Meet Jerry Xu, the 17-year-old Massachusetts student who built an AI program that turns protein structures into strings of numbers; he won $90,000
Imagine, what if a protein’s complex 3-D structure could be converted into a simple string of numbers—and that string could help scientists understand what the protein does? That’s the premise of an innovative AI model developed by 17-year-old Jerry Xu of Lexington, Massachusetts, who earned $90,000 in the Regeneron Science Talent Search for his research, states an online report by the Society for Science. Scroll down to read the details.
Converting protein structures to numbers
According to the online report, Xu’s project, “A Unified Protein Embedding Model With Local and Global Structural Sensitivity,” is in the area of computational biology and bioinformatics. His AI model is designed to compare the structures of proteins and amino acids rapidly. The structure of proteins gives important clues to how these molecules function. But it can take huge amounts of computing power to find and compare all the details in those structures. Another problem facing scientists is that of using large databases; current methods are either too slow to deal with vast collections of molecular frameworks or they miss important details. If we go by the report, Xu’s approach attempts to address both of these issues.
A quicker way to compare proteins
It has also been mentioned that Xu found that structural information can be distilled into numerical representations, or strings of numbers, while preserving key features of a protein’s shape. Such numerical representations can assist and accelerate the comparison of molecules by an AI system. Instead of having to reexamine every structural detail from scratch, researchers could use these representations to more efficiently find similarities between proteins. Also, the approach may be particularly useful when scientists are faced with protein regions whose functions are not yet known. By comparing their structures to better-studied molecules, researchers might get clues about what those unknown regions do.
Student who loves science
Xu is a student at Lexington High School, where he is captain of the math team and science bowl club. He is also interested in science education and community outreach. (Image: Society for Science)
Xu is a student at Lexington High School, where he is captain of the math team and science bowl club. He is also interested in science education and community outreach. He started a summer science lecture series for elementary to high school students with others. He teaches biology, mathematics and does live experiments. He is a teaching assistant for KTBYTE Computer Science Academy, where he helps students with their programming homework, states the report by the Society for Science.
Outside the project
But Xu’s coding interests don’t stop at biology. For the past two years, he has led a team of student programmers who build and maintain a free chatbot to help local residents learn about their town’s municipal budget. His work demonstrates how artificial intelligence and programming can be applied to solving problems ranging from molecular biology to everyday civic life.
A bright young scientist with big ideas
Xu’s protein work is a glimpse of how AI might help scientists cope with the vast amounts of structural information generated by modern biology. His model could speed up the comparison of proteins by translating complex molecular shapes into numbers and may also help researchers to probe unknown biological functions. Outside of science and coding, Xu likes Magic: The Gathering. He especially likes the challenge of devising strategies on a shoestring budget and with limited options – a good hobby for someone who spends his time coming up with creative solutions to complex problems.
