The Center for Biomarker Research and Precision Medicine at Virginia Commonwealth University has a new study published in Molecular Psychiatry showing how the combination of artificial intelligence (AI) and genomics can produce DNA biomarkers that predict nearly 17 years after exposure to mental health problems: youth trauma.
Childhood trauma was assessed by events that converge with DSM after-traumatic tension Disorder Criteria in the Child and Adolescent Psychiatric Assessment (CAPA) and the Young Adult Psychiatric Assessment (YAPA) of hundreds of children ages 9-13 who participated in the 30-year study initiated by Duke University and the North Carolina Department of Health and Human Services called the Great Smoky Mountain Study (GSM). Bloodstain samples and clinical data were collected for each wave.
More than 970 bloodstain samples were used from more than 480 participants who delivered more than 670 samples before reaching age 21, along with a subset of more than 300 participants who delivered a sample in adulthood.
“We predict the outcome for adults based on DNA methylation,” said lead author Edwin van den Oord, PhD, a Dutch psychiatric geneticist, professor and director of the Center for Biomarker Research and Precision Medicine at Virginia Commonwealth University. “We found a wide range of outcomes, such as mature depression, anxiety, alcohol abuse, nicotine addictionpoverty, social and medical problems.”
Neuropsychiatric diseases and cancer have been associated with changes in DNA methylation. According to Van den Oord, there are 28 million places in the human genome where methylation can take place.
“We know where all the SNPs (single nucleotide polymorphisms) are,” said Van den Oord. “We take the human reference genome from the Human Genome project and search for CG sites, and then we input all the SNPs.”
Genetics is the branch of biology that studies the genes, genetic variation, and heredity in living organisms. DNA, deoxyribonucleic acid, is the hereditary material in humans and most organisms where the information is stored as a code made up of four chemical bases: adenine (A), guanine (G), cytosine (C) and thymine (T).
DNA can be modified by environmental factors, and epigenetic change, which can alter gene expression. DNA methylation, the process of adding methyl groups to DNA bases, is an epigenetic modification. Since methylation often occurs at CpG, or CG, sites, the researchers determined the areas in the human genome where these sites occur. Specifically, they identified regions of the DNA where a cytosine nucleotide is followed by a guanine nucleotide.
To determine all possible sites that can be methylated in a majority of humans, the researchers started by identifying CpG sites in the Human Genome Project’s reference human genome.
“We fragment the DNA and change it into small pieces, like 100 base pairs, and then sequence it,” says Van den Oord. “And now we know the sequence of all these little fragments. And then we have to match it to the reference genome. If something corresponds to a location that has a CpG, we calculate how much methylation is taking place for that location.”
The scientists calculated the risk scores for methylation using artificial intelligence (AI) machine learning. In AI, Elastic Net linear regression is a method that combines Lasso (Least Absolute Shrinkage and Selection Operator) and Ridge regression methods.
The predictive power of the methylation risk scores generated by the AI algorithm was “higher than that of reported trauma and could not be explained by the reported trauma, correlations with demographic variables, or a continuity of the predicted health problems from childhood to adulthood.”
According to researchers, the methylation risk scores predicted a wide range of adverse outcomes and have the potential to serve as a clinical biomarker to evaluate health risks of trauma exposure.
Copyright © 2022 Cami Rosso All rights reserved.