Scientists NVIDIA and Harvard have made a huge breakthrough in genetic research. They have developed a deep learning toolkit capable of dramatically reducing the time and costs required to run rare, single-cell experiments. According to a study published in Nature communications, the AtacWorks Toolkit can perform whole genome inference, a process that normally takes just over two days, in just half an hour. It is able to do this thanks to NVIDIA Tensor Core GPUs.
AtacWorks works with ATAC-seq, a well-established method designed to find open areas in the genome of healthy and diseased cells. These “open areas” are subsections of a person’s DNA that are used to determine and activate specific functions (think cells in the liver, blood or skin). It’s the part of a person’s genome that could give scientists clues that a person might have Alzheimer’s disease, heart disease, or cancer.
ATAC-sec typically requires analysis of tens of thousands of cells, but AtacWorks is able to achieve the same results using only tens of cells. The researchers also applied AtacWorks to a dataset of stem cells that produce red and white blood cells, subtypes that generally cannot be studied using traditional methods. But with AtacWorks, they were able to identify distinct parts of DNA associated with white blood cells and red blood cells, respectively.
The ability to analyze the genome faster and more cheaply will go a long way in identifying specific mutations or biomarkers that could lead to certain diseases. It might even aid drug discovery by helping researchers understand how the disease works.
“With very rare cell types, it is not possible to study the differences in their DNA using existing methods,” said NVIDIA researcher and lead author of the article, Avantika Lal. “AtacWorks can not only help reduce the cost of collecting data on chromatin accessibility, but also open up new possibilities in drug discovery and diagnostics.”
