DNA Methylation Sites IDed by Machine Learning Algorithm

A research team led by investigators at the Children's Hospital of Philadelphia (CHOP) and New Jersey Institute of Technology (NJIT) has released their findings for a new algorithm they developed that uses machine learning to predict sites of DNA methylation--a process that can change the activity of DNA without changing its overall structure--and could identify disease-causing mechanisms that would otherwise be missed by conventional screening methods. Findings from the new study were published recently in Nature Machine Intelligence through an article titled "Elucidation of DNA methylation on N6-adenine with deep learning." DNA methylation is involved in many key cellular processes and an important component in gene expression. Likewise, errors in methylation can be linked to a variety of human diseases. While genomic sequencing tools are effective at pinpointing polymorphisms that may cause disease, those same methods are unable to capture the effects of methylation because the individual genes still look the same.