A deep learning algorithm to translate and classify cardiac electrophysiology
- University of California Davis, United States
- Washington University in St. Louis, United States
- University of Shizuoka, Japan
- National Institute of Health Sciences, Japan
- University California Davis, United States
Abstract
The development of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) has been a critical in vitro advance in the study of patient-specific physiology, pathophysiology and pharmacology. We designed a new deep learning multitask network approach intended to address the low throughput, high variability and immature phenotype of the iPSC-CM platform. The rationale for combining translation and classification tasks is because the most likely application of the deep learning technology we describe here is to translate iPSC-CMs following application of a perturbation. The deep learning network was trained using simulated action potential (AP) data and applied to classify cells into the drug-free and drugged categories and to predict the impact of electrophysiological perturbation across the continuum of aging from the immature iPSC-CMs to the adult ventricular myocytes. The phase of the AP extremely sensitive to perturbation due to a steep rise of the membrane resistance was found to contain the key information required for successful network multitasking. We also demonstrated successful translation of both experimental and simulated iPSC-CM AP data validating our network by prediction of experimental drug-induced effects on adult cardiomyocyte APs by the latter.
Data availability
Since we used simulated data, we have made all drugged and drug-free iPSC-CM and adult-CM AP data used for training and testing the multitask network publicly available at Clancy lab Github.(https://github.com/ClancyLabUCD/Multitask_network/tree/master/data). In addition, we have illustrated training and test dataset in Figure1 and Figure5.We have also shared the jupyter notebook for preparing clean and organized data for training the network at Clancy lab Github (https://github.com/ClancyLabUCD/Multitask_network/tree/master/jupyter).We also made experimental data used for the model validation publicly available at Clancy lab Github.(https://github.com/ClancyLabUCD/Multitask_network/blob/master/data/clean_data/experiments.csv ). Figure 7 illustrates the experimental data we used to validate the network.
Article and author information
Author details
Yasunari Kanda Ph.D.
Colleen E Clancy Ph.D.
Funding
Common Fund (OT2OD026580)
- Igor Vorobyov
- Colleen E Clancy Ph.D.
Texas Advanced Computing Center Leadership Resource Allocation (MCB20010)
- Igor Vorobyov
- Colleen E Clancy Ph.D.
Oracle cloud for research allocation
- Igor Vorobyov
- Colleen E Clancy Ph.D.
Common Fund (OT2OD025308‐01S2)
- Parya Aghasafari Ph.D.
American Heart Association (19CDA34770101)
- Igor Vorobyov
National Heart, Lung, and Blood Institute (R01HL152681)
- Igor Vorobyov
- Colleen E Clancy Ph.D.
National Heart, Lung, and Blood Institute (R01HL128170)
- Colleen E Clancy Ph.D.
National Heart, Lung, and Blood Institute (U01HL126273)
- Colleen E Clancy Ph.D.
Department of Physiology and Membrane Biology Research Partnership Fund
- Igor Vorobyov
- Colleen E Clancy Ph.D.
Extreme Science and Engineering Discovery Environment (MCB170095)
- Igor Vorobyov
- Colleen E Clancy Ph.D.
National Center for Supercomputing Applications Blue Waters Broadening Participation Allocation
- Igor Vorobyov
- Colleen E Clancy Ph.D.
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Copyright
© 2021, Aghasafari 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
-
- 2,002
- views
-
- 289
- downloads
-
- 21
- 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)
A deep learning algorithm to translate and classify cardiac electrophysiology
eLife 10:e68335.
https://doi.org/10.7554/eLife.68335
Further reading
-
- Cell Biology
- Computational and Systems Biology
Induced pluripotent stem cell (iPSC) technology is revolutionizing cell biology. However, the variability between individual iPSC lines and the lack of efficient technology to comprehensively characterize iPSC-derived cell types hinder its adoption in routine preclinical screening settings. To facilitate the validation of iPSC-derived cell culture composition, we have implemented an imaging assay based on cell painting and convolutional neural networks to recognize cell types in dense and mixed cultures with high fidelity. We have benchmarked our approach using pure and mixed cultures of neuroblastoma and astrocytoma cell lines and attained a classification accuracy above 96%. Through iterative data erosion, we found that inputs containing the nuclear region of interest and its close environment, allow achieving equally high classification accuracy as inputs containing the whole cell for semi-confluent cultures and preserved prediction accuracy even in very dense cultures. We then applied this regionally restricted cell profiling approach to evaluate the differentiation status of iPSC-derived neural cultures, by determining the ratio of postmitotic neurons and neural progenitors. We found that the cell-based prediction significantly outperformed an approach in which the population-level time in culture was used as a classification criterion (96% vs 86%, respectively). In mixed iPSC-derived neuronal cultures, microglia could be unequivocally discriminated from neurons, regardless of their reactivity state, and a tiered strategy allowed for further distinguishing activated from non-activated cell states, albeit with lower accuracy. Thus, morphological single-cell profiling provides a means to quantify cell composition in complex mixed neural cultures and holds promise for use in the quality control of iPSC-derived cell culture models.
-
- Computational and Systems Biology
- Structural Biology and Molecular Biophysics
Viral adhesion to host cells is a critical step in infection for many viruses, including monkeypox virus (MPXV). In MPXV, the H3 protein mediates viral adhesion through its interaction with heparan sulfate (HS), yet the structural details of this interaction have remained elusive. Using AI-based structural prediction tools and molecular dynamics (MD) simulations, we identified a novel, positively charged α-helical domain in H3 that is essential for HS binding. This conserved domain, found across orthopoxviruses, was experimentally validated and shown to be critical for viral adhesion, making it an ideal target for antiviral drug development. Targeting this domain, we designed a protein inhibitor, which disrupted the H3-HS interaction, inhibited viral infection in vitro and viral replication in vivo, offering a promising antiviral candidate. Our findings reveal a novel therapeutic target of MPXV, demonstrating the potential of combination of AI-driven methods and MD simulations to accelerate antiviral drug discovery.
