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
4370 - Continental differences in pathologic response with neoadjuvant ipilimumab (IPI) plus nivolumab (NIVO) in patients with macroscopic stage III melanoma in the phase 2 OpACIN-neo trial.
Presenter: Irene Reijers
Session: Poster Display session 3
Resources:
Abstract
3230 - Comparable responses of melanoma at primary site and synchronous lymph node metastases upon neoadjuvant ipilimumab (IPI) and nivolumab (NIVO)
Presenter: Judith Versluis
Session: Poster Display session 3
Resources:
Abstract
3171 - Adjuvant Therapies for Stage III Melanoma: Benchmarks for Bringing Clinical Trials to Clinical Practice
Presenter: Tina HIEKEN
Session: Poster Display session 3
Resources:
Abstract
3493 - Mixture-cure modeling for resected stage III/IV melanoma in the phase 3 CheckMate 238 trial
Presenter: Jeffrey Weber
Session: Poster Display session 3
Resources:
Abstract
3036 - An open-label, non-randomized, phase IIIb study of trametinib in combination with dabrafenib for patients with unresectable advanced BRAFV600-mutant melanoma: a subgroup analysis of patients with brain metastasis
Presenter: Caroline Dutriaux
Session: Poster Display session 3
Resources:
Abstract
2233 - Adverse event (AE) kinetics in patients (pts) treated with dabrafenib + trametinib (D + T) in the metastatic and adjuvant setting
Presenter: Jean Jacques Grob
Session: Poster Display session 3
Resources:
Abstract
2435 - A Single Arm, Open Label, Phase II, Multicenter Study to Assess the Detection of the BRAF V600 Mutation on cfDNA from Plasma in Patients with Advanced Melanoma
Presenter: Piotr Rutkowski
Session: Poster Display session 3
Resources:
Abstract
1766 - Efficacy and Safety of Dabrafenib and Trametinib in Patients with Metastatic BRAFV600 Mutation-positive Melanoma in the Real-World Setting – Interim results of the non-interventional COMBI-r study
Presenter: Carola Berking
Session: Poster Display session 3
Resources:
Abstract
2131 - Trial update: A randomized Phase Ib/II study of the selective small molecule Axl inhibitor Bemcentinib (BGB324) in combination with either dabrafenib/trametinib (D/T) or pembrolizumab in patients with metastatic melanoma
Presenter: Oddbjørn Straume
Session: Poster Display session 3
Resources:
Abstract
4074 - Analysis of pyrexia in patients (pts) treated with dabrafenib (D) and/or trametinib (T) across clinical trials
Presenter: Caroline Robert
Session: Poster Display session 3
Resources:
Abstract