It’s an exciting day in the world of physics & music. Researchers have discovered that proteins have their own unique musical vibrations, & have created their very own musical scores by using AI and proteins.
Proteins are the building blocks of the human body, found in our hair, our tendons, our muscles, and everywhere else. They’re a part of us, and it turns out they can make music too.
The findings were published in the journal APL Bioengineering on Tuesday.
Proteins are naturally found in anything from silk to human cells, however, scientists have no way to automatically figure out their design, and need them to create new proteins.
This is where engineers, Markus Buehler (MIT) & Chi Hua Yu (The National Cheng Kung University in Taiwan), come in. They discovered that each of the 20 amino acids that make up a protein has its very own sound.
Intent on plugging the gap, Buehler and Yu came up with a workaround that started with a single, very left field observation: each of the twenty amino acids that make a protein has its own vibration frequency.
Which is a necessity if you want to make musical notes of different pitches.
Then the pair came up with another insight – proteins and music share a hierarchical structure. The structure for proteins is the varied ordering of the amino acids, such as leucine, alanine and cysteine, in a chain.
As you climb the ladder of complexity there is a panoply of twists and folds, including helical arrangements and pleated structures called beta sheets, that are integral to the protein’s function, whether that be the strength of a tendon or the catalytic properties of an enzyme. The hierarchy of music is surprisingly similar.
At the base, there is pitch, the notes of the C major scale for example. But for composers to work their magic the length of notes must be altered, multiple pitches are played simultaneously to form chords, and then hundreds of other variations are added until you have an Eroica or Bittersweet symphony.
Now Buehler and Yu decided to take their experiment further by assigning each protein trait a musical analogue. For example, a specific amino acid was assigned the musical note “C”, and so on and so forth.
But that wasn’t enough to satiate Buehler and Yu’s thirst for science and technology. The team then trained a deep learning algorithm on data sets that included a number of proteins and their linked musical scores.
Once the training was done, the algorithm was prompted with bits of music to start producing entirely new musical compositions. This is music like you’ve never heard before.
The result was never before heard music. Which translated back to never before invented proteins that could say Buehler and Yu, form part of future targeted protein design, to make new enzymes for example.
The researchers even built in a knob to dial-up or down the creativity of their AI.
Increasing the temperature during protein design ramped up the randomness of the musical creations & their partner proteins. Reducing the temperature pulled back the manufacturing process in a better way.
It’s not yet certain how this discovery will assist science, however, Buehler is optimistic as he stated “This paves the way for making entirely new biomaterials. Or perhaps you find an enzyme in nature and want to improve how it catalyzes or come up with new variations of proteins altogether.”
More in AI