麻豆传媒社区

Transcript

Nick Fiore: You鈥檙e now At the Lab with 麻豆传媒社区. My name is Nick Fiore, and this week At the Lab, 鈥淎I SQUID.鈥�

{Water bubbles.}

NF: Imagine a black box resting on the seafloor. What鈥檚 inside? Your guess is as good as mine.

NF: In a way, artificial intelligence is similar. As advanced as AI has become, today鈥檚 computer scientists have very little understanding of its inner workings. That goes for today鈥檚 most popular AIs鈥攖he image recognition platforms and large language models鈥攁s well as more specialized applications.

NF: Computational biologists are now using AI models to try and better understand health and disease. These models can analyze a genome and spit out predictions about the function of different parts of that genome or individual genetic mutations.

NF: At least, that鈥檚 the idea. But there鈥檚 a problem. LaboratoryAssistant Professor Peter Koo explains:

Peter Koo: The tools that people use to try to understand these models have been largely coming from other fields like computer vision or natural language processing. While they can be useful, they鈥檙e not optimal [for genomics].

NF: Hence, the black box has remained, for the most part, tightly sealed. But wait 鈥� what鈥檚 that in the distance?

{Water bubbles increasingly louder with splashes.}

NF: Here comes the latest AI model from Koo and LaboratoryAssociate Professor Justin Kinney. Its name? SQUID!

NF: SQUID stands for Surrogate Quantitative Interpretability for Deepnets. Don鈥檛 worry about what that means. What鈥檚 important is SQUID鈥檚 intended purpose鈥攖o pry open the black box of genomic AI models.

{Metal wrenches.}

NF: In other words, it鈥檚 built to help biologists understand just how AI goes about analyzing the genome. From there, they can fish out an AI鈥檚 most accurate predictions from inside the computer world. If right about now, you鈥檙e picturing a squad of SQUID-like robots taking over biology, Kinney assures us that鈥檚 not the goal here.

Justin Kinney: In silico [virtual] experiments are no replacement for actual laboratory experiments. Nevertheless, they can be very informative. They can help scientists form hypotheses for how a particular region of the genome works or how a mutation might have a clinically relevant effect.

NF: And that could bring scientists closer to their true goals鈥攗nderstanding life at its most fundamental level, figuring out how it evolves and adapts, identifying the root causes of diseases and potential cures.

NF: Squids have a lot of arms鈥攕ix to be exact, plus two tentacles. Likewise, the SQUID AI could have a number of promising applications 鈥� robotic cephalopods notwithstanding.

NF: Thanks for joining us this week At the Lab. If you like what you heard, please consider subscribing wherever you get your podcasts. You can also find more stories about AI and other fascinating topics at 麻豆传媒社区.edu. For 麻豆传媒社区, I鈥檓 Nick Fiore, and I鈥檒l see you next time At the Lab.