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
5650 - Tissue-based activation of mucosal-associated invariant T (MAIT) cells in combination ipilimumab and nivolumab checkpoint inhibitor (CI) colitis.
Presenter: Sarah Sasson
Session: Poster Display session 3
Resources:
Abstract
5944 - Significance of severe immune-related adverse effects (irAE) on patients with advanced tumors treated with immune checkpoint inhibitors being admitted for secondary toxicity: Clinical relevance and next steps
Presenter: Leyre Zubiri
Session: Poster Display session 3
Resources:
Abstract
5989 - Implementation of a dedicated immuno-oncology toxicity service reduces the acute impact of immune-related adverse events
Presenter: Anna Olsson-Brown
Session: Poster Display session 3
Resources:
Abstract
3267 - Cardiotoxic and pro-inflammatory effects induced by the association of immune checkpoint inhibitor Pembrolizumab and Trastuzumab in preclinical models
Presenter: Nicola Maurea
Session: Poster Display session 3
Resources:
Abstract
3417 - Interstitial lung disease associated with immune-checkpoint inhibitors in malignant diseases
Presenter: Akira Yamagata
Session: Poster Display session 3
Resources:
Abstract
2071 - A Phase 1 Study of Intraperitoneal MCY-M11 Anti-Mesothelin CAR for Women with Platinum Resistant High Grade Serous Adenocarcinoma of the Ovary, Primary Peritoneum, or Fallopian Tube, or Subjects with Peritoneal Mesothelioma with Recurrence after Prior Chemotherapy
Presenter: Christina Annunziata
Session: Poster Display session 3
Resources:
Abstract
4935 - Trial in progress: First-in-human study of a novel anti-NY-ESO-1–anti-CD3, TCR-based bispecific (IMCnyeso) as monotherapy in NY-ESO-1/LAGE-1A-positive advanced solid tumors (IMCnyeso-101)
Presenter: Juanita Lopez
Session: Poster Display session 3
Resources:
Abstract
5613 - Nimotuzumab-Cisplatin-Radiation versus Cisplatin-Radiation in HPV negative oropharyngeal cancer
Presenter: Kumar Prabhash
Session: Poster Display session 3
Resources:
Abstract
2576 - Interim analysis of a single arm phase 2 study of adjuvant nivolumab after salvage resection in head and neck squamous cell carcinoma patients previously treated with definitive therapy.
Presenter: Trisha Wise-draper
Session: Poster Display session 3
Resources:
Abstract
4758 - A Phase I Study of the CDK4/6 Inhibitor, Palbociclib in combination with Cetuximab and Intensity Modulated Radiation Therapy (IMRT) for Locally Advanced Squamous Cell Carcinoma of the Head and Neck (SCCHN); A Result of Dose Escalation Cohort
Presenter: Nuttapong Ngamphaiboon
Session: Poster Display session 3
Resources:
Abstract