Researchers translate proteins into musical compositions, and vice versa

A team of scientists at MIT have developed a system to convert protein sequences into audible sound that resembles musical passages. Then, by reversing the process, researchers can introduce variations in the sounds and convert them back into brand new proteins.

Yu et al report a method to translate amino acid sequences into audible sound, use representation in musical space to train a neural network, and then apply it to generate protein designs using artificial intelligence. Image credit: Yu et al, doi: 10.1021 / acsnano.9b02180.

MIT’s Professor Buehler and his colleagues transposed the unique natural vibrational frequencies of 20 types of amino acids – the building blocks that come together in chains to form all proteins – into sound frequencies that humans can hear.

In this way, the scientists generated a scale made up of 20 unique tones.

Unlike musical notes, however, each amino acid tone consisted of the layering of many different frequencies – similar to a chord.

The researchers translated several proteins into audio compositions, the duration of each tone being specified by the different 3D structures that make up the molecule.

“The whole concept is to better understand proteins and their wide range of variations,” said Professor Buehler, head of the Department of Civil and Environmental Engineering at MIT.

“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. “

“But their structures, including the way they bend into the shapes that often determine 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.

Finally, the team used artificial intelligence (AI) to recognize specific musical patterns that matched certain protein architectures.

The computer then generated scores and translated them into proteins new to nature.

“No synthetic or natural instruments are used, which shows how this new source of sound can be used as a creative platform,” said Professor Buehler.

“Musical motifs derived from both naturally occurring proteins and from AI-generated proteins are used in the examples, and all sounds, including some that sound like bass or snare drums, are also generated from them. amino acid sounds. “

The teams job was published in the journal ACS Nano.


Chi hua yu et al. A self-consistent sonication method to translate amino acid sequences into musical compositions and application in protein design using artificial intelligence. ACS Nano, published online June 26, 2019; doi: 10.1021 / acsnano.9b02180

About Madeline J. Carter

Check Also

Cincinnati Chamber Orchestra’s Summermusik Festival Brings Award-Winning Compositions to Queen City | cultural | Cincinnati

Click to enlarge Photo: Sergio R. Reyes A performance by Héctor del Curto will open …