MIT Researchers Turn COVID-19 into a Classical Melody Using AI

#MIT_CEE Department Chair Markus Buehler's work was featured in @ScienceMagazine Science: https://t.co/2x52N5TjkL

— MIT CEE (@MIT_CEE) April 4, 2020

Creating an AI system that turns the coronavirus' structure into a melody could indeed assist scientists to spot specific details of COVID-19 that they may not have noticed until now. 

The AI-built tune is an accurate audible representation of how the coronavirus' spike proteins work. These spread the infection by reaching out of the virus and latching on to human cells. The name "corona", which means crown in Latin, is due to the fact that these spikes make the surface of the virus look like a crown. 

The coronavirus' spikes are made up of amino acids, and it's these that the MIT researchers turned into sounds. Each amino acid was given a unique note in the musical scale. 

Following this, the team created an algorithm that converted the data into a melody, which shows how the proteins are arranged. Have a listen to it below:

MIT shared a Q&A online in which project lead, Mark Buehler, explained the motivation behind their idea. Here are some of his explanations as to why this piece of music could in fact help scientists uncover further information about the coronavirus: 

"Our brains are great at processing sound! In one sweep, our ears pick up all of its hierarchical features: pitch, timbre, volume, melody, rhythm, and chords," he said.

"We would need a high-powered microscope to see the equivalent detail in an image, and we could never see it all at once. Sound is such an elegant way to access the information stored in a protein."

This type of research could assist scientists as follows: "We could search for a new protein that matches the melody and rhythm of an antibody capable of binding to the spike protein, interfering with its ability to infect," explained Professor Buehler.