and Paclitaxel Combination for treatment of metastatic triple negative breast cancer is safe with very promising efficacy
Presenter: Hazem Ghebeh
Session: Poster Display session 3
Resources:
Abstract
1520 - A prospective cohort study on the pharmacokinetics of nivolumab in metastatic non-small cell lung cancer, melanoma, and renal cell cancer patients
Presenter: Daan Hurkmans
Session: Poster Display session 3
Resources:
Abstract
1603 - Safety and clinical activity of subcutaneously (SC) administered anti-PD-1 antibody PF-06801591 in phase I dose-expansion cohorts of locally advanced or metastatic non-small-cell lung cancer (NSCLC) and urothelial carcinoma (UC)
Presenter: Byoung Cho
Session: Poster Display session 3
Resources:
Abstract
3922 - Development of the Functional Assessment of Cancer Therapy-Immune Checkpoint Modulator (FACT-ICM): A scale to measure quality of life in cancer patients treated with ICMs
Presenter: Aaron Hansen
Session: Poster Display session 3
Resources:
Abstract
2408 - Immune checkpoint inhibitors (ICIs) as “chemotherapy (Ctx) sensitization” strategy in advanced solid tumors
Presenter: Francisco Javier Ros Montana
Session: Poster Display session 3
Resources:
Abstract
3612 - Validation of progression-free survival (PFS) as surrogate endpoint in randomised trials of immune checkpoint inhibitors in advanced solid cancers
Presenter: Peey Sei Kok
Session: Poster Display session 3
Resources:
Abstract
3827 - Pharmacokinetic (PK) analysis of weight-based and fixed dose cemiplimab in patients (pts) with advanced malignancies
Presenter: Michael Migden
Session: Poster Display session 3
Resources:
Abstract
2120 - A burst of highly differentiated CD4 TL identifies a subset of fast progressors, and correlates with hyperprogressive disease in NSCLC patients treated with ICI
Presenter: Hugo Arasanz
Session: Poster Display session 3
Resources:
Abstract
4254 - Nivolumab treatment in advanced non-small cell lung cancer (aNSCLC): a French nationwide retrospective cohort (UNIVOC Study)
Presenter: Christos Chouaid
Session: Poster Display session 3
Resources:
Abstract
1084 - Dissociated responses in patients with metastatic solid tumors treated with immunotherapy
Presenter: Pauline Vaflard
Session: Poster Display session 3
Resources:
Abstract