Posters - Schedules
Posters Home

View Posters By Category

Monday, July 24, between 18:00 CEST and 19:00 CEST
Tuesday, July 25, between 18:00 CEST and 19:00 CEST
Session A Poster Set-up and Dismantle
Session A Posters set up:
Monday, July 24, between 08:00 CEST and 08:45 CEST
Session A Posters dismantle:
Monday, July 24, at 19:00 CEST 		Session B Poster Set-up and Dismantle
Session B Posters set up:
Tuesday, July 25, between 08:00 CEST and 08:45 CEST
Session B Posters dismantle:
Tuesday, July 25, at 19:00 CEST
Wednesday, July 26, between 18:00 CEST and 19:00 CEST
Session C Poster Set-up and Dismantle
Session C Posters set up:
Wednesday, July 26,between 08:00 CEST and 08:45 CEST
Session C Posters dismantle:
Wednesday, July 26, at 19:00 CEST
Virtual
B-384: A Deep Learning System Classifies Cancer Origins Using Somatic Mutation Patterns Detected by Plasma Whole-Genome Sequencing
Track: Bio-Ontologies
  • Xindi Zhang, Ontario Institute for Cancer Research. Department of Molecular Genetics, University of Toronto., Canada
  • Wei Jiao, Ontario Institute for Cancer Research., Canada
  • Gurnit Atwal, University of Toronto, United States
  • Paz Polak, Department of Oncological Sciences, Icahn School of Medicine at Mount Sinai., United States
  • Rosa Karlic, Bioinformatics Group, Division of Molecular Biology, Department of Biology, Faculty of Science, University of Zagreb., Croatia
  • Edwin Cuppen, Hartwig Medical Foundation. Center for Molecular Medicine and Oncode Institute, University Medical Center Utrecht., Netherlands
  • Pcawg Tumor Subtypes And Clinical Translation Working Group, PCAWG Consortium., United States
  • Alexandra Danyi, Center for Molecular Medicine, University Medical Center Utrecht., Netherlands
  • Jeroen de Ridder, Center for Molecular Medicine, University Medical Center Utrecht., Netherlands
  • Carla Van Herpen, Radboud University Medical Center., Netherlands
  • Martijn P. Lolkema, Department of Medical Oncology, Erasmus MC Cancer Institute, University Medical Center Rotterdam., Netherlands
  • Neeltje Steeghs, Department of Medical Oncology, The Netherlands Cancer Institute., Netherlands
  • Gad Getz, The Broad Institute of MIT and Harvard., United States
  • Quaid D. Morris, Sloan Kettering Institute., United States
  • Lincoln D. Stein, Ontario Institute for Cancer Research. Department of Molecular Genetics, University of Toronto., Canada
  • PCAWG Consortium, PCAWG Consortium., United States


Presentation Overview: Show

A cancer's tissue of origin is the most important predictor of its natural history, but is sometimes challenging to identify in patients with metastatic cancer who have had multiple previous primaries, and for patients with early-stage disease identified by liquid biopsy. Our team developed DeepTumour, a deep learning neural network that identifies tumour types based on somatic mutation patterns obtained through tumour whole-genome sequencing (WGS). DeepTumour achieved an accuracy of 91% in discriminating among 24 common cancer types. This project aims to improve and expand DeepTumour to identify tumour types using plasma WGS (pWGS), enabling the characterization of small early cancers and other tumours that cannot be biopsied due to their size or location. To achieve this, we expanded DeepTumour’s training data which allowed it to identify 28 cancer types with 88% accuracy. To assess DeepTumour's performance on pWGS, we generated simulated datasets by randomly subsampling 70%-1% of somatic mutations from tissue-based genomics sets. When providing at least 25% of somatic mutations, the accuracy remained above 80%. These results suggest that DeepTumour holds promise for aiding in diagnosis, treatment decisions, and retrospective research, and may be adapted to pWGS, as pWGS collects at most 70% of somatic mutations.