Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.

Journal: Cancer discovery
Published Date:

Abstract

UNLABELLED: Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time.

Authors

  • Madison Darmofal
    Computational and Systems Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Shalabh Suman
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Gurnit Atwal
    Computational Biology Program, Ontario Institute for Cancer Research, Toronto, ON, Canada.
  • Michael Toomey
    Computational and Systems Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Jie-Fu Chen
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Jason C Chang
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Efsevia Vakiani
    Marie-Josée and Henry R. Kravis Center for Molecular Oncology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Anna M Varghese
    Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Anoop Balakrishnan Rema
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Aijazuddin Syed
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Nikolaus Schultz
    Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
  • Michael F Berger
    Human Oncology and Pathogenesis Program, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Quaid Morris
    Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario M5S 3G4, Canada. Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario M5S 3E1, Canada. Program on Genetic Networks and Program on Neural Computation & Adaptive Perception, Canadian Institute for Advanced Research, Toronto, Ontario M5G 1Z8, Canada. Department of Molecular Genetics, University of Toronto, Toronto, Ontario M5S 1A8, Canada.