Artificial Intelligence Tracks Microbes express
To avoid losing a fast soccer player in the frame, a drone doesn't need a bright beacon — recognizing the silhouette is enough. Similarly, a neural network now tracks microbes: the algorithm analyzes an ordinary microscope image and instantly finds a bacterium in a drop of water. Previously, they were marked with glowing dyes, but those quickly faded, and the intense light disrupted natural behavior.
It turned out that the magnetic field serves them not as a compass, but as a depth indicator — sliding along the field lines, bacteria find water layers with the right oxygen level. Now biologists can see how a single microbe chooses its path, searches for food, and communicates with neighbors. The method reveals invisible life from soil to ocean.
Original abstract
as written by the authors arXiv:2603.20764
How microorganisms respond to and interact with their environment can vary significantly from individual to individual, which can have important microbiological and ecological implications. However, most microscopy techniques can only observe motile microorganisms for short times because of their limited fields of view. Using Lagrangian tracking, a single microorganism can be followed in 3D, potentially indefinitely, allowing to decipher individual phenotypical traits. Current Lagrangian tracking methods use the fluorescence signal emitted by the microorganism as feedback to keep it in focus. However, over long times, epifluorescent imaging can induce photobleaching and photodamage, and importantly, not all microorganisms can easily be made fluorescent. Additionally, traditional algorithms used in feedback loops to determine microorganism position are prone to errors, especially in optically complex media. Here, we present a faster, more reliable, and versatile Lagrangian tracking method that uses deep learning to determine the 3D position of the microorganism. This new method demonstrates enhanced accuracy and speed in tracking fluorescent bacteria with fluorescence microscopy also in optically complex media. Furthermore, we track bacteria with other microscopy modalities, such as brightfield microscopy -- for example, this enables us to track magnetotactic bacteria, which cannot be made fluorescent without degrading their magnetotactic properties. These novel capabilities allow to extract previously inaccessible quantitative information, significantly advancing the study of microorganism behavior -- and thus opening new avenues for research in complex biological and ecological systems.
Back in the 17th century, Robert Hooke examined mold under a homemade microscope but couldn't track the movement of a single bacterium. Magnetotactic bacteria contain magnetite crystals and swim along Earth's magnetic field lines — it's not a compass, but an elevator: that's how they find water layers with the right oxygen level.