Deep learning detects cardiotoxicity in a high-content screen with induced pluripotent stem cell-derived cardiomyocytes

Abstract

Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to detect drug-induced toxicity in vitro. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those with potential cardiotoxic liabilities in iPSC-CMs using a single-parameter score based on deep learning. Compounds demonstrating cardiotoxicity in iPSC-CMs included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks that show cardiotoxic signal in iPSC-CMs. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that may protect against diseased phenotypes and deleterious mutations.

Data availability

Our RNA-Seq data has been deposited on the Gene Expression Omnibus (GEO) database. GEO Submission (GSE172181):https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE172181

The following data sets were generated

Article and author information

Author details

  1. Francis Grafton

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Francis Grafton, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  2. Jaclyn Ho

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Jaclyn Ho, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  3. Sara Ranjbarvaziri

    Pediatrics (Cardiology),, Stanford University, Palo Alto, United States
    Competing interests
    No competing interests declared.
  4. Farshad Farshidfar

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Farshad Farshidfar, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  5. Anastasiia Budan

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Anastasiia Budan, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  6. Stephanie Steltzer

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Stephanie Steltzer, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  7. Mahnaz Maddah

    -, Dana Solutions, Palo Alto, United States
    Competing interests
    Mahnaz Maddah, is affiliated with Dana Solutions. The author has no other competing interests to declare..
  8. Kevin E Loewke

    -, Dana Solutions, Palo Alto, United States
    Competing interests
    Kevin E Loewke, is affiliated with Dana Solutions. The author has no other competing interests to declare..
  9. Kristina Green

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Kristina Green, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  10. Snahel Patel

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Snahel Patel, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  11. Tim Hoey

    Drug Discovery, Tenaya Therapeutics, South San Francisco, United States
    Competing interests
    Tim Hoey, is an employee of Tenaya Therapeutics and has stock holdings in the company..
  12. Mohammad Ali Mandegar

    Tenaya Therapeutics, Tenaya Therapeutics, South San Francisco, United States
    For correspondence
    mandegar@tenayathera.com
    Competing interests
    Mohammad Ali Mandegar, is an employee of Tenaya Therapeutics and has stock holdings in the company..
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-5323-7891

Funding

No external funding was received for this work

Reviewing Editor

  1. Arduino A Mangoni, Flinders Medical Centre, Australia

Version history

  1. Preprint posted: March 24, 2021 (view preprint)
  2. Received: March 24, 2021
  3. Accepted: July 27, 2021
  4. Accepted Manuscript published: August 2, 2021 (version 1)
  5. Version of Record published: August 16, 2021 (version 2)

Copyright

© 2021, Grafton et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 4,036
    views
  • 577
    downloads
  • 25
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Francis Grafton
  2. Jaclyn Ho
  3. Sara Ranjbarvaziri
  4. Farshad Farshidfar
  5. Anastasiia Budan
  6. Stephanie Steltzer
  7. Mahnaz Maddah
  8. Kevin E Loewke
  9. Kristina Green
  10. Snahel Patel
  11. Tim Hoey
  12. Mohammad Ali Mandegar
(2021)
Deep learning detects cardiotoxicity in a high-content screen with induced pluripotent stem cell-derived cardiomyocytes
eLife 10:e68714.
https://doi.org/10.7554/eLife.68714

Share this article

https://doi.org/10.7554/eLife.68714

Further reading

    1. Neuroscience
    2. Stem Cells and Regenerative Medicine
    Pascal Forcella, Niklas Ifflander ... Verdon Taylor
    Research Article

    Neural stem cells (NSCs) are multipotent and correct fate determination is crucial to guarantee brain formation and homeostasis. How NSCs are instructed to generate neuronal or glial progeny is not well understood. Here we addressed how murine adult hippocampal NSC fate is regulated and describe how Scaffold Attachment Factor B (SAFB) blocks oligodendrocyte production to enable neuron generation. We found that SAFB prevents NSC expression of the transcription factor Nuclear Factor I/B (NFIB) by binding to sequences in the Nfib mRNA and enhancing Drosha-dependent cleavage of the transcripts. We show that increasing SAFB expression prevents oligodendrocyte production by multipotent adult NSCs, and conditional deletion of Safb increases NFIB expression and oligodendrocyte formation in the adult hippocampus. Our results provide novel insights into a mechanism that controls Drosha functions for selective regulation of NSC fate by modulating the post-transcriptional destabilization of Nfib mRNA in a lineage-specific manner.

    1. Stem Cells and Regenerative Medicine
    Sangeetha Kandoi, Cassandra Martinez ... Deepak A Lamba
    Research Article

    Retinitis pigmentosa (RP), a heterogenous group of inherited retinal disorder, causes slow progressive vision loss with no effective treatments available. Mutations in the rhodopsin gene (RHO) account for ~25% cases of autosomal dominant RP (adRP). In this study, we describe the disease characteristics of the first-ever reported mono-allelic copy number variation (CNV) in RHO as a novel cause of adRP. We (a) show advanced retinal degeneration in a male patient (68 years of age) harboring four transcriptionally active intact copies of rhodopsin, (b) recapitulated the clinical phenotypes using retinal organoids, and (c) assessed the utilization of a small molecule, Photoregulin3 (PR3), as a clinically viable strategy to target and modify disease progression in RP patients associated with RHO-CNV. Patient retinal organoids showed photoreceptors dysgenesis, with rod photoreceptors displaying stunted outer segments with occasional elongated cilia-like projections (microscopy); increased RHO mRNA expression (quantitative real-time PCR [qRT-PCR] and bulk RNA sequencing); and elevated levels and mislocalization of rhodopsin protein (RHO) within the cell body of rod photoreceptors (western blotting and immunohistochemistry) over the extended (300 days) culture time period when compared against control organoids. Lastly, we utilized PR3 to target NR2E3, an upstream regulator of RHO, to alter RHO expression and observed a partial rescue of RHO protein localization from the cell body to the inner/outer segments of rod photoreceptors in patient organoids. These results provide a proof-of-principle for personalized medicine and suggest that RHO expression requires precise control. Taken together, this study supports the clinical data indicating that RHO-CNV associated adRPdevelops as a result of protein overexpression, thereby overloading the photoreceptor post-translational modification machinery.