Deep Learning Algorithms Identify Structures in Living Cells

Researchers are using artificial intelligence to pick out the features of brightfield microscopy images.

| 4 min read
images taken with brightfield microscopy

Register for free to listen to this article
Listen with Speechify
0:00
4:00
Share

ABOVE: MODIFIED FROM THE ALLEN INSTITUTE

For cell biologists, fluorescence micro­scopy is an invaluable tool. Fusing dyes to antibodies or inserting genes coding for fluorescent proteins into the DNA of living cells can help scientists pick out the location of organelles, cytoskeletal elements, and other subcellular structures from otherwise impenetrable microscopy images. But this technique has its drawbacks. There are limits to the number of fluorescent tags that can be introduced into a cell, and side effects such as photo­toxicity—damage caused by repeated exposure to light—can hinder researchers’ ability to conduct live cell imaging.

These issues were on biomedical engineer Greg Johnson’s mind when he joined the Allen Institute for Cell Science in Seattle in 2016. Johnson, whose doctoral work at Carnegie Mellon University had focused on creating computational tools to model cellular structures (see “Robert Murphy Bets Self Driving Instruments Will Crack Biology's Mysteries” here), was hired as part ...

Interested in reading more?

Become a Member of

The Scientist Logo
Receive full access to digital editions of The Scientist, as well as TS Digest, feature stories, more than 35 years of archives, and much more!
Already a member? Login Here

Keywords

Meet the Author

  • Diana Kwon

    Diana is a freelance science journalist who covers the life sciences, health, and academic life.

Published In

May 2019 The Scientist Issue
May 2019

AI Tackles Biology

How machine learning will revolutionize science and medicine.

Share
3D illustration of a gold lipid nanoparticle with pink nucleic acid inside of it. Purple and teal spikes stick out from the lipid bilayer representing polyethylene glycol.
February 2025, Issue 1

A Nanoparticle Delivery System for Gene Therapy

A reimagined lipid vehicle for nucleic acids could overcome the limitations of current vectors.

View this Issue
Enhancing Therapeutic Antibody Discovery with Cross-Platform Workflows

Enhancing Therapeutic Antibody Discovery with Cross-Platform Workflows

sartorius logo
Considerations for Cell-Based Assays in Immuno-Oncology Research

Considerations for Cell-Based Assays in Immuno-Oncology Research

Lonza
An illustration of animal and tree silhouettes.

From Water Bears to Grizzly Bears: Unusual Animal Models

Taconic Biosciences
Sex Differences in Neurological Research

Sex Differences in Neurological Research

bit.bio logo

Products

Photo of a researcher overseeing large scale production processes in a laboratory.

Scaling Lentiviral Vector Manufacturing for Optimal Productivity

Thermo Fisher Logo
Collage-style urban graphic of wastewater surveillance and treatment

Putting Pathogens to the Test with Wastewater Surveillance

An illustration of an mRNA molecule in front of a multicolored background.

Generating High-Quality mRNA for In Vivo Delivery with lipid nanoparticles

Thermo Fisher Logo
Tecan Logo

Tecan introduces Veya: bringing digital, scalable automation to labs worldwide