A team of scientists at MIT has developed a system for converting protein sequences into audible sound that resembles musical passages. Then, reversing the process, the researchers can introduce some variations into 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 the representation in the 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 Professor Buehler and colleagues transposed unique natural vibrational frequencies of 20 types of amino acids — the building blocks that join together in chains to form all proteins — into sound frequencies that humans can hear.
In this way, the scientists generated a scale consisting of 20 unique tones.
Unlike musical notes, however, each amino acid tone consisted of the overlay of many different frequencies — similar to a chord.
The researchers translated several proteins into audio compositions, with the duration of each tone specified by the different 3D structures that make up the molecule.
“The whole concept is to get a better handle on understanding proteins and their vast array of variations,” said Professor Buehler, head of the Department of Civil and Environmental Engineering at MIT.
“Proteins make up the structural material of skin, bone, and muscle, 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 fold themselves into the shapes that often determine their functions, are exceedingly 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 corresponded to certain protein architectures.
The computer then generated scores and translated them into new-to-nature proteins.
“There are no synthetic or natural instruments used, showing how this new source of sounds can be utilized as a creative platform,” Professor Buehler said.
“Musical motifs derived from both naturally existing proteins and AI-generated proteins are used throughout the examples, and all the sounds, including some that resemble bass or snare drums, are also generated from the sounds of amino acids.”
The team’s work was published in the journal ACS Nano.
_____
Chi-Hua Yu et al. A Self-Consistent Sonification 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
