AI-Designed NovoTags Enable Real-Time Fluorescent Labeling of Mitochondria and Other Cellular Structures in Living Cells

Scientists have created a powerful new tool for observing cellular processes almost in real time. Using advanced artificial intelligence systems, researchers designed tiny protein tags from scratch that attach to selected molecules and cause them to glow brightly under a microscope. The development, named NovoTags, promises to significantly expand the capabilities of cell biology.

Modern microscopes can visualize individual cellular structures, yet locating a specific protein among millions of molecules remains challenging. Researchers typically attach a fluorescent label to the protein of interest, which glows when illuminated. Existing systems are limited to a narrow set of dyes and struggle with simultaneous observation of multiple processes.

A team from the Institute for Protein Design at the University of Washington, the Janelia Research Campus, and the European Molecular Biology Laboratory engineered small artificial proteins capable of capturing specific Janelia Fluor dyes. They produced three independent tags covering the green, orange, and far-red spectral ranges. Each tag can be genetically fused to a chosen protein, after which the dye illuminates the target molecule inside a living cell.

The protein structures were not obtained by screening natural variants. Instead, the algorithm RFdiffusion generated the shape of the future protein, while LigandMPNN selected the amino acid sequence. AlphaFold and RoseTTAFold then verified whether the resulting molecule would fold correctly. The most promising designs were synthesized and tested in the laboratory.

Unlike conventional fluorescent proteins, NovoTags do not fluoresce by themselves. The artificial protein forms a pocket around the dye molecule, firmly retains it, and modifies its optical properties. Thanks to their high brightness and precise binding, the tags are suitable for super-resolution microscopy techniques that reveal details smaller than the diffraction limit of conventional light microscopes.

In experiments, researchers applied NovoTags in living human cells. The tags successfully highlighted endosomes, mitochondria, and chromatin. Scientists also performed STED super-resolution microscopy and fluorescence lifetime imaging, allowing distinction of labels not only by color but also by emission duration.

Combining color and lifetime parameters could dramatically increase the number of objects observable simultaneously. The authors estimate that different combinations may eventually allow differentiation of up to 30 distinct proteins within a single cell, although further experiments are required to confirm reliability at such high labeling density.

The team also created a controllable version called NovoSplit. They split the artificial protein into two halves, each fused to a separate molecule. Upon addition of the appropriate dye, the halves assemble like puzzle pieces, bringing the attached proteins together. In this configuration the dye functions both as a fluorescent marker and as molecular glue.

NovoSplit enables scientists not only to observe protein interactions but also to trigger them at a chosen moment. The method will help study cell signaling, assembly of molecular complexes, and other processes that depend on transient protein contacts.

Looking ahead, the developers plan to integrate NovoTags with cryo-electron tomography. This approach would first locate a protein via fluorescence and then examine surrounding molecular structures at much higher resolution, allowing direct correlation of a protein’s position, shape, and function inside a near-native frozen cell.

The sequences of NovoTags and compatible dyes have been released to the scientific community. Laboratories worldwide are already expanding the toolkit with new colors and functionalities. The study was published on 16 July 2026 in the journal Science.