10
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In cancer, the primary tumour’s organ of origin and histopathology are the strongest determinants of its clinical behaviour, but in 3% of cases a patient presents with a metastatic tumour and no obvious primary. Here, as part of the ICGC/TCGA Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium, we train a deep learning classifier to predict cancer type based on patterns of somatic passenger mutations detected in whole genome sequencing (WGS) of 2606 tumours representing 24 common cancer types produced by the PCAWG Consortium. Our classifier achieves an accuracy of 91% on held-out tumor samples and 88% and 83% respectively on independent primary and metastatic samples, roughly double the accuracy of trained pathologists when presented with a metastatic tumour without knowledge of the primary. Surprisingly, adding information on driver mutations reduced accuracy. Our results have clinical applicability, underscore how patterns of somatic passenger mutations encode the state of the cell of origin, and can inform future strategies to detect the source of circulating tumour DNA.

          Abstract

          Some cancer patients first present with metastases where the location of the primary is unidentified; these are difficult to treat. In this study, using machine learning, the authors develop a method to determine the tissue of origin of a cancer based on whole sequencing data.

          Related collections

          Most cited references18

          • Record: found
          • Abstract: found
          • Article: not found

          Cell-of-origin chromatin organization shapes the mutational landscape of cancer

          Cancer is a disease potentiated by mutations in somatic cells. Cancer mutations are not distributed uniformly along the genome. Instead, different genomic regions vary by up to 5-fold in the local density of somatic mutations 1 , posing a fundamental problem for statistical methods of cancer genomics. Epigenomic organization has been proposed as a major determinant of the cancer mutational landscape 1-5 . However, both somatic mutagenesis and epigenomic features are highly cell-type-specific 6,7 . We investigated the distribution of mutations in multiple samples of diverse cancer types and compared them to cell-type-specific epigenomic features. Here, we show that chromatin accessibility and modification, together with replication timing, explain up to 86% of the variance in mutation rates along cancer genomes. Overwhelmingly, the best predictors of local somatic mutation density are epigenomic features derived from the most likely cell type of origin of the corresponding malignancy. Moreover, we find that cell-of-origin chromatin features are much stronger determinants of cancer mutation profiles than chromatin features of cognate cancer cell lines. We show further that the cell type of origin of a cancer can be accurately determined based on the distribution of mutations along its genome. Thus, DNA sequence of a cancer genome encompasses a wealth of information about the identity and epigenomic features of its cell of origin.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Genomics-Driven Precision Medicine for Advanced Pancreatic Cancer: Early Results from the COMPASS Trial

            Purpose: To perform real-time whole genome sequencing (WGS) and RNA sequencing (RNASeq) of advanced pancreatic ductal adenocarcinoma (PDAC) to identify predictive mutational and transcriptional features for better treatment selection.Experimental Design: Patients with advanced PDAC were prospectively recruited prior to first-line combination chemotherapy. Fresh tumor tissue was acquired by image-guided percutaneous core biopsy for WGS and RNASeq. Laser capture microdissection was performed for all cases. Primary endpoint was feasibility to report WGS results prior to first disease assessment CT scan at 8 weeks. The main secondary endpoint was discovery of patient subsets with predictive mutational and transcriptional signatures.Results: Sixty-three patients underwent a tumor biopsy between December 2015 and June 2017. WGS and RNASeq were successful in 62 (98%) and 60 (95%), respectively. Genomic results were reported at a median of 35 days (range, 19-52 days) from biopsy, meeting the primary feasibility endpoint. Objective responses to first-line chemotherapy were significantly better in patients with the classical PDAC RNA subtype compared with those with the basal-like subtype (P = 0.004). The best progression-free survival was observed in those with classical subtype treated with m-FOLFIRINOX. GATA6 expression in tumor measured by RNA in situ hybridization was found to be a robust surrogate biomarker for differentiating classical and basal-like PDAC subtypes. Potentially actionable genetic alterations were found in 30% of patients.Conclusions: Prospective genomic profiling of advanced PDAC is feasible, and our early data indicate that chemotherapy response differs among patients with different genomic/transcriptomic subtypes. Clin Cancer Res; 24(6); 1344-54. ©2017 AACR.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Diagnostic and therapeutic management of cancer of an unknown primary.

              Metastatic Cancer of Unknown Primary Site (CUP) accounts for approximately 3% of all malignant neoplasms and is therefore one of the 10 most frequent cancer diagnoses in man. Patients with CUP present with metastatic disease for which the site of origin cannot be identified at the time of diagnosis. It is now accepted that CUP represents a heterogeneous group of malignancies that share a unique clinical behaviour and, presumably, unique biology. The following clinicopathological entities have been recognised: (i) metastatic CUP primarily to the liver or to multiple sites, (ii) metastatic CUP to lymph nodes including the sub-sets involving primarily the mediastinal-retroperitoneal, the axillary, the cervical or the inguinal nodes, (iii) metastatic CUP of peritoneal cavity including the peritoneal papillary serous carcinomatosis in females and the peritoneal non-papillary carcinomatosis in males or females, (iv) metastatic CUP to the lungs with parenchymal metastases or isolated malignant pleural effusion, (v) metastatic CUP to the bones, (vi) metastatic CUP to the brain, (vii) metastatic neuroendocrine carcinomas and (viii) metastatic melanoma of an unknown primary. Extensive work-up with specific pathology investigations (immunohistochemistry, electron microscopy, molecular diagnosis) and modern imaging technology (computed tomography (CT), mammography, Positron Emission Tomography (PET) scan) have resulted in some improvements in diagnosis; however, the primary site remains unknown in most patients, even on autopsy. The most frequently detected primaries are carcinomas hidden in the lung or pancreas. Several favourable sub-sets of CUP have been identified, which are responsive to systemic chemotherapy and/or locoregional treatment. Identification and treatment of these patients is of paramount importance. The considered responsive sub-sets to platinum-based chemotherapy are the poorly differentiated carcinomas involving the mediastinal-retroperitoneal nodes, the peritoneal papillary serous adenocarcinomatosis in females and the poorly differentiated neuroendocrine carcinomas. Other tumours successfully managed by locoregional treatment with surgery and/or irradiation are the metastatic adenocarcinoma of isolated axillary nodes, metastatic squamous cell carcinoma of cervical nodes, or any other single metastatic site. Empirical chemotherapy benefits some of the patients who do not fit into any favourable sub-set, and should be considered in patients with a good performance status.
                Bookmark

                Author and article information

                Contributors
                lincoln.stein@gmail.com
                Journal
                Nat Commun
                Nat Commun
                Nature Communications
                Nature Publishing Group UK (London )
                2041-1723
                5 February 2020
                5 February 2020
                2020
                : 11
                : 728
                Affiliations
                [1 ]ISNI 0000 0004 0626 690X, GRID grid.419890.d, Ontario Institute for Cancer Research, ; Toronto, ON M5G0A3 Canada
                [2 ]ISNI 0000 0001 2157 2938, GRID grid.17063.33, Department of Molecular Genetics, , University of Toronto, ; Toronto, ON Canada
                [3 ]GRID grid.494618.6, Vector Institute, ; Toronto, ON Canada
                [4 ]ISNI 0000 0001 0670 2351, GRID grid.59734.3c, Department of Oncological Sciences, , Icahn School of Medicine at Mount Sinai, ; 15 1425 Madison Ave., New York, NY 10029 USA
                [5 ]ISNI 0000 0001 0657 4636, GRID grid.4808.4, Bioinformatics Group, Division of Molecular Biology, Department of Biology, Faculty of Science, , University of Zagreb, ; Horvatovac 102a, Zagreb, Croatia
                [6 ]Hartwig Medical Foundation, Science Park 408, Amsterdam, The Netherlands
                [7 ]ISNI 0000000090126352, GRID grid.7692.a, Center for Molecular Medicine and Oncode Institute, , University Medical Center Utrecht, ; Utrecht, The Netherlands
                [8 ]ISNI 0000000090126352, GRID grid.7692.a, Center for Molecular Medicine, , University Medical Center Utrecht, ; Utrecht, The Netherlands
                [9 ]ISNI 0000 0004 0444 9382, GRID grid.10417.33, Radboud University Medical Center, ; Nijmegen, The Netherlands
                [10 ]ISNI 000000040459992X, GRID grid.5645.2, Department of Medical Oncology, Erasmus MC Cancer Institute, , University Medical Center Rotterdam, ; Dr. Molewaterplein 40, 3015 GD Rotterdam, The Netherlands
                [11 ]GRID grid.430814.a, Department of Medical Oncology, , The Netherlands Cancer Institute, ; Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands
                [12 ]GRID grid.66859.34, The Broad Institute of MIT and Harvard, ; Cambridge, MA 02142 USA
                [13 ]ISNI 0000 0001 2157 2938, GRID grid.17063.33, Department of Computer Science, , University of Toronto, ; Toronto, ON Canada
                [14 ]ISNI 0000 0001 2157 2938, GRID grid.17063.33, Donnelly Centre, , University of Toronto, ; Toronto, ON Canada
                [15 ]ISNI 0000 0000 8700 1153, GRID grid.7719.8, Bioinformatics Unit, , Spanish National Cancer Research Centre (CNIO), ; Madrid, 28029 Spain
                [16 ]ISNI 0000 0004 0626 690X, GRID grid.419890.d, Computational Biology Program, , Ontario Institute for Cancer Research, ; Toronto, ON M5G 0A3 Canada
                [17 ]ISNI 0000 0001 2193 314X, GRID grid.8756.c, University of Glasgow, CRUK Beatson Institute for Cancer Research, Bearsden, ; Glasgow, G61 1BD UK
                [18 ]ISNI 0000 0004 4902 0432, GRID grid.1005.4, South Western Sydney Clinical School, Faculty of Medicine, , University of NSW, ; Liverpool, NSW 2170 Australia
                [19 ]ISNI 0000 0004 4902 0432, GRID grid.1005.4, The Kinghorn Cancer Centre, Cancer Division, Garvan Institute of Medical Research, , University of NSW, ; Sydney, NSW 2010 Australia
                [20 ]ISNI 0000 0000 9825 7840, GRID grid.411714.6, West of Scotland Pancreatic Unit, , Glasgow Royal Infirmary, ; Glasgow, G31 2ER UK
                [21 ]ISNI 0000 0001 2193 314X, GRID grid.8756.c, Wolfson Wohl Cancer Research Centre, Institute of Cancer Sciences, , University of Glasgow, Bearsden, ; Glasgow, G61 1QH UK
                [22 ]ISNI 0000 0001 2157 2938, GRID grid.17063.33, Department of Medical Biophysics, , University of Toronto, ; Toronto, ON M5S 1A8 Canada
                [23 ]ISNI 0000 0001 2157 2938, GRID grid.17063.33, Department of Pharmacology, , University of Toronto, ; Toronto, ON M5S 1A8 Canada
                [24 ]ISNI 0000 0000 9632 6718, GRID grid.19006.3e, University of California Los Angeles, ; Los Angeles, CA 90095 USA
                [25 ]Wellcome Sanger Institute, Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SA UK
                [26 ]ISNI 0000000121885934, GRID grid.5335.0, Department of Haematology, , University of Cambridge, ; Cambridge, CB2 2XY UK
                [27 ]ISNI 0000 0004 0386 9924, GRID grid.32224.35, Massachusetts General Hospital, ; Boston, MA 02114 USA
                [28 ]ISNI 000000041936877X, GRID grid.5386.8, Weill Cornell Medical College, ; New York, NY 10065 USA
                [29 ]ISNI 0000 0001 2106 9910, GRID grid.65499.37, Dana-Farber Cancer Institute, ; Boston, MA 02215 USA
                [30 ]GRID grid.66859.34, Broad Institute of MIT and Harvard, ; Cambridge, MA 02142 USA
                [31 ]ISNI 0000 0004 0386 9924, GRID grid.32224.35, Center for Cancer Research, , Massachusetts General Hospital, ; Boston, MA 02129 USA
                [32 ]ISNI 0000 0004 0386 9924, GRID grid.32224.35, Department of Pathology, , Massachusetts General Hospital, ; Boston, MA 02115 USA
                [33 ]ISNI 000000041936754X, GRID grid.38142.3c, Harvard Medical School, ; Boston, MA 02115 USA
                [34 ]ISNI 0000 0001 2179 088X, GRID grid.1008.9, University of Melbourne Centre for Cancer Research, , The University of Melbourne, ; Melbourne, VIC 3052 Australia
                [35 ]ISNI 0000000122483208, GRID grid.10698.36, Department of Genetics, , University of North Carolina at Chapel Hill, ; Chapel Hill, NC 27599 USA
                [36 ]ISNI 0000000122483208, GRID grid.10698.36, Lineberger Comprehensive Cancer Center, , University of North Carolina at Chapel Hill, ; Chapel Hill, NC 27599 USA
                [37 ]ISNI 0000 0004 1936 7988, GRID grid.4305.2, MRC Human Genetics Unit, MRC IGMM, , University of Edinburgh, ; Edinburgh, EH4 2XU UK
                [38 ]ISNI 0000 0001 2168 5385, GRID grid.272242.3, Department of Bioinformatics, , Research Institute, National Cancer Center Japan, ; Tokyo, 104-0045 Japan
                [39 ]ISNI 0000 0001 2291 4776, GRID grid.240145.6, Departments of Pathology, Genomic Medicine, and Translational Molecular Pathology, , The University of Texas MD Anderson Cancer Center, ; Houston, TX 77030 USA
                [40 ]ISNI 0000 0000 9758 5690, GRID grid.5288.7, Oregon Health & Science University, ; Portland, OR 97239 USA
                [41 ]ISNI 0000 0001 2193 314X, GRID grid.8756.c, University of Glasgow, ; Glasgow, G61 1BD UK
                [42 ]ISNI 0000 0004 0626 690X, GRID grid.419890.d, Genome Informatics Program, , Ontario Institute for Cancer Research, ; Toronto, ON M5G 0A3 Canada
                [43 ]ISNI 0000000121885934, GRID grid.5335.0, Academic Department of Medical Genetics, , University of Cambridge, Addenbrooke’s Hospital, ; Cambridge, CB2 0QQ UK
                [44 ]ISNI 0000000121885934, GRID grid.5335.0, MRC Cancer Unit, , University of Cambridge, ; Cambridge, CB2 0XZ UK
                [45 ]ISNI 0000000121885934, GRID grid.5335.0, The University of Cambridge School of Clinical Medicine, ; Cambridge, CB2 0SP UK
                [46 ]ISNI 0000 0004 6023 5303, GRID grid.430406.5, Sage Bionetworks, ; Seattle, WA 98109 USA
                [47 ]ISNI 0000 0001 2297 6811, GRID grid.266102.1, Department of Radiation Oncology, , University of California San Francisco, ; San Francisco, CA 94518 USA
                [48 ]ISNI 0000 0001 0726 5157, GRID grid.5734.5, Bern Center for Precision Medicine, , University Hospital of Bern, University of Bern, ; Bern, 3008 Switzerland
                [49 ]ISNI 0000 0001 0726 5157, GRID grid.5734.5, Department for Biomedical Research, , University of Bern, ; Bern, 3008 Switzerland
                [50 ]ISNI 000000041936877X, GRID grid.5386.8, Englander Institute for Precision Medicine, , Weill Cornell Medicine and NewYork Presbyterian Hospital, ; New York, NY 10021 USA
                [51 ]ISNI 000000041936877X, GRID grid.5386.8, Meyer Cancer Center, , Weill Cornell Medicine, ; New York, NY 10065 USA
                [52 ]ISNI 000000041936877X, GRID grid.5386.8, Pathology and Laboratory, , Weill Cornell Medical College, ; New York, NY 10021 USA
                [53 ]ISNI 0000 0001 2168 5385, GRID grid.272242.3, Division of Cancer Genomics, , National Cancer Center Research Institute, ; Tokyo, 104-0045 Japan
                [54 ]ISNI 0000 0001 2151 536X, GRID grid.26999.3d, Laboratory of Molecular Medicine, Human Genome Center, The Institute of Medical Science, , The University of Tokyo, Minato-ku, ; Tokyo, 108-8639 Japan
                [55 ]ISNI 0000 0001 2153 9986, GRID grid.9764.c, Human Genetics, , University of Kiel, ; Kiel, 24118 Germany
                [56 ]GRID grid.410712.1, Institute of Human Genetics, , Ulm University and Ulm University Medical Center, ; Ulm, 89081 Germany
                [57 ]GRID grid.11478.3b, CNAG-CRG, Centre for Genomic Regulation (CRG), Barcelona Institute of Science and Technology (BIST), ; Barcelona, 08028 Spain
                [58 ]ISNI 0000 0001 2172 2676, GRID grid.5612.0, Universitat Pompeu Fabra (UPF), ; Barcelona, 08003 Spain
                [59 ]ISNI 0000 0004 0393 3981, GRID grid.301713.7, MRC-University of Glasgow Centre for Virus Research, ; Glasgow, G61 1QH UK
                [60 ]ISNI 0000 0001 2193 314X, GRID grid.8756.c, Wolfson Wohl Cancer Research Centre, Institute of Cancer Sciences, , University of Glasgow, ; Bearsden, G61 1QH United Kingdom
                [61 ]ISNI 0000000121885934, GRID grid.5335.0, Cancer Research UK Cambridge Institute, , University of Cambridge, ; Cambridge, CB2 0RE UK
                [62 ]ISNI 0000 0001 2193 314X, GRID grid.8756.c, School of Computing Science, , University of Glasgow, ; Glasgow, G12 8RZ UK
                Author information
                http://orcid.org/0000-0003-2817-3117
                http://orcid.org/0000-0002-2153-4488
                http://orcid.org/0000-0002-1291-2897
                http://orcid.org/0000-0002-0828-3477
                http://orcid.org/0000-0003-0466-2928
                http://orcid.org/0000-0002-0936-0753
                http://orcid.org/0000-0002-2760-6999
                Article
                13825
                10.1038/s41467-019-13825-8
                7002586
                32024849
                18b5b575-9c69-4572-ba47-30654fdcc851
                © The Author(s) 2020

                Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

                History
                : 27 November 2017
                : 26 November 2019
                Categories
                Article
                Custom metadata
                © The Author(s) 2020

                Uncategorized
                cancer genomics,cancer of unknown primary
                Uncategorized
                cancer genomics, cancer of unknown primary

                Comments

                Comment on this article