Scientists from NVIDIA and Harvard have made a huge breakthrough in genetic research. They developed a deep-learning toolkit that is able to significantly cut down the time and cost needed to run rare and single-cell experiments. According to a study published in Nature Communications, the AtacWorks toolkit can run inference on a whole genome, a process that normally takes a little over two days, in just half an hour. It’s able to do so thanks to NVIDIA’s 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 liver, blood or skin cells). This is the part of a person’s genome that could give scientists indications on whether a person could have Alzheimer’s, heart disease or cancer.
ATAC-sec usually requires the analysis of tens of thousands of cells, but AtacWorks is able to get the same results using only tens of cells. Researchers also applied AtacWorks to a dataset of stem cells that produce red and white blood cells, subtypes that typically can’t be studied using traditional methods. But with AtacWorks, they were able to identify separate parts of the DNA associated with white blood cells and red blood cells respectively.
The ability to analyze the genome faster and cheaper will go a long way in identifying the specific mutations or biomarkers that could lead to certain diseases. It could even help drug discovery by helping researchers figure out how the disease works.
“With very rare cell types, it’s not possible to study differences in their DNA using existing methods,” said NVIDIA researcher and the paper’s lead author Avantika Lal. “AtacWorks can help not only drive down the cost of gathering chromatin accessibility data, but also open up new possibilities in drug discovery and diagnostics.”