Related Experiment Video
Updated: Jul 8, 2026
Modelling Zika Virus Infection of the Developing Human Brain In Vitro Using Stem Cell Derived Cerebral Organoids
Published on: September 19, 2017
Deep learning-based image classification reveals heterogeneous execution of cell death fates during viral infection
Edoardo Centofanti1, Alon Oyler-Yaniv1, Jennifer Oyler-Yaniv1
1The Department of Systems Biology at Harvard Medical School, Boston, MA 02115.
Abstract:
Cell fate decisions, such as proliferation, differentiation, and death, are driven by complex molecular interactions and signaling cascades. While significant progress has been made in understanding the molecular determinants of these processes, historically, cell fate transitions were identified through light microscopy that focused on changes in cell morphology and function. Modern techniques have shifted toward probing molecular effectors to quantify these transitions, offering more precise quantification and mechanistic understanding. However, challenges remain in cases where the molecular signals are ambiguous, complicating the assignment of cell fate. During viral infection, programmed cell death (PCD) pathways, including apoptosis, necroptosis, and pyroptosis, exhibit complex signaling and molecular cross-talk. This can lead to simultaneous activation of multiple PCD pathways, which confounds assignment of cell fate based on molecular information alone. To address this challenge, we employed deep learning-based image classification of dying cells to analyze PCD in single herpes simplex virus-1 (HSV-1)-infected cells. Our approach reveals that despite heterogeneous activation of signaling, individual cells adopt predominantly prototypical death morphologies. Nevertheless, PCD is executed heterogeneously within a uniform population of virus-infected cells and varies over time. These findings demonstrate that image-based phenotyping can provide valuable insights into cell fate decisions, complementing molecular assays.
Insights
Deep learning image analysis reveals that dying herpes simplex virus-1 (HSV-1)-infected cells exhibit distinct morphologies despite complex molecular signaling. This image-based phenotyping aids in understanding programmed cell death (PCD) heterogeneity.
Area of Science:
- Cell biology
- Virology
- Computational biology
Background:
- Cell fate decisions are crucial biological processes.
- Historically, cell morphology changes were used to identify cell fate transitions.
- Modern molecular assays offer precise quantification but face challenges with ambiguous signals, particularly during viral infections involving complex programmed cell death (PCD) pathways.
Purpose of the Study:
- To address challenges in assigning cell fate during viral infections with ambiguous molecular signals.
- To analyze programmed cell death (PCD) in single herpes simplex virus-1 (HSV-1)-infected cells using deep learning-based image classification.
- To investigate the relationship between heterogeneous molecular signaling and cell morphology during PCD.
Main Methods:
- Employed deep learning-based image classification to analyze dying cells.
- Focused on single herpes simplex virus-1 (HSV-1)-infected cells.
- Correlated molecular signaling with observed cell morphologies.
Main Results:
- Despite heterogeneous molecular signaling, individual infected cells adopted predominantly prototypical death morphologies.
- Programmed cell death (PCD) was executed heterogeneously within a uniform population of virus-infected cells.
- Cell death execution varied over time.
Conclusions:
- Image-based phenotyping provides valuable insights into cell fate decisions, complementing molecular assays.
- Deep learning analysis can resolve complex PCD events in viral infections.
- Cell morphology remains a key indicator of cell fate, even with complex underlying molecular events.
Related Concept Videos
01:30Overview of Cell Death
Cell death was observed in the early 19th century, but there was no experimental evidence to prove it. In 1842, Carl Vogt first discovered cell death in a metamorphic toad; however, it was not termed ‘cell death.’ Scientists discovered different cell death pathways only in the 20th century...
01:18Autophagic Cell Death
Autophagy and Apoptosis
Autophagy can activate apoptosis. In normal conditions, the autophagy activating protein Beclin-1 and pro-apoptotic...
01:11Cellular Injury IlI: Cellular Death
01:16Cellular Injury IV: Necrosis