1 min read

SQUID pries open AI black box

SQUID pries open AI black box
SQUID pries open AI black box - CSHL scientists have engineered a new computational tool named SQUID to plumb the depths of AI’s mysterious inner workings. AI-generated image.

COLD SPRING HARBOR, N.Y.June 21, 2024 — Artificial intelligence continues to squirm its way into many aspects of our lives. But what about biology, the study of life itself? AI can sift through hundreds of thousands of genome data points to identify potential new therapeutic targets. While these genomic insights may appear helpful, scientists aren’t sure how today’s AI models come to their conclusions in the first place. Now, a new system named SQUID arrives on the scene armed to pry open AI’s black box of murky internal logic.

SQUID, short for Surrogate Quantitative Interpretability for Deepnets, is a computational tool created by Cold Spring Harbor Laboratory (CSHL) scientists. It’s designed to help interpret how AI models analyze the genome. Compared with other analysis tools, SQUID is more consistent, reduces background noise, and can lead to more accurate predictions about the effects of genetic mutations.

 

Google News

Stay on Top with AI News!

Follow our Google News page!

How does it work so much better? The key, CSHL Assistant Professor Peter Koo says, lies in SQUID’s specialized training. Koo explains:

“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’re not optimal for genomics. What we did with SQUID was leverage decades of quantitative genetics knowledge to help us understand what these deep neural networks are learning.”

SQUID works by first generating a library of over 100,000 variant DNA sequences. It then analyzes the library of mutations and their effects using a program called MAVE-NN (Multiplex Assays of Variant Effects Neural Network). This tool allows scientists to perform thousands of virtual experiments simultaneously. In effect, they can “fish out” the algorithms behind a given AI’s most accurate predictions. Their computational “catch” could set the stage for experiments that are more grounded in reality. CSHL Associate Professor Justin Kinney, a co-author of the study, explains:

“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.”

There are tons of AI models in the sea. More enter the waters each day. Koo, Kinney, and colleagues hope that SQUID will help scientists grab hold of those that best meet their specialized needs.

Though mapped, the human genome remains an incredibly challenging terrain. SQUID could help biologists navigate the field more effectively, bringing them closer to their findings’ true medical implications.

About Cold Spring Harbor Laboratory
Founded in 1890, Cold Spring Harbor Laboratory has shaped contemporary biomedical research and education with programs in cancer, neuroscience, plant biology and quantitative biology. Home to eight Nobel Prize winners, the private, not-for-profit Laboratory employs 1,000 people including 600 scientists, students and technicians. For more information, visit www.cshl.edu

SOURCE Cold Spring Harbor Laboratory

Laszlo Szabo / NowadAIs

As an avid AI enthusiast, I immerse myself in the latest news and developments in artificial intelligence. My passion for AI drives me to explore emerging trends, technologies, and their transformative potential across various industries!

Categories

Follow us on Facebook!

4colors Research Finalist in Airbus-BMW Quantum Computing Challenge
Previous Story

4colors Research Named Finalist in Quantum-Powered Logistics Challenge by Airbus and BMW

Tianjin Advances with AI
Next Story

Tianjin Advances with AI

Latest from Blog

2024 WIC Wuzhen Summit set for November

2024 WIC Wuzhen Summit set for November

Last Updated on October 9, 2024 7:22 am by Laszlo Szabo / NowadAIs | Published on October 9, 2024 by Juhasz “the Mage” Gabor BEIJING, Oct. 9, 2024 — A report from CRIOnline: The 2024
Go toTop