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
2655 - The K-BASKET trial: A prospective phase II biomarker-driven multiple basket trial in Korean solid cancer patients.
Presenter: Seul Kim
Session: Poster Display session 3
Resources:
Abstract
5938 - Cambridge Liquid biopsy “CALIBRATION” study: Can changes in circulating tumour DNA (ctDNA) predict durable tumour responses in patients with advanced oesophageal cancer receiving MEDI4736?
Presenter: Constanza Linossi
Session: Poster Display session 3
Resources:
Abstract
3799 - Validation of a tumour mutational burden workflow on routine histological samples of colorectal cancer and assessment of a cohort with synchronous hepatic metastases
Presenter: Andrea Mafficini
Session: Poster Display session 3
Resources:
Abstract
4647 - Microsatellite Instability Testing and Lynch Syndrome Screening For Colorectal Cancer Patients Through Tumor Sequencing
Presenter: Li Liu
Session: Poster Display session 3
Resources:
Abstract
3231 - "Liquid Withdarw" technique in CT-guided cutting needle lung biopsy: decreased incidence of complications and increased tissue amount for lung cancer molecular testing.
Presenter: Xue Wang
Session: Poster Display session 3
Resources:
Abstract
3282 - WGS Implementation in standard cancer Diagnostics for Every cancer patient (WIDE)
Presenter: Paul Roepman
Session: Poster Display session 3
Resources:
Abstract
5905 - Known and unknown gene fusion detection capabilities of solid tumor laboratories conducting next generation sequencing in 6 countries
Presenter: Steph Finucane
Session: Poster Display session 3
Resources:
Abstract
4238 - Clinical and Analytical Accuracy of a 523 Gene Panel Next-Generation Sequencing (NGS) Assay on Formalin-Fixed Paraffin-Embedded (FFPE) Solid Tumor Samples
Presenter: Ina Deras
Session: Poster Display session 3
Resources:
Abstract
2493 - Methylation analysis of MLH1 using droplet digital PCR and methylation sensitive restriction enzyme.
Presenter: Celine De Rop
Session: Poster Display session 3
Resources:
Abstract
2963 - Analytical performance of the Resolution-HRD plasma assay used to identify mCRPC patients with biallelic disruption of DNA repair genes for treatment with niraparib
Presenter: Ira Pekker
Session: Poster Display session 3
Resources:
Abstract