Frontiers in Oncology (Oct 2020)
A Deep Learning Approach Validates Genetic Risk Factors for Late Toxicity After Prostate Cancer Radiotherapy in a REQUITE Multi-National Cohort
- Michela Carlotta Massi,
- Michela Carlotta Massi,
- Francesca Gasperoni,
- Francesca Ieva,
- Francesca Ieva,
- Francesca Ieva,
- Anna Maria Paganoni,
- Anna Maria Paganoni,
- Anna Maria Paganoni,
- Paolo Zunino,
- Andrea Manzoni,
- Nicola Rares Franco,
- Liv Veldeman,
- Liv Veldeman,
- Piet Ost,
- Piet Ost,
- Valérie Fonteyne,
- Valérie Fonteyne,
- Christopher J. Talbot,
- Tim Rattay,
- Adam Webb,
- Paul R. Symonds,
- Kerstie Johnson,
- Maarten Lambrecht,
- Karin Haustermans,
- Gert De Meerleer,
- Dirk de Ruysscher,
- Dirk de Ruysscher,
- Ben Vanneste,
- Evert Van Limbergen,
- Evert Van Limbergen,
- Ananya Choudhury,
- Rebecca M. Elliott,
- Elena Sperk,
- Carsten Herskind,
- Marlon R. Veldwijk,
- Barbara Avuzzi,
- Tommaso Giandini,
- Riccardo Valdagni,
- Riccardo Valdagni,
- Riccardo Valdagni,
- Alessandro Cicchetti,
- David Azria,
- Marie-Pierre Farcy Jacquet,
- Barry S. Rosenstein,
- Barry S. Rosenstein,
- Richard G. Stock,
- Kayla Collado,
- Ana Vega,
- Ana Vega,
- Ana Vega,
- Miguel Elías Aguado-Barrera,
- Miguel Elías Aguado-Barrera,
- Patricia Calvo,
- Patricia Calvo,
- Alison M. Dunning,
- Laura Fachal,
- Laura Fachal,
- Sarah L. Kerns,
- Debbie Payne,
- Jenny Chang-Claude,
- Jenny Chang-Claude,
- Petra Seibold,
- Catharine M. L. West,
- Tiziana Rancati
Affiliations
- Michela Carlotta Massi
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Michela Carlotta Massi
- Center for Analysis, Decisions and Society, Human Technopole, Milan, Italy
- Francesca Gasperoni
- Medical Research Council-Biostatistic Unit, University of Cambridge, Cambridge, United Kingdom
- Francesca Ieva
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Francesca Ieva
- Center for Analysis, Decisions and Society, Human Technopole, Milan, Italy
- Francesca Ieva
- CHRP-National Center for Healthcare Research and Pharmacoepidemiology, University of Milano-Bicocca, Milan, Italy
- Anna Maria Paganoni
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Anna Maria Paganoni
- Center for Analysis, Decisions and Society, Human Technopole, Milan, Italy
- Anna Maria Paganoni
- CHRP-National Center for Healthcare Research and Pharmacoepidemiology, University of Milano-Bicocca, Milan, Italy
- Paolo Zunino
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Andrea Manzoni
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Nicola Rares Franco
- Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy
- Liv Veldeman
- Department of Human Structure and Repair, Ghent University, Ghent, Belgium
- Liv Veldeman
- Department of Radiation Oncology, Ghent University Hospital, Ghent, Belgium
- Piet Ost
- Department of Human Structure and Repair, Ghent University, Ghent, Belgium
- Piet Ost
- Department of Radiation Oncology, Ghent University Hospital, Ghent, Belgium
- Valérie Fonteyne
- Department of Human Structure and Repair, Ghent University, Ghent, Belgium
- Valérie Fonteyne
- Department of Radiation Oncology, Ghent University Hospital, Ghent, Belgium
- Christopher J. Talbot
- Leicester Cancer Research Centre, Department of Genetics and Genome Biology, University of Leicester, Leicester, United Kingdom
- Tim Rattay
- Leicester Cancer Research Centre, Department of Genetics and Genome Biology, University of Leicester, Leicester, United Kingdom
- Adam Webb
- Leicester Cancer Research Centre, Department of Genetics and Genome Biology, University of Leicester, Leicester, United Kingdom
- Paul R. Symonds
- Leicester Cancer Research Centre, Department of Genetics and Genome Biology, University of Leicester, Leicester, United Kingdom
- Kerstie Johnson
- Leicester Cancer Research Centre, Department of Genetics and Genome Biology, University of Leicester, Leicester, United Kingdom
- Maarten Lambrecht
- Department of Radiation Oncology, University Hospitals Leuven, Leuven, Belgium
- Karin Haustermans
- Department of Radiation Oncology, University Hospitals Leuven, Leuven, Belgium
- Gert De Meerleer
- Department of Radiation Oncology, University Hospitals Leuven, Leuven, Belgium
- Dirk de Ruysscher
- Maastricht University Medical Center, Maastricht, Netherlands
- Dirk de Ruysscher
- 0Department of Radiation Oncology (Maastro), GROW Institute for Oncology and Developmental Biology, Maastricht, Netherlands
- Ben Vanneste
- 0Department of Radiation Oncology (Maastro), GROW Institute for Oncology and Developmental Biology, Maastricht, Netherlands
- Evert Van Limbergen
- Maastricht University Medical Center, Maastricht, Netherlands
- Evert Van Limbergen
- 0Department of Radiation Oncology (Maastro), GROW Institute for Oncology and Developmental Biology, Maastricht, Netherlands
- Ananya Choudhury
- 1Translational Radiobiology Group, Division of Cancer Sciences, Manchester Academic Health Science Centre, Christie Hospital, University of Manchester, Manchester, United Kingdom
- Rebecca M. Elliott
- 1Translational Radiobiology Group, Division of Cancer Sciences, Manchester Academic Health Science Centre, Christie Hospital, University of Manchester, Manchester, United Kingdom
- Elena Sperk
- 2Department of Radiation Oncology, Universitätsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Carsten Herskind
- 2Department of Radiation Oncology, Universitätsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Marlon R. Veldwijk
- 2Department of Radiation Oncology, Universitätsmedizin Mannheim, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Barbara Avuzzi
- 3Department of Radiation Oncology 1, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- Tommaso Giandini
- 4Department of Medical Physics, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- Riccardo Valdagni
- 3Department of Radiation Oncology 1, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- Riccardo Valdagni
- 5Department of Oncology and Haemato-Oncology, University of Milan, Milan, Italy
- Riccardo Valdagni
- 6Prostate Cancer Program, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- Alessandro Cicchetti
- 6Prostate Cancer Program, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- David Azria
- 7Department of Radiation Oncology, University Federation of Radiation Oncology, Montpellier Cancer Institute, Univ Montpellier MUSE, Grant INCa_Inserm_DGOS_12553, Inserm U1194, Montpellier, France
- Marie-Pierre Farcy Jacquet
- 8Department of Radiation Oncology, University Federation of Radiation Oncology, CHU Caremeau, Nîmes, France
- Barry S. Rosenstein
- 9Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, United States
- Barry S. Rosenstein
- 0Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States
- Richard G. Stock
- 9Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, United States
- Kayla Collado
- 9Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, United States
- Ana Vega
- 1Fundación Pública Galega de Medicina Xenómica, Grupo de Medicina Xenómica (USC), Santiago de Compostela, Spain
- Ana Vega
- 2Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
- Ana Vega
- 3Biomedical Network on Rare Diseases (CIBERER), Madrid, Spain
- Miguel Elías Aguado-Barrera
- 1Fundación Pública Galega de Medicina Xenómica, Grupo de Medicina Xenómica (USC), Santiago de Compostela, Spain
- Miguel Elías Aguado-Barrera
- 2Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
- Patricia Calvo
- 2Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
- Patricia Calvo
- 4Department of Radiation Oncology, Complexo Hospitalario Universitario de Santiago, SERGAS, Santiago de Compostela, Spain
- Alison M. Dunning
- 5Strangeways Research Labs, Department of Oncology, Centre for Cancer Genetic Epidemiology, University of Cambridge, Cambridge, United Kingdom
- Laura Fachal
- 5Strangeways Research Labs, Department of Oncology, Centre for Cancer Genetic Epidemiology, University of Cambridge, Cambridge, United Kingdom
- Laura Fachal
- 6Wellcome Sanger Institute, Wellcome Genome Campus, Hinxton, United Kingdom
- Sarah L. Kerns
- 7Departments of Radiation Oncology and Surgery, University of Rochester Medical Center, Rochester, New York, NY, United States
- Debbie Payne
- 8Centre for Integrated Genomic Medical Research (CIGMR), University of Manchester, Manchester, United Kingdom
- Jenny Chang-Claude
- 9Division of Cancer Epidemiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Jenny Chang-Claude
- 0University Cancer Center Hamburg, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
- Petra Seibold
- 9Division of Cancer Epidemiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Catharine M. L. West
- 1Translational Radiobiology Group, Division of Cancer Sciences, Manchester Academic Health Science Centre, Christie Hospital, University of Manchester, Manchester, United Kingdom
- Tiziana Rancati
- 6Prostate Cancer Program, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- DOI
- https://doi.org/10.3389/fonc.2020.541281
- Journal volume & issue
-
Vol. 10
Abstract
Background: REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side effects and improve QUalITy of lifE in cancer survivors) is an international prospective cohort study. The purpose of this project was to analyse a cohort of patients recruited into REQUITE using a deep learning algorithm to identify patient-specific features associated with the development of toxicity, and test the approach by attempting to validate previously published genetic risk factors.Methods: The study involved REQUITE prostate cancer patients treated with external beam radiotherapy who had complete 2-year follow-up. We used five separate late toxicity endpoints: ≥grade 1 late rectal bleeding, ≥grade 2 urinary frequency, ≥grade 1 haematuria, ≥ grade 2 nocturia, ≥ grade 1 decreased urinary stream. Forty-three single nucleotide polymorphisms (SNPs) already reported in the literature to be associated with the toxicity endpoints were included in the analysis. No SNP had been studied before in the REQUITE cohort. Deep Sparse AutoEncoders (DSAE) were trained to recognize features (SNPs) identifying patients with no toxicity and tested on a different independent mixed population including patients without and with toxicity.Results: One thousand, four hundred and one patients were included, and toxicity rates were: rectal bleeding 11.7%, urinary frequency 4%, haematuria 5.5%, nocturia 7.8%, decreased urinary stream 17.1%. Twenty-four of the 43 SNPs that were associated with the toxicity endpoints were validated as identifying patients with toxicity. Twenty of the 24 SNPs were associated with the same toxicity endpoint as reported in the literature: 9 SNPs for urinary symptoms and 11 SNPs for overall toxicity. The other 4 SNPs were associated with a different endpoint.Conclusion: Deep learning algorithms can validate SNPs associated with toxicity after radiotherapy for prostate cancer. The method should be studied further to identify polygenic SNP risk signatures for radiotherapy toxicity. The signatures could then be included in integrated normal tissue complication probability models and tested for their ability to personalize radiotherapy treatment planning.
Keywords