Understanding how DNA is folded in 3D is “crucial for figuring out how diseases develop,” but computer tools to analyse this structure often produce inconsistent results. Now, researchers at Case Western Reserve University have found that artificial intelligence programs are especially effective at handling this complex and low-quality data.
The work, published in Nature Communications, benchmarked 13 software tools against 10 datasets from mice and humans to help scientists better understand how DNA folds inside individual cells.
“The 3D structure of DNA affects how genes interact with each other, just like the layout of a house affects how people move through it,” said Fulai Jin, professor in the Department of Genetics and Genome Sciences at the Case Western Reserve School of Medicine.
The improved analysis could help scientists identify which genes are switched on or off in diseased cells, explain why treatments work for some patients but not others, and track how cells change during early development.
Building better microscopes
“We’re essentially helping scientists find or build better microscopes to see how DNA works inside individual cells,” Jin said. “This could lead to a better understanding of genetic diseases and potentially new treatment strategies.”
To aid other researchers, the team created a new software package, which is freely available on GitHub. Jin said the software acts “like a GPS app” by testing multiple approaches and recommending the optimal one for a scientist’s specific data.
“This is a significant step toward making sense of the massive genetic data from modern sequencing — and toward understanding how our genetic blueprint truly works,” Jin said.
