Researchers from Harvard University and Tech Company Nvidia will launch Artificial Intelligence-based deep learning platform for Cell DNA analysis.
An artificial intelligence-based toolkit named AtacWorks will be used to study epigenomics, which is the study of modification on the genetic material of a cell.
What is AtacWorks?
AtacWorks is a neural network based on Pytorch. It was trained on labelled pairs of matching ATAC-seq datasets of one high-quality and noisy dataset. The model learned to predict an accurate, high-quality version of a dataset and identify peaks in the signal.
The deep learning toolkit was originally a neural network for computer vision. This toolkit would allow to study and analyse of genomic variations in human cells leading to different types of diseases.
AtacWorks will be able to diagnose and predict situations, which at a time seemed impossible for the biological world. As a result, this would lead to the discovery of new drug targets.
AtacWorks employs ATAC-seq used to discover parts of the genome that can be accessed through human cells thereby allowing the understanding of the variability of a cell and what makes the cell infected or cancerous.
AttackWorks was proved to be successful in identifying the genome sequence related to producing white blood cells and red blood cells as the human DNA is a complex structure and requires a deep and stable study process.
This approach decodes a range of diseases, including cardiovascular disease, Alzheimer’s, diabetes and neurological disorders contrary to the systems today which use 15 hours with 32 CPU cores to work this kind of data
In the future, it is possible that we train models using whatever data we have available and apply it to entirely new biological samples making it a revolution in the complex DNA world.
By: Mannu Mathew | Sub Editor | ELE Times