MIT researchers are using artificial intelligence to design latest proteins that transcend those present in nature.

They developed machine-learning algorithms that may generate proteins with specific structural features, which might be used to make materials which have certain mechanical properties, like stiffness or elasticity. Such biologically inspired materials could potentially replace materials created from petroleum or ceramics, but with a much smaller carbon footprint.

The researchers from MIT, the MIT-IBM Watson AI Lab, and Tufts University employed a generative model, which is similar style of machine-learning model architecture utilized in AI systems like DALL-E 2. But as a substitute of using it to generate realistic images from natural language prompts, like DALL-E 2 does, they adapted the model architecture so it could predict amino acid sequences of proteins that achieve specific structural objectives.

In a paper published today in , the researchers show how these models can generate realistic, yet novel, proteins. The models, which learn biochemical relationships that control how proteins form, can produce latest proteins that might enable unique applications, says senior creator Markus Buehler, the Jerry McAfee Professor in Engineering and professor of civil and environmental engineering and of mechanical engineering.

For example, this tool might be used to develop protein-inspired food coatings, which could keep produce fresh longer while being secure for humans to eat. And the models can generate hundreds of thousands of proteins in a number of days, quickly giving scientists a portfolio of recent ideas to explore, he adds.

“When you consider designing proteins nature has not discovered yet, it’s such an enormous design space that you could’t just sort it out with a pencil and paper. You’ve gotten to determine the language of life, the way in which amino acids are encoded by DNA after which come together to form protein structures. Before we had deep learning, we actually couldn’t do that,” says Buehler, who can be a member of the MIT-IBM Watson AI Lab.

Joining Buehler on the paper are lead creator Bo Ni, a postdoc in Buehler’s Laboratory for Atomistic and Molecular Mechanics; and David Kaplan, the Stern Family Professor of Engineering and professor of bioengineering at Tufts.

Adapting latest tools for the duty

Proteins are formed by chains of amino acids, folded together in 3D patterns. The sequence of amino acids determines the mechanical properties of the protein. While scientists have identified hundreds of proteins created through evolution, they estimate that an unlimited variety of amino acid sequences remain undiscovered.

To streamline protein discovery, researchers have recently developed deep learning models that may predict the 3D structure of a protein for a set of amino acid sequences. However the inverse problem — predicting a sequence of amino acid structures that meet design targets — has proven even more difficult.

A latest advent in machine learning enabled Buehler and his colleagues to tackle this thorny challenge: attention-based diffusion models.

Attention-based models can learn very long-range relationships, which is vital to developing proteins because one mutation in an extended amino acid sequence could make or break your entire design, Buehler says. A diffusion model learns to generate latest data through a process that involves adding noise to training data, then learning to get better the info by removing the noise. They are sometimes simpler than other models at generating high-quality, realistic data that could be conditioned to fulfill a set of goal objectives to fulfill a design demand.

The researchers used this architecture to construct two machine-learning models that may predict a wide range of latest amino acid sequences which form proteins that meet structural design targets.

“Within the biomedical industry, you would possibly not need a protein that is totally unknown because then you definately don’t know its properties. But in some applications, you would possibly need a brand-new protein that is comparable to 1 present in nature, but does something different. We will generate a spectrum with these models, which we control by tuning certain knobs,” Buehler says.

Common folding patterns of amino acids, often called secondary structures, produce different mechanical properties. For example, proteins with alpha helix structures yield stretchy materials while those with beta sheet structures yield rigid materials. Combining alpha helices and beta sheets can create materials which can be stretchy and robust, like silks.

The researchers developed two models, one which operates on overall structural properties of the protein and one which operates on the amino acid level. Each models work by combining these amino acid structures to generate proteins. For the model that operates on the general structural properties, a user inputs a desired percentage of various structures (40 percent alpha-helix and 60 percent beta sheet, as an illustration). Then the model generates sequences that meet those targets. For the second model, the scientist also specifies the order of amino acid structures, which provides much finer-grained control.

The models are connected to an algorithm that predicts protein folding, which the researchers use to find out the protein’s 3D structure. Then they calculate its resulting properties and check those against the design specifications.

Realistic yet novel designs

They tested their models by comparing the brand new proteins to known proteins which have similar structural properties. Many had some overlap with existing amino acid sequences, about 50 to 60 percent usually, but in addition some entirely latest sequences. The extent of similarity suggests that most of the generated proteins are synthesizable, Buehler adds.

To make sure the anticipated proteins are reasonable, the researchers tried to trick the models by inputting physically inconceivable design targets. They were impressed to see that, as a substitute of manufacturing improbable proteins, the models generated the closest synthesizable solution.

“The training algorithm can pick up the hidden relationships in nature. This offers us confidence to say that whatever comes out of our model may be very more likely to be realistic,” Ni says.

Next, the researchers plan to experimentally validate a number of the latest protein designs by making them in a lab. Additionally they wish to proceed augmenting and refining the models so that they can develop amino acid sequences that meet more criteria, resembling biological functions.

“For the applications we’re occupied with, like sustainability, medicine, food, health, and materials design, we’re going to must transcend what nature has done. Here’s a latest design tool that we will use to create potential solutions that may help us solve a number of the really pressing societal issues we face,” Buehler says.

“Along with their natural role in living cells, proteins are increasingly playing a key role in technological applications starting from biologic drugs to functional materials. On this context, a key challenge is to design protein sequences with desired properties suitable for specific applications. Generative machine-learning approaches, including ones leveraging diffusion models, have recently emerged as powerful tools on this space,” says Tuomas Knowles, professor of physical chemistry and biophysics at Cambridge University, who was not involved with this research. “Buehler and colleagues show a vital advance on this area by providing a design approach which allows the secondary structure of the designed protein to be tailored. That is an exciting advance with implications for a lot of potential areas, including for designing constructing blocks for functional materials, the properties of that are governed by secondary structure elements.”

“This particular work is fascinating since it is examining the creation of recent proteins that mostly don’t exist, but then it examines what their characteristics could be from a mechanics-based direction,” adds Philip LeDuc, the William J. Brown Professor of Mechanical Engineering at Carnegie Mellon University, who was also not involved with this work. “I personally have been fascinated by the concept of making molecules that don’t exist which have functionality that we haven’t even imagined yet. That is an amazing step in that direction.”

This research was supported, partly, by the MIT-IBM Watson AI Lab, the U.S. Department of Agriculture, the U.S. Department of Energy, the Army Research Office, the National Institutes of Health, and the Office of Naval Research.