Researches conducted in the treatment of schizophrenia and autism, have made significant progress in the area. These diseases would otherwise take a lifetime to cure. The advancements, in particular, has led to the discovery of some hundreds of genetic loci which were found to be associated with the risk of mental health states.
A locus in genetics means a fixed position on a chromosome, as the position of a gene or a genetic marker. Each chromosome carries many genes and the human's estimated 'haploid' protein-coding genes are 19,000–20,000, on the 23 different chromosomes.
The loci do not necessarily identify with a particular gene and because of that the development and experience of schizophrenia cannot be linked to something as simple as variations in a particular gene. Besides some studies have come to the conclusion that the actual effect of many of these loci regarding the risk of the condition varies from patient to patient.
A group of researchers from the Geffen School of Medicine at UCLA's, SUNY Downstate Medical Center College of Medicine, and the School of Medicine at the University of North Carolina have come together to generate a refined model to learn the effect of these on more global genomes in patients with schizophrenia.
This team better known as PsychENCODE used AI and deep learning to analyze the genetic data from relevant studies of the past, including their own to construct and run this model. This data is not just concerned with the actual genes and their expression but also the rest of the applicable genes and loci that influence similar expressions. These tracts of DNA are known to be regulatory networks and include ‘enhancer’ genes and loci that are meant to promote the expression of certain other genes which are more directly involved in brain activity and structure.
These interactions were conceptualised in a 3D way for better understanding. In other words, the possibility that certain genes are able to affect others, due to their proximity affected by the way DNA is packed into chromosomes, was also studied in this model.
The resulting model was then applied to the 142 risk loci for schizophrenia. It was found that these loci, in fact, control 321 additional genes, some of which were identified as risk factors of the same condition as in the previous studies. Therefore, it appears that the new model is powerful enough to track the actual roles of the ‘risky’ DNA in this disorder.
The PsychENCODE team concludes that their new model can be used to generate similar genetic profiles for other, related mental health conditions. Autism disorders and bipolar disorders (which has a similar genetic ‘overlap’ with schizophrenia) are likely to be modelled using PsychENCODE, according to the team.
The new model output was compared to a more established, one based on the non-regulatory genome. It was found that PsychENCODE was more accurate.
The researchers are now of the opinion that it can be used to create more powerful, precise assessments for those who may have a chance of exhibiting various psychiatric conditions. This can lead to improved treatments for the patients in question. Therapies are recommended based on the genetic-risk profile of individuals who are more likely to be affected. Therefore, the PsychENCODE model and its following models would be an effective tool in this form of treatment.
The research and method of PsychENCODE were constructed on the data gathered from the hundreds of studies that were already done on the genes that may play a role in conditions such as schizophrenia.
The PsychENCODE project, was funded by the National Institute of Mental Health (NIMH), may also have helped confirm the study that neurological disorders and the chances of developing one are too complex to be defined through a simple gene-expression activity.