Arc Institute’s Patrick Hsu on Building an App Store for Biology with AI

# How AI is Creating an App Store for Biology: Arc Institute’s Breakthrough

In a world obsessed with AI-generated chatbots and image creators, a quieter but potentially more profound revolution is happening at the intersection of artificial intelligence and biology. Arc Institute co-founder Patrick Hsu is leading this charge with EVO, an open-source biological foundation model that could transform how we understand our genetic code.

## The mystery of genetic mutations

Have you ever taken a 23andMe test or another genetic screening? If so, you might have encountered something scientists call “variants of unknown significance” – mutations in your DNA that, frankly, researchers don’t fully understand.

“Most of the mutations that you have, there’s sort of this… we call them variants of unknown significance, which is fancy scientist for ‘what the hell is going on?'” explains Hsu.

This is precisely the problem EVO was built to solve. By training on DNA itself – what Hsu calls “the fundamental information layer of life” – the AI model can identify patterns and predict the effects of genetic mutations with remarkable accuracy.

## More than just drug discovery

While much of the AI-biology conversation centers around discovering new medications, Hsu emphasizes this is just one application in a much broader landscape.

“ML for bio is not just drug design,” he argues. “This is actually ultimately a very important but narrow part of the potential of biology.”

Instead, Hsu envisions a comprehensive “app store for biology” built on foundation models like EVO, where researchers can develop specialized tools for everything from understanding breast cancer mutations to designing new CRISPR gene editing systems.

## Why DNA matters more than proteins

Many AI biology projects focus on proteins, which earned Nobel Prizes for researchers like David Baker and Demis Hassabis. But Hsu’s team at Arc Institute took a different approach by focusing on DNA itself.

“Proteins are encoded in DNA along with RNA and regulatory DNA and all of the things that you need to make life,” Hsu explains. This more fundamental approach provides a foundation for understanding biological systems at all scales.

The results speak for themselves. EVO is already best-in-class at predicting effects of breast cancer-causing mutations – knowledge that can influence life-altering medical decisions like whether someone needs preventative surgery.

##