The foundation of this breakthrough lies in the ability of these ingeniously AI-designed protein switches to operate both within living bacterial cells and as integral components of electrochemical biosensors. By converting molecular recognition events into measurable outputs, such as colorimetric changes, luminescence, or electrical signals, these proteins have created a versatile platform reminiscent of the well-established glucose meter, which translates biochemical interactions into real-time, actionable data. This represents a significant leap forward in the design and deployment of biosensors, as it extends capabilities far beyond the constraints of naturally sourced proteins.

Professor Kirill Alexandrov, leading the project from QUT’s School of Biology and Environmental Science and the ARC Centre of Excellence in Synthetic Biology, emphasizes the molecular machinery role that proteins perform in cells, underpinning their ability to sense and respond to environmental changes. “Synthetic biology’s frontier has long sought to engineer protein systems tailor-made to detect molecules of interest and trigger beneficial responses,” Alexandrov notes. Historically, efforts to build such systems relied heavily on modifying existing natural proteins, which posed inherent limitations in diversity and customizability. This research carves a new path, using artificial intelligence to unlock far greater design freedom.

Central to the team’s strategy was deploying machine learning approaches to craft novel protein receptors that bind specifically to target molecules. Unlike traditional protein engineering, which often required large conformational shifts in protein structure to switch activity on or off, these new switches function through surprisingly subtle dynamical changes. The binding event finely tunes how the protein moves and vibrates, modulating enzymatic activity without major shape alterations. This insight not only challenges long-standing notions in protein science but also opens pathways for more efficient and versatile biosensor design.

These newly designed molecular switches demonstrated responsiveness to an array of molecular entities including small organic compounds, peptides, and entire proteins, showcasing remarkable adaptability. Importantly, the switch constructs were validated to function reliably in vivo within bacterial cells, underscoring their promise for integration in living synthetic biological systems. Moreover, their compatibility with electrochemical setups enables the generation of rapid, quantifiable electrical signals upon target detection—a feature vital for portable sensor development.

Potential applications for such technology are profound and varied. In medicine, these biosensors could facilitate real-time, point-of-care diagnostics capable of detecting critical biomarkers with unprecedented sensitivity and specificity. Environmental monitoring could benefit through compact devices that rapidly identify pollutants or hazardous compounds, contributing to ecosystem protection and public health. Additionally, the ability to embed these switches in engineered cells may lead to intelligent bioreactors or therapeutic cells that dynamically adjust their behavior in response to chemical stimuli.

The international collaboration underpinning this research drew expertise from seven research groups across Australia, the United Kingdom, and the United States, including notable partnership with the University of Washington led by Nobel laureate Professor David Baker, and the Australian national science agency CSIRO. Such synergy reflects the complex, interdisciplinary nature of engineering functional synthetic proteins—a task requiring knowledge in computational design, molecular biology, and bioengineering.

Among the contributing QUT researchers were Dr. Zhong Guo, Dr. Zhenling Cui, Dr. Cagla Ergun Ayva, Dr. Roxane Mutschler, and Dr. Mica Fiorito, whose combined efforts ranged from AI algorithm development to experimental validation. Their comprehensive approach ensured not only the theoretical viability of these protein switches but also practical demonstration and functional characterization in biological contexts.

By harnessing the power of deep learning and molecular dynamics simulations, the team effectively expanded the protein engineering toolkit, enabling the de novo design of ligand-specific receptors that elicit functional responses without relying on the constraints of natural evolutionary pathways. This represents a seminal advance, potentially catalyzing innovation in biosensing, therapeutics, and synthetic biology at large.

In summary, the creation of AI-designed artificial allosteric protein switches represents a landmark achievement with far-reaching implications. These molecular devices transcend previous limitations by enabling the rational design of highly tailored, efficient protein sensors and actuators. Their successful integration into living cells and electrochemical platforms portends a future where biosensors become ubiquitously accessible, smart, and integrated deeply into biomedical and environmental infrastructures—transforming how we detect and respond to the molecular underpinnings of health and nature.

Subject of Research: Artificial allosteric protein switches designed by machine learning for biosensing applications

Article Title: Artificial allosteric protein switches with machine learning-designed receptors

News Publication Date: 2026

Web References:

• Nature Biotechnology article
• DOI link

Image Credits: QUT

Keywords: synthetic biology, protein engineering, artificial intelligence, molecular switches, biosensors, electrochemical detection, machine learning, allosteric proteins

Proteins serve as the fundamental workhorses of the cell, orchestrating myriad biochemical processes vital for life. They are composed of one or more subunits known as domains, each conferring specific structural or functional traits. These domains act as independent yet interconnected modules, enabling proteins to detect environmental cues, catalyze reactions, or mediate signaling pathways. Natural evolution leverages this modularity, progressively recombining domains to yield novel proteins with enhanced or altered capabilities. Drawing inspiration from this evolutionary paradigm, the Heidelberg team sought to simulate and accelerate such recombination artificially, thereby rationally engineering proteins with controllable and desirable features.

Central to this endeavor was the development of an AI-driven platform that can systematically analyze the complex landscape of domain combinations and predict optimal insertion sites for merging domains without compromising protein stability or function. To train and validate their model, the scientists employed a comprehensive dataset derived from over 100,000 proteins, meticulously curated from extensive protein databases. This rich dataset encapsulates a vast diversity of naturally occurring domain architectures, providing a robust foundation for the AI to learn patterns governing successful domain integration within proteins.

ProDomino’s predictive prowess lies in its ability to consider a multitude of structural and functional parameters simultaneously, such as domain compatibility, folding dynamics, and allosteric communication pathways. By simulating potential domain insertions computationally, the AI can forecast how hybrid proteins will behave upon recombination, including whether the engineered protein switch can effectively modulate its activity in response to external signals. This capability marks a significant step beyond traditional trial-and-error protein engineering, heralding a shift towards rational, in silico-guided design.

One of the showcased applications involved coupling chemosensitive sensor domains with the CRISPR-Cas system, a revolutionary genome editing tool. By fusing these sensor modules to the molecular “scissors,” researchers generated allosteric protein switches capable of being toggled on or off by specific chemical stimuli. This innovation substantially enhances the safety profile of CRISPR-based editing by enabling precise temporal and spatial control over gene-editing activity, thereby minimizing off-target effects and unwanted genetic modifications. The successful in vitro validation of these engineered proteins underscores ProDomino’s potential in fine-tuning complex biomolecular systems.

Further emphasizing the versatility of ProDomino, the research team demonstrated the model’s utility in designing proteins sensitive to diverse stimuli, including biochemical signals and environmental factors such as light and temperature. This adaptability paves the way for creating bespoke biosensors, regulatory proteins, and therapeutic agents with switchable functionalities—components that can fundamentally transform approaches in synthetic biology, diagnostics, and targeted therapies.

Prof. Dr. Dominik Niopek, the leading scientist behind this pioneering work at Heidelberg’s Institute of Pharmacy and Molecular Biotechnology, highlighted the transformative nature of their AI model: “Our approach allows us to produce artificial proteins more efficiently and precisely than ever before. By leveraging computational predictions, we bypass laborious experimental screening and steer protein engineering toward rational design.” He envisions that this technology will accelerate the development of protein-based tools that are not only more effective but also customizable, enabling novel therapeutic strategies and biotechnological innovations.

The open-source release of ProDomino reflects the research team’s commitment to fostering collaborative progress in the scientific community. By making the software freely available, they empower researchers worldwide to explore new protein combinations and applications, from customizing enzymes for industrial processes to engineering cellular machines for regenerative medicine. This democratization of advanced protein design tools is expected to catalyze breakthroughs across multiple disciplines.

Underpinning the success of ProDomino is an interdisciplinary fusion of computational biology, protein chemistry, and machine learning. The computational simulation methodologies employed incorporate advanced modeling algorithms that consider the energetic and dynamic complexities of protein folding and domain-domain interactions. This holistic approach not only predicts compatible domain combinations but also anticipates conformational changes critical for allosteric regulation—a key feature for engineering switchable proteins.

The research was generously supported by the European Research Council (ERC), underscoring the importance of funding fundamental scientific innovation. The team’s findings were published on August 4, 2025, in the prestigious journal Nature Methods, where the full technical details and validation experiments are documented.

Looking ahead, the potential implications of ProDomino extend well beyond laboratory research. By enabling precise, programmable control over protein function, this AI-driven approach may underpin next-generation therapies for genetic diseases, innovative biosensors for environmental monitoring, and bespoke enzymes tailored for sustainable industrial applications. The convergence of AI and synthetic biology promises to unlock a new era in which proteins are engineered with the same precision and predictability as electronic circuits, transforming medicine and biotechnology at a fundamental level.

Subject of Research: Computational biology, protein engineering
Article Title: Rational engineering of allosteric protein switches by in silico prediction of domain insertion sites
News Publication Date: 4-Aug-2025
Web References: DOI link
Image Credits: Jan Mathony & Benedict Wolf, Heidelberg University
Keywords: Computational biology, protein design, artificial intelligence, synthetic biology, protein engineering, CRISPR, allosteric proteins, biotechnology, genome editing