Skip to content

Subclonal reconstruction of tumors by using machine learning and population genetics

Human Technopole
Home Microscope
  • Facebook
  • Twitter
  • Bluesky
  • Instagram
  • LinkedIn
  • YouTube
  • Flickr
EN / IT
  • HOME
  • About us
    • Our Mission
    • Governance
  • News & outreach
  • Join us
  • People
  • Research
    • Groups
      • ALL GROUPS
      • Genomics
        • Bienko Group
        • Calviello Group
        • Carninci Group
        • Domínguez Conde Group
        • Giustacchini Group
        • Glastonbury Group
        • Legnini Group
        • Soranzo Group
        • Soskic Group
      • Neurogenomics
        • Davila-Velderrain Group
        • Harschnitz Group
        • Kalebic Group
        • Taverna Group
        • Testa Group
      • Structural biology
        • Casañal Group
        • Coscia Group
        • Erdmann Group
        • Pigino Group
        • Vannini Group
      • Computational biology
        • Iorio Group
        • Jug Group
        • Pinheiro Group
        • Sottoriva Group
      • Health Data Science
        • Di Angelantonio & Ieva Group
        • Zuccolo Group
      • Molecular Cell Biology
        • Zerial Group
      • Biophysical Modelling and Simulation
    • Flagship Programmes
      • Cardiovascular & Metabolic Diseases
      • Multimodal AI Across Scales
      • Immunogenomics, Cancer & Infections
      • Neurodevelopmental and Neuropsychiatric Conditions
      • Ciliopathies
    • Collaborations
  • Infrastructure
    • National Facilities
      • All National Facilities
      • Genomics
      • Genome Engineering & Disease Modelling
      • Structural Biology
      • Light Imaging
      • Data Handling & Analysis
  • Training
    • External Training
    • Internal Training
  • Tech Transfer
    • Centre for Innovation & Tech Transfer
  • Switch to light modeSwitch to dark mode
  • Versione italiana
  • Colour mode
  • Home
  • Publications
  • Subclonal reconstruction of tumors by using machine learning and population genetics
09/2020 - Nature Genetics

Subclonal reconstruction of tumors by using machine learning and population genetics

Authors:

  • Giulio Caravagna, Timon Heide, Marc J. Williams, Luis Zapata, Daniel Nichol, Ketevan Chkhaidze, William Cross, George D. Cresswell, Benjamin Werner, Ahmet Acar, Louis Chesler, Chris P. Barnes, Guido Sanguinetti, Trevor A. Graham,
  • Sottoriva A.

Abstract:

Most cancer genomic data are generated from bulk samples composed of mixtures of cancer subpopulations, as well as normal cells. Subclonal reconstruction methods based on machine learning aim to separate those subpopulations in a sample and infer their evolutionary history. However, current approaches are entirely data driven and agnostic to evolutionary theory. We demonstrate that systematic errors occur in the analysis if evolution is not accounted for, and this is exacerbated with multi-sampling of the same tumor. We present a novel approach for model-based tumor subclonal reconstruction, called MOBSTER, which combines machine learning with theoretical population genetics. Using public whole-genome sequencing data from 2,606 samples from different cohorts, new data and synthetic validation, we show that this method is more robust and accurate than current techniques in single-sample, multiregion and longitudinal data. This approach minimizes the confounding factors of nonevolutionary methods, thus leading to more accurate recovery of the evolutionary history of human cancers.

  • Facebook
  • Twitter
  • LinkedIn
  • Email

Links:

  • Link
  • How to reach us
  • Press room
  • Newsletter
    • Facebook
    • Twitter
    • Bluesky
    • Instagram
    • LinkedIn
    • YouTube
    • Flickr
    • Transparent Administration
    • Tenders
    • Whistleblowing
    • HT Intranet
    • Privacy
    • Cookie Policy
    • Social Media Policy
    • Manage Cookies
    Human Technopole
    Fondazione Human Technopole - Viale Rita Levi-Montalcini, 1 - Area MIND - 20157 Milano Italy - C.F. 97821360159 - PEC: [email protected]
    Manage Cookie Consent
    This website uses technical cookies to provide you with a better browsing experience and, subject to your consent, profiling cookies to offer you information and advertising in line with your preferences. For more details, you can consult our cookie policy by clicking on the link below, or set your preferences by clicking "set preferences". By selecting "accept cookies" you consent to the use of all types of cookies while you can revoke your consent by clicking on "refuse". By deciding to refuse or closing the banner, only the technical cookies necessary for the correct functioning of the site will be activated.
    Technical cookies (required) Always active
    The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
    Preferences
    The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
    Third party cookies for statistics
    The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
    Third party cookies for profiling
    The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
    Manage options Manage services Manage {vendor_count} vendors Read more about these purposes
    Set preferences
    {title} {title} {title}