黑料吃瓜资源

Imagine you鈥檙e looking at millions upon millions of mysterious genetic mutations. With CRISPR gene-editing technology, a select few of these mutations might have therapeutic potential. However, proving it would mean many thousands of hours of lab work. Just figuring out which ones are worth exploring further would take a lot of time and money. But what if you could do it in the virtual realm with artificial intelligence?

CREME is a new AI-powered virtual laboratory invented by 黑料吃瓜资源 (CSHL) Assistant Professor Peter Koo and his team. It allows geneticists to run thousands of virtual experiments with the click of a button. Now, scientists can use it to begin identifying and understanding key regions of the genome.

The program is modeled after CRISPR interference (CRISPRi), a genetic perturbation technique based on CRISPR. CRISPRi allows biologists to turn down the activity of specific genes in a cell. CREME lets scientists make similar changes in the virtual genome and predicts their effects on gene activity. In other words, it鈥檚 almost like an AI version of CRISPRi. Koo explains:

鈥淚n reality, CRISPRi is incredibly challenging to perform in the laboratory. And you’re limited by the number of perturbations and the scale. But since we鈥檙e doing all our perturbations [virtually], we can push the boundaries. And the scale of experiments that we performed is unprecedented鈥攈undreds of thousands of perturbation experiments.鈥�

Koo and his team tested CREME on another AI-powered genome analysis tool called Enformer. They wanted to know how Enformer鈥檚 algorithm makes predictions about the genome. Questions like that are central to Koo鈥檚 work, he says.

鈥淲e have these big, powerful models. They鈥檙e quite compelling at taking DNA sequences and predicting gene expression. But we don’t really have any good ways of trying to understand what these models are learning. Presumably, they鈥檙e making accurate predictions because they鈥檝e learned a lot of the rules about gene regulation, but we don鈥檛 actually know what their predictions are based off of.鈥�

With CREME, Koo鈥檚 team uncovered a series of genetic rules that Enformer learned while analyzing the genome. That insight may one day prove invaluable for drug discovery. 鈥淯nderstanding the rules of gene regulation gives you more options for tuning gene expression levels in precise and predictable ways,鈥� says Koo.

With further fine-tuning, CREME may soon set geneticists on the path to discovering new therapeutic targets. Perhaps most impactfully, it may even give scientists who do not have access to a real laboratory the power to make these breakthroughs.

Written by: Luis Sandoval, Communications Specialist | [email protected] | 516-367-6826

Funding

National Human Genome Research Institute, National Institute of General Medical Sciences, Simons Center for Quantitative Biology, National Institutes of Health, NVIDIA GPU Grant Program

Citation

Toneyan, S., et al., 鈥淚nterpreting cis-regulatory Interactions from large-scale deep neural networks鈥�, Nature Genetics, Sept 16, 2024. DOI: