Each and every individual has a complicated genome. With numerous variances within each individual, it is comparable to three billion letters of code. Perhaps it is impossible for a human to sit and evaluate all that code.
However, according to a research published in the journal named “Nature Machine Intelligence”, Artificial Intelligence has the ability to spot things that humans may miss through billions of codings. Someday, AI-powered genome readers may even be able to predict the incidence of diseases from cancer to the common cold. Unfortunately, AI’s recent popularity surge has led to a bottleneck in innovation. “It’s like the Wild West right now. Everyone’s just doing whatever the hell they want,” says Cold Spring Harbor Laboratory (CSHL) Assistant Professor Peter Koo. Just like Frankenstein’s monster was a mix of different parts, AI researchers are constantly building new algorithms from various sources. And it’s difficult to judge whether their creations will be good or bad. After all, how can scientists judge “good” and “bad” when dealing with computations that are beyond human capabilities?
That’s where GOPHER, the Koo lab’s newest invention, comes in. GOPHER (short for GenOmic Profile-model compreHensive EvaluatoR) is a new method that helps researchers identify the most efficient AI programs to analyze the genome. “We created a framework where you can compare the algorithms more systematically,” explains Ziqi Tang, a graduate student in Koo’s laboratory.
GOPHER judges AI programs on several criteria: how well they learn the biology of our genome, how accurately they predict important patterns and features, their ability to handle background noise, and how interpretable their decisions are. “AI are these powerful algorithms that are solving questions for us,” says Tang. But, she notes: “One of the major issues with them is that we don’t know how they came up with these answers.”
GOPHER helped Koo and his team dig up the parts of AI algorithms that drive reliability, performance, and accuracy. The findings help define the key building blocks for constructing the most efficient AI algorithms going forward. “We hope this will help people in the future who are new to the field,” says Shushan Toneyan, another graduate student at the Koo lab.
Imagine having a health issue and being able to pinpoint it with the touch of a button. This science fiction cliché may one day become a standard fixture in every doctor’s office thanks to AI. Artificial intelligence (AI) programmes may recognise distinctive features of our genome that result in individualised medicine and treatments, much like video-streaming algorithms that learn users’ preferences based on their viewing history. The Koo team is hoping that GOPHER will aid in refining such AI algorithms so that we can be confident they are picking up the right information for the right purposes.
Toneyan says: “If the algorithm is making predictions for the wrong reasons, they’re not going to be helpful.”
