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.
Related articles
Home Lab Overhaul: Securing Proxmox Infrastructure After Discovering 63,000 Forgejo Spam Accounts
A home lab administrator migrated Docker stacks to new LXC containers on Proxmox and uncovered multiple security misconfigurations. The setup relied on Cloudflare proxying, MikroTik port forwarding to NPMplus with CrowdSec, and Cloudflare Tunnels for admin panels. After fixing IP address logging in the WAF, logs revealed 63,021 spam accounts created on a Forgejo instance that had open registration. The operator disabled registrations, recreated the instance from verified Git mirrors, and eliminated direct internet exposure by routing all traffic through Cloudflare Tunnel. Additional controls included Zero Trust policies, device enrollment restrictions, and TOTP on Guacamole. The changes removed open ports, enforced proper client IP visibility for CrowdSec, and segmented public, limited, and admin access paths.
Benchmarking AES-GCM and Ascon AEAD Performance on ESP32 and ESP8266 for Industrial Telemetry
Researchers conducted detailed experiments measuring the real-world costs of three AEAD implementations on ESP32 and ESP8266 microcontrollers used in industrial telemetry scenarios. The study compared mbedTLS AES-128-GCM, legacy Ascon-128 via CryptoLW, and a portable C++ port of NIST Ascon-AEAD128 across three load profiles ranging from stable low-frequency packets to maximum-rate 10 ms intervals. Key metrics included AEAD execution time, CPU cycles, memory usage, UDP transmission success rates, and power consumption captured via TC66C. Initial tests revealed significant UDP packet loss on ESP32 under MAX load due to ENOMEM and ENOBUFS errors in the lwIP stack, which were largely resolved after network handling improvements. Results showed AES-GCM completing in roughly 618 µs on ESP32 versus 803 µs for legacy Ascon-128, while the reverse held on the slower ESP8266 where legacy Ascon outperformed AES by a factor of approximately 3.5. The work highlights that network stack limitations often dominate over cryptographic overhead in high-throughput industrial sensor deployments.
ARinteg Earns Golden Partner Status from Ideco for NGFW Security Projects
ARinteg has been awarded Golden Partner status by Ideco following successful joint projects in network security. The integrator supplies and implements the Ideco NGFW Novum next-generation firewall for perimeter protection and secure remote access. Collaboration also covers customer migrations from foreign NGFW solutions to the Russian vendor’s product. Commercial Director Dmitry Slobodenyuk stated the new status will allow ARinteg to deliver fuller support across all implementation stages. Ideco’s Partner Relations Head Sergey Markin highlighted ARinteg’s technical expertise in large-scale deployments. The partnership supports import substitution and hybrid infrastructure requirements.
Zero Trust in Practice: Avoiding YAML Pitfalls with Kubernetes NetworkPolicy and Istio
A detailed case study demonstrates how a single misplaced hyphen in a Kubernetes NetworkPolicy YAML file can unintentionally grant cluster-wide access instead of restricting it to a single client Pod. The example uses a shop namespace API connecting to an orders service in the backend namespace over TCP/8080, showing the correct use of namespaceSelector and podSelector together within the same from element. Tests on K3s with four vCPU and 4 GB RAM confirmed that only the intended client succeeds while others receive Connection refused. The implementation then extends to Istio with PeerAuthentication in STRICT mode and an AuthorizationPolicy limiting requests to GET /orders/* from the orders-api ServiceAccount. Additional checks cover RBAC permissions for creating Pods with specific ServiceAccounts and the need to verify DNS routes and existing allow-all policies. The article stresses maintaining an explicit list of required connections, testing both success and denial cases, and preserving rollback manifests before applying changes in production.