A huge breakthrough in genetic research has been made by scientists from NVIDIA and Harvard, who developed a deep-learning toolkit through which time and cost needed to run rare and single-cell experiments can be reduced. According to a study published in Nature Communications, this toolkit named “AtacWorks” uses NVIDIA’s Tensor Core GPUs to run inference on a whole genome, which normally takes over two days of time to complete, but now can be done in just half an hour.
“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.”
AtacWorks toolkit works with ATAC-seq, a method designed to find “open areas” (subsections of a person’s DNA that are used to determine and activate specific functions) in the genome of healthy and diseased cells. Open Areas could give scientists indications about a person who could have Alzheimer’s, heart disease, or cancer or not.
ATAC-sec usually, tens of thousands of cells are required for analysis, but with the AtacWorks toolkit, we can get the same results by only using tens of cells. This technique will further help in the identification of the specific mutations or biomarkers that could lead to certain diseases and could even help drug discovery by helping researchers figure out how the disease works.
[…] couple of changes. They were likewise ready to demonstrate how valuable it very well may be in huge genetic tests. During their tests, they had the option to discover antibiotics resistance mutations in E. coli by […]