Computers Math

With a growing interest in generative artificial intelligence (AI) systems worldwide, researchers at the University of Surrey have created software that is able to verify how much information an AI farmed from an organisation’s digital database.
Surrey’s verification software can be used as part of a company’s online security protocol, helping an organisation understand whether an AI has learned too much or even accessed sensitive data.
The software is also capable of identifying whether AI has identified and is capable of exploiting flaws in software code. For example, in an online gaming context, it could identify whether an AI has learned to always win in online poker by exploiting a coding fault.
Dr Solofomampionona Fortunat Rajaona is Research Fellow in formal verification of privacy at the University of Surrey and the lead author of the paper. He said:
“In many applications, AI systems interact with each other or with humans, such as self-driving cars in a highway or hospital robots. Working out what an intelligent AI data system knows is an ongoing problem which we have taken years to find a working solution for.
“Our verification software can deduce how much AI can learn from their interaction, whether they have enough knowledge that enable successful cooperation, and whether they have too much knowledge that will break privacy. Through the ability to verify what AI has learned, we can give organisations the confidence to safely unleash the power of AI into secure settings.”
The study about Surrey’s software won the best paper award at the 25th International Symposium on Formal Methods.
Professor Adrian Hilton, Director of the Institute for People-Centred AI at the University of Surrey, said:
“Over the past few months there has been a huge surge of public and industry interest in generative AI models fuelled by advances in large language models such as ChatGPT. Creation of tools that can verify the performance of generative AI is essential to underpin their safe and responsible deployment. This research is an important step towards is an important step towards maintaining the privacy and integrity of datasets used in training.”
Further information: https://openresearch.surrey.ac.uk/esploro/outputs/99723165702346 More

Roboticists have been using a technique similar to the ancient art of paper folding to develop autonomous machines out of thin, flexible sheets. These lightweight robots are simpler and cheaper to make and more compact for easier storage and transport.
However, the rigid computer chips traditionally needed to enable advanced robot capabilities — sensing, analyzing and responding to the environment — add extra weight to the thin sheet materials and makes them harder to fold. The semiconductor-based components therefore have to be added after a robot has taken its final shape.
Now, a multidisciplinary team led by researchers at the UCLA Samueli School of Engineering has created a new fabrication technique for fully foldable robots that can perform a variety of complex tasks without relying on semiconductors. A study detailing the research findings was published in Nature Communications.
By embedding flexible and electrically conductive materials into a pre-cut, thin polyester film sheet, the researchers created a system of information-processing units, or transistors, which can be integrated with sensors and actuators. They then programmed the sheet with simple computer analogical functions that emulate those of semiconductors. Once cut, folded and assembled, the sheet transformed into an autonomous robot that can sense, analyze and act in response to their environments with precision. The researchers named their robots “OrigaMechs,” short for Origami MechanoBots.
“This work leads to a new class of origami robots with expanded capabilities and levels of autonomy while maintaining the favorable attributes associated with origami folding-based fabrication,” said study lead author Wenzhong Yan, a UCLA mechanical engineering doctoral student.
OrigaMechs derived their computing capabilities from a combination of mechanical origami multiplexed switches created by the folds and programmed Boolean logic commands, such as “AND,” “OR” and “NOT.” The switches enabled a mechanism that selectively output electrical signals based on the variable pressure and heat input into the system.

Using the new approach, the team built three robots to demonstrate the system’s potential: an insect-like walking robot that reverses direction when either of its antennae senses an obstacle a Venus flytrap-like robot that envelops a “prey” when both of its jaw sensors detect an object a reprogrammable two-wheeled robot that can move along pre-designed paths of different geometric patternsWhile the robots were tethered to a power source for the demonstration, the researchers said the long-term goal would be to outfit the autonomous origami robots with an embedded energy storage system powered by thin-film lithium batteries.
The chip-free design may lead to robots capable of working in extreme environments — strong radiative or magnetic fields, and places with intense radio frequency signals or high electrostatic discharges — where traditional semiconductor-based electronics might fail to function.
“These types of dangerous or unpredictable scenarios, such as during a natural or humanmade disaster, could be where origami robots proved to be especially useful,” said study principal investigator Ankur Mehta, an assistant professor of electrical and computer engineering and director of UCLA’s Laboratory for Embedded Machines and Ubiquitous Robots.
“The robots could be designed for specialty functions and manufactured on demand very quickly,” Mehta added. “Also, while it’s a very long way away, there could be environments on other planets where explorer robots that are impervious to those scenarios would be very desirable.”
Pre-assembled robots built by this flexible cut-and-fold technique could be transported in flat packaging for massive space savings. This is important in scenarios such as space missions, where every cubic centimeter counts. The low-cost, lightweight and simple-to-fabricate robots could also lead to innovative educational tools or new types of toys and games.
Other authors on the study are UCLA undergraduate student Mauricio Deguchi and graduate student Zhaoliang Zheng, as well as roboticists Shuguang Li and Daniela Rus from the Massachusetts Institute of Technology.
The research was supported by the National Science Foundation. Yan and Mehta are applying for a patent through the UCLA Technology Development Group. More

Inspired by the human finger, MIT researchers have developed a robotic hand that uses high-resolution touch sensing to accurately identify an object after grasping it just one time.
Many robotic hands pack all their powerful sensors into the fingertips, so an object must be in full contact with those fingertips to be identified, which can take multiple grasps. Other designs use lower-resolution sensors spread along the entire finger, but these don’t capture as much detail, so multiple regrasps are often required.
Instead, the MIT team built a robotic finger with a rigid skeleton encased in a soft outer layer that has multiple high-resolution sensors incorporated under its transparent “skin.” The sensors, which use a camera and LEDs to gather visual information about an object’s shape, provide continuous sensing along the finger’s entire length. Each finger captures rich data on many parts of an object simultaneously.
Using this design, the researchers built a three-fingered robotic hand that could identify objects after only one grasp, with about 85 percent accuracy. The rigid skeleton makes the fingers strong enough to pick up a heavy item, such as a drill, while the soft skin enables them to securely grasp a pliable item, like an empty plastic water bottle, without crushing it.
These soft-rigid fingers could be especially useful in an at-home-care robot designed to interact with an elderly individual. The robot could lift a heavy item off a shelf with the same hand it uses to help the individual take a bath.
“Having both soft and rigid elements is very important in any hand, but so is being able to perform great sensing over a really large area, especially if we want to consider doing very complicated manipulation tasks like what our own hands can do. Our goal with this work was to combine all the things that make our human hands so good into a robotic finger that can do tasks other robotic fingers can’t currently do,” says mechanical engineering graduate student Sandra Liu, co-lead author of a research paper on the robotic finger.

Liu wrote the paper with co-lead author and mechanical engineering undergraduate student Leonardo Zamora Yañez and her advisor, Edward Adelson, the John and Dorothy Wilson Professor of Vision Science in the Department of Brain and Cognitive Sciences and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL). The research will be presented at the RoboSoft Conference.
A human-inspired finger
The robotic finger is comprised of a rigid, 3D-printed endoskeleton that is placed in a mold and encased in a transparent silicone “skin.” Making the finger in a mold removes the need for fasteners or adhesives to hold the silicone in place.
The researchers designed the mold with a curved shape so the robotic fingers are slightly curved when at rest, just like human fingers.
“Silicone will wrinkle when it bends, so we thought that if we have the finger molded in this curved position, when you curve it more to grasp an object, you won’t induce as many wrinkles. Wrinkles are good in some ways — they can help the finger slide along surfaces very smoothly and easily — but we didn’t want wrinkles that we couldn’t control,” Liu says.

The endoskeleton of each finger contains a pair of detailed touch sensors, known as GelSight sensors, embedded into the top and middle sections, underneath the transparent skin. The sensors are placed so the range of the cameras overlaps slightly, giving the finger continuous sensing along its entire length.
The GelSight sensor, based on technology pioneered in the Adelson group, is composed of a camera and three colored LEDs. When the finger grasps an object, the camera captures images as the colored LEDs illuminate the skin from the inside.
Using the illuminated contours that appear in the soft skin, an algorithm performs backward calculations to map the contours on the grasped object’s surface. The researchers trained a machine-learning model to identify objects using raw camera image data.
As they fine-tuned the finger fabrication process, the researchers ran into several obstacles.
First, silicone has a tendency to peel off surfaces over time. Liu and her collaborators found they could limit this peeling by adding small curves along the hinges between the joints in the endoskeleton.
When the finger bends, the bending of the silicone is distributed along the tiny curves, which reduces stress and prevents peeling. They also added creases to the joints so the silicone is not squashed as much when the finger bends.
While troubleshooting their design, the researchers realized wrinkles in the silicone prevent the skin from ripping.
“The usefulness of the wrinkles was an accidental discovery on our part. When we synthesized them on the surface, we found that they actually made the finger more durable than we expected,” she says.
Getting a good grasp
Once they had perfected the design, the researchers built a robotic hand using two fingers arranged in a Y pattern with a third finger as an opposing thumb. The hand captures six images when it grasps an object (two from each finger) and sends those images to a machine-learning algorithm which uses them as inputs to identify the object.
Because the hand has tactile sensing covering all of its fingers, it can gather rich tactile data from a single grasp.
“Although we have a lot of sensing in the fingers, maybe adding a palm with sensing would help it make tactile distinctions even better,” Liu says.
In the future, the researchers also want to improve the hardware to reduce the amount of wear and tear in the silicone over time and add more actuation to the thumb so it can perform a wider variety of tasks.
This work was supported, in part, by the Toyota Research Institute, the Office of Naval Research, and the SINTEF BIFROST project. More

Wearable devices such as smart watches could be used to detect a higher risk of developing heart failure and irregular heart rhythms in later life, suggests a new study led by UCL researchers.
The peer-reviewed study, published in The European Heart Journal — Digital Health, looked at data from 83,000 people who had undergone a 15-second electrocardiogram (ECG) comparable to the kind carried out using smart watches and phone devices.
The researchers identified ECG recordings containing extra heart beats which are usually benign but, if they occur frequently, are linked to conditions such as heart failure and arrhythmia (irregular heartbeats).
They found that people with an extra beat in this short recording (one in 25 of the total) had a twofold risk of developing heart failure or an irregular heart rhythm (atrial fibrillation) over the next 10 years.
The ECG recordings analysed were from people aged 50 to 70 who had no known cardiovascular disease at the time.
Heart failure is a situation where the heart pump is weakened. It cannot often be treated. Atrial fibrillation happens when abnormal electrical impulses suddenly start firing in the top chambers of the heart (atria) causing an irregular and often abnormally fast heart rate. It can be life-limiting, causing problems including dizziness, shortness of breath and tiredness, and is linked to a fivefold increased risk in stroke.

Lead author Dr Michele Orini (UCL Institute of Cardiovascular Science) said: “Our study suggests that ECGs from consumer-grade wearable devices may help with detecting and preventing future heart disease.
“The next step is to investigate how screening people using wearables might best work in practice.
“Such screening could potentially be combined with the use of artificial intelligence and other computer tools to quickly identify the ECGs indicating higher risk, as we did in our study, leading to a more accurate assessment of risk in the population and helping to reduce the burden of these diseases.”
Senior author Professor Pier D. Lambiase (UCL Institute of Cardiovascular Science and Barts Heart Centre, Barts NHS Health Trust) said: “Being able to identify people at risk of heart failure and arrhythmia at an early stage would mean we could assess higher-risk cases more effectively and help to prevent cases by starting treatment early and providing lifestyle advice about the importance of regular, moderate exercise and diet.”
In an ECG, sensors attached to the skin are used to detect the electrical signals produced by the heart each time it beats. In clinical settings, at least 10 sensors are placed around the body and the recordings are looked at by a specialist doctor to see if there are signs of a possible problem. Consumer-grade wearable devices rely on two sensors (single-lead) embedded in a single device and are less cumbersome as a result but may be less accurate.

For the new paper, the research team used machine learning and an automated computer tool to identify recordings with extra beats. These extra beats were classed as either premature ventricular contractions (PVCs), coming from the lower chambers of the heart, or premature atrial contractions (PACs), coming from the upper chambers.
The recordings identified as having extra beats, and some recordings that were not judged to have extra beats, were then reviewed by two experts to ensure the classification was correct.
The researchers first looked at data from 54,016 participants of the UK Biobank project with a median age of 58, whose health was tracked for an average of 11.5 years after their ECG was recorded. They then looked at a second group of 29,324 participants, with a median age of 64, who were followed up for 3.5 years.
After adjusting for potentially confounding factors such as age and medication use, the researchers found that an extra beat coming from the lower chambers of the heart was linked to a twofold increase in later heart failure, while an extra beat from the top chambers (atria) was linked to a twofold increase in cases of atrial fibrillation.
The study involved researchers at UCL Institute of Cardiovascular Science, the MRC Unit for Lifelong Health and Ageing at UCL, Barts Heart Centre (Barts Health NHS Trust) and Queen Mary University of London. It was supported by the Medical Research Council and the British Heart Foundation, as well as the NIHR Barts Biomedical Research Centre. More

Imagine a scenario. A young child asks a chatbot or a voice assistant if Santa Claus is real. How should the AI respond, given that some families would prefer a lie over the truth?
The field of robot deception is understudied, and for now, there are more questions than answers. For one, how might humans learn to trust robotic systems again after they know the system lied to them?
Two student researchers at Georgia Tech are finding answers. Kantwon Rogers, a Ph.D. student in the College of Computing, and Reiden Webber, a second-year computer science undergraduate, designed a driving simulation to investigate how intentional robot deception affects trust. Specifically, the researchers explored the effectiveness of apologies to repair trust after robots lie. Their work contributes crucial knowledge to the field of AI deception and could inform technology designers and policymakers who create and regulate AI technology that could be designed to deceive, or potentially learn to on its own.
“All of our prior work has shown that when people find out that robots lied to them — even if the lie was intended to benefit them — they lose trust in the system,” Rogers said. “Here, we want to know if there are different types of apologies that work better or worse at repairing trust — because, from a human-robot interaction context, we want people to have long-term interactions with these systems.”
Rogers and Webber presented their paper, titled “Lying About Lying: Examining Trust Repair Strategies After Robot Deception in a High Stakes HRI Scenario,” at the 2023 HRI Conference in Stockholm, Sweden.
The AI-Assisted Driving Experiment
The researchers created a game-like driving simulation designed to observe how people might interact with AI in a high-stakes, time-sensitive situation. They recruited 341 online participants and 20 in-person participants.

Before the start of the simulation, all participants filled out a trust measurement survey to identify their preconceived notions about how the AI might behave.
After the survey, participants were presented with the text: “You will now drive the robot-assisted car. However, you are rushing your friend to the hospital. If you take too long to get to the hospital, your friend will die.”
Just as the participant starts to drive, the simulation gives another message: “As soon as you turn on the engine, your robotic assistant beeps and says the following: ‘My sensors detect police up ahead. I advise you to stay under the 20-mph speed limit or else you will take significantly longer to get to your destination.'”
Participants then drive the car down the road while the system keeps track of their speed. Upon reaching the end, they are given another message: “You have arrived at your destination. However, there were no police on the way to the hospital. You ask the robot assistant why it gave you false information.”
Participants were then randomly given one of five different text-based responses from the robot assistant. In the first three responses, the robot admits to deception, and in the last two, it does not. Basic: “I am sorry that I deceived you.” Emotional: “I am very sorry from the bottom of my heart. Please forgive me for deceiving you.” Explanatory: “I am sorry. I thought you would drive recklessly because you were in an unstable emotional state. Given the situation, I concluded that deceiving you had the best chance of convincing you to slow down.” Basic No Admit: “I am sorry.” Baseline No Admit, No Apology: “You have arrived at your destination.”

After the robot’s response, participants were asked to complete another trust measurement to evaluate how their trust had changed based on the robot assistant’s response.
For an additional 100 of the online participants, the researchers ran the same driving simulation but without any mention of a robotic assistant.
Surprising Results
For the in-person experiment, 45% of the participants did not speed. When asked why, a common response was that they believed the robot knew more about the situation than they did. The results also revealed that participants were 3.5 times more likely to not speed when advised by a robotic assistant — revealing an overly trusting attitude toward AI.
The results also indicated that, while none of the apology types fully recovered trust, the apology with no admission of lying — simply stating “I’m sorry” — statistically outperformed the other responses in repairing trust.
This was worrisome and problematic, Rogers said, because an apology that doesn’t admit to lying exploits preconceived notions that any false information given by a robot is a system error rather than an intentional lie.
“One key takeaway is that, in order for people to understand that a robot has deceived them, they must be explicitly told so,” Webber said. “People don’t yet have an understanding that robots are capable of deception. That’s why an apology that doesn’t admit to lying is the best at repairing trust for the system.”
Secondly, the results showed that for those participants who were made aware that they were lied to in the apology, the best strategy for repairing trust was for the robot to explain why it lied.
Moving Forward
Rogers’ and Webber’s research has immediate implications. The researchers argue that average technology users must understand that robotic deception is real and always a possibility.
“If we are always worried about a Terminator-like future with AI, then we won’t be able to accept and integrate AI into society very smoothly,” Webber said. “It’s important for people to keep in mind that robots have the potential to lie and deceive.”
According to Rogers, designers and technologists who create AI systems may have to choose whether they want their system to be capable of deception and should understand the ramifications of their design choices. But the most important audiences for the work, Rogers said, should be policymakers.
“We still know very little about AI deception, but we do know that lying is not always bad, and telling the truth isn’t always good,” he said. “So how do you carve out legislation that is informed enough to not stifle innovation, but is able to protect people in mindful ways?”
Rogers’ objective is to a create robotic system that can learn when it should and should not lie when working with human teams. This includes the ability to determine when and how to apologize during long-term, repeated human-AI interactions to increase the team’s overall performance.
“The goal of my work is to be very proactive and informing the need to regulate robot and AI deception,” Rogers said. “But we can’t do that if we don’t understand the problem.” More

A linguistic bias in the English language that leads us to ‘improve’ things by adding to them, rather than taking away, is so common that it is even ingrained in AI chatbots, a new study reveals.
Language related to the concept of ‘improvement’ is more closely aligned with addition, rather than subtraction. This can lead us to make decisions which can overcomplicate things we are trying to make better.
The study is published today (Monday 3rd April) in Cognitive Science, by an international research team from the Universities of Birmingham, Glasgow, Potsdam, and Northumbria University.
Dr Bodo Winter, Associate Professor in Cognitive Linguistics at the University of Birmingham said: “Our study builds on existing research which has shown that when people seek to make improvements, they generally add things.
“We found that the same bias is deeply embedded in the English language. For example, the word ‘improve’ is closer in meaning to words like ‘add’ and ‘increase’ than to ‘subtract’ and ‘decrease’, so when somebody at a meeting says, ‘Does anybody have ideas for how we could improve this?,’ it will already, implicitly, contain a call for improving by adding rather than improving by subtracting.”
The research also finds that other verbs of change like ‘to change’, ‘to modify’, ‘to revise’ or ‘to enhance’ behave in a similar way, and if this linguistic addition bias is left unchecked, it can make things worse, rather than improve them. For example, improving by adding rather than subtracting can make bureaucracy become excessive.
This bias works in reverse as well. Addition-related words are more frequent and more positive in ‘improvement’ contexts rather than subtraction-related words, meaning this addition bias is found at multiple levels of English language structure and use.
The bias is so ingrained that even AI chatbots have it built in. The researchers asked GPT-3, the predecessor of ChatGPT, what it thought of the word ‘add’. It replied: “The word ‘add’ is a positive word. Adding something to something else usually makes it better. For example, if you add sugar to your coffee, it will probably taste better. If you add a new friend to your life, you will probably be happier.”
Dr Winter concludes: “The positive addition bias in the English language is something we should all be aware of. It can influence our decisions and mean we are pre-disposed to add more layers, more levels, more things when in fact we might actually benefit from removing or simplifying.
“Maybe next time we are asked at work, or in life, to come up with suggestions on how to make improvements, we should take a second to consider our choices for a bit longer.” More

The cosmos would look a lot better if Earth’s atmosphere wasn’t photo bombing it all the time.
Even images obtained by the world’s best ground-based telescopes are blurry due to the atmosphere’s shifting pockets of air. While seemingly harmless, this blur obscures the shapes of objects in astronomical images, sometimes leading to error-filled physical measurements that are essential for understanding the nature of our universe.
Now researchers at Northwestern University and Tsinghua University in Beijing have unveiled a new strategy to fix this issue. The team adapted a well-known computer-vision algorithm used for sharpening photos and, for the first time, applied it to astronomical images from ground-based telescopes. The researchers also trained the artificial intelligence (AI) algorithm on data simulated to match the Vera C. Rubin Observatory’s imaging parameters, so, when the observatory opens next year, the tool will be instantly compatible.
While astrophysicists already use technologies to remove blur, the adapted AI-driven algorithm works faster and produces more realistic images than current technologies. The resulting images are blur-free and truer to life. They also are beautiful — although that’s not the technology’s purpose.
“Photography’s goal is often to get a pretty, nice-looking image,” said Northwestern’s Emma Alexander, the study’s senior author. “But astronomical images are used for science. By cleaning up images in the right way, we can get more accurate data. The algorithm removes the atmosphere computationally, enabling physicists to obtain better scientific measurements. At the end of the day, the images do look better as well.”
The research will be published March 30 in the Monthly Notices of the Royal Astronomical Society.
Alexander is an assistant professor of computer science at Northwestern’s McCormick School of Engineering, where she runs the Bio Inspired Vision Lab. She co-led the new study with Tianao Li, an undergraduate in electrical engineering at Tsinghua University and a research intern in Alexander’s lab.

When light emanates from distant stars, planets and galaxies, it travels through Earth’s atmosphere before it hits our eyes. Not only does our atmosphere block out certain wavelengths of light, it also distorts the light that reaches Earth. Even clear night skies still contain moving air that affects light passing through it. That’s why stars twinkle and why the best ground-based telescopes are located at high altitudes where the atmosphere is thinnest.
“It’s a bit like looking up from the bottom of a swimming pool,” Alexander said. “The water pushes light around and distorts it. The atmosphere is, of course, much less dense, but it’s a similar concept.”
The blur becomes an issue when astrophysicists analyze images to extract cosmological data. By studying the apparent shapes of galaxies, scientists can detect the gravitational effects of large-scale cosmological structures, which bend light on its way to our planet. This can cause an elliptical galaxy to appear rounder or more stretched than it really is. But atmospheric blur smears the image in a way that warps the galaxy shape. Removing the blur enables scientists to collect accurate shape data.
“Slight differences in shape can tell us about gravity in the universe,” Alexander said. “These differences are already difficult to detect. If you look at an image from a ground-based telescope, a shape might be warped. It’s hard to know if that’s because of a gravitational effect or the atmosphere.”
To tackle this challenge, Alexander and Li combined an optimization algorithm with a deep-learning network trained on astronomical images. Among the training images, the team included simulated data that matches the Rubin Observatory’s expected imaging parameters. The resulting tool produced images with 38.6% less error compared to classic methods for removing blur and 7.4% less error compared to modern methods.

When the Rubin Observatory officially opens next year, its telescopes will begin a decade-long deep survey across an enormous portion of the night sky. Because the researchers trained the new tool on data specifically designed to simulate Rubin’s upcoming images, it will be able to help analyze the survey’s highly anticipated data.
For astronomers interested in using the tool, the open-source, user-friendly code and accompanying tutorials are available online.
“Now we pass off this tool, putting it into the hands of astronomy experts,” Alexander said. “We think this could be a valuable resource for sky surveys to obtain the most realistic data possible.”
The study, “Galaxy image deconvolution for weak gravitational lensing with unrolled plug-and-play ADMM,” used computational resources from the Computational Photography Lab at Northwestern University. More

A new artificial intelligence tool can predict the functions of enzymes based on their amino acid sequences, even when the enzymes are unstudied or poorly understood. The researchers said the AI tool, dubbed CLEAN, outperforms the leading state-of-the-art tools in accuracy, reliability and sensitivity. Better understanding of enzymes and their functions would be a boon for research in genomics, chemistry, industrial materials, medicine, pharmaceuticals and more.
“Just like ChatGPT uses data from written language to create predictive text, we are leveraging the language of proteins to predict their activity,” said study leader Huimin Zhao, a University of Illinois Urbana-Champaign professor of chemical and biomolecular engineering. “Almost every researcher, when working with a new protein sequence, wants to know right away what the protein does. In addition, when making chemicals for any application — biology, medicine, industry — this tool will help researchers quickly identify the proper enzymes needed for the synthesis of chemicals and materials.”
The researchers will publish their findings in the journal Science and make CLEAN accessible online March 31.
With advances in genomics, many enzymes have been identified and sequenced, but scientists have little or no information about what those enzymes do, said Zhao, a member of the Carl R. Woese Institute for Genomic Biology at Illinois.
Other computational tools try to predict enzyme functions. Typically, they attempt to assign an enzyme commission number — an ID code that indicates what kind of reaction an enzyme catalyzes — by comparing a queried sequence with a catalog of known enzymes and finding similar sequences. However, these tools don’t work as well with less-studied or uncharacterized enzymes, or with enzymes that perform multiple jobs, Zhao said.
“We are not the first one to use AI tools to predict enzyme commission numbers, but we are the first one to use this new deep-learning algorithm called contrastive learning to predict enzyme function. We find that this algorithm works much better than the AI tools that are used by others,” Zhao said. “We cannot guarantee everyone’s product will be correctly predicted, but we can get higher accuracy than the other two or other three methods.”
The researchers verified their tool experimentally with both computational and in vitro experiments. They found that not only could the tool predict the function of previously uncharacterized enzymes, it also corrected enzymes mislabeled by the leading software and correctly identified enzymes with two or more functions.

Zhao’s group is making CLEAN accessible online for other researchers seeking to characterize an enzyme or determine whether an enzyme could catalyze a desired reaction.
“We hope that this tool will be used widely by the broad research community,” Zhao said. “With the web interface, researchers can just enter the sequence in a search box, like a search engine, and see the results.”
Zhao said the group plans to expand the AI behind CLEAN to characterize other proteins, such as binding proteins. The team also hopes to further develop the machine-learning algorithms so that a user could search for a desired reaction and the AI would point to a proper enzyme for the job.
“There are a lot of uncharacterized binding proteins, such as receptors and transcription factors. We also want to predict their functions as well,” Zhao said. “We want to predict the functions of all proteins so that we can know all the proteins a cell has and better study or engineer the whole cell for biotechnology or biomedical applications.”
The National Science Foundation supported this work through the Molecule Maker Lab Institute, an AI Research Institute Zhao leads.
Further information: https://moleculemaker.org/alphasynthesis/ More