Scientists have developed an artificial intelligence (AI) -activated system to translate protein structures into music and reconvert them to create new proteins never before seen in nature.
The method developed by researchers at the Massachusetts Institute of Technology (MIT) in the United States provides a systematic way to translate the amino acid sequence of a protein into a musical sequence, using the physical properties of molecules to determine sounds .
Although the sounds are transposed in order to bring them within the range audible to humans, the tones and their relationships are based on the actual vibrational frequencies of each amino acid molecule itself, calculated using theories of quantum chemistry.
The system, described in the journal ACS Nano, translates the 20 types of amino acids, the building blocks that come together in chains to form all proteins, on a 20-tone scale.
The long amino acid sequence of any protein then becomes a sequence of notes.
Markus Buehler, professor at MIT, said that after listening to the resulting melodies, he is now able to differentiate certain sequences of amino acids that are in harmony with proteins with specific structural functions.
The whole concept is to better understand proteins and their wide range of variations, Buehler said.
Proteins are the structural material of skin, bones, and muscles, but are also enzymes, signaling chemicals, molecular switches, and a host of other functional materials that make up the machinery of all living things.
Their structures, however, including the way they bend into the shapes that often establish their functions, are extremely complicated.
“They have their own language, and we don’t know how it works. We don’t know what makes a silk protein a silk protein or what patterns reflect the functions found in an enzyme. We don’t know the code. “, he added. he said.
Buehler and his team hope to gain new insight into the relationships and differences between different families of proteins and their variations.
They also want to use this as a way to explore the many possible adjustments and modifications to their structure and function by translating this language into a different form that humans are very familiar with.
This allows different aspects of information to be encoded in different dimensions, height, volume and duration, the researchers said.
As with music, the structure of proteins is hierarchical, with different levels of structure at different time scales, they said.
To study the catalog of melodies by a wide variety of different proteins, an artificial intelligence system was used by the team.
The AI system introduced slight changes in the musical sequence or created completely new sequences, and then translated the sounds into proteins that correspond to the modified or newly designed versions.
With this process, the team was able to create variations of existing proteins.
While the underlying rules may not be known to the researchers themselves, “AI has learned the language of protein design,” and it can code it to create variations of existing versions or designs. completely new protein, Buehler said.
Since there are “billions and billions” of potential combinations, he said, when it comes to creating new proteins, “you wouldn’t be able to do it from scratch, but that’s what AI can do. “
According to Buehler, training the AI system with a dataset for a particular class of proteins can take a few days, but it can then produce a design for a new variant in microseconds.
“No other method comes close,” he said.
“The downside is that the model doesn’t tell us what’s really going on inside. We just know it’s working,” Buehler said.
“When you look at a molecule in a textbook, it’s static,” Buehler said.
The process does not allow for any controlled modification. Any change in properties such as mechanical strength, elasticity or chemical reactivity will be essentially random.
“You have yet to experience it,” he said.
When a new protein variant is produced, “there is no way to predict what it will do.”
Musical compositions developed from the sounds of amino acids were created by the team, which define this new musical scale of 20 tones.
The works of art they built are made entirely of sounds generated from amino acids.