This site is part of the Siconnects Division of Sciinov Group
This site is operated by a business or businesses owned by Sciinov Group and all copyright resides with them.
ADD THESE DATES TO YOUR E-DIARY OR GOOGLE CALENDAR
17 Jun, 2024
A study published in the Translational Psychiatry journal highlights that schizophrenia (SCZ) is a chronic, severe, and complex psychiatric disorder affecting various aspects of personal functioning. Although SCZ has a strong biological basis, there are currently no objective diagnostic tests available. Recently, there has been increased focus on identifying epigenetic biomarkers for SCZ. This study presents a novel, three-step, automated machine learning (AutoML)-based, data-driven approach for biomarker discovery. By utilizing genome-wide DNA methylation datasets and laboratory validation, the study aims to develop a highly effective blood-based epigenetic biosignature with diagnostic value for SCZ.
The researchers analyzed publicly available blood methylomes from SCZ patients and healthy controls using AutoML to identify SCZ-specific biomarkers. These identified gene methylation markers were further analyzed using targeted qMSP assays in the blood gDNA of 30 first-episode drug-naïve SCZ patients and 30 healthy controls (CTRL). Finally, AutoML was employed to create an optimized disease-specific biosignature, combining patient methylation data with demographic information.
The study identified a novel set of SCZ-specific gene methylation biomarkers, including IGF2BP1, CENPI, and PSME4. Functional analysis explored the connections between these biomarkers and SCZ pathology, revealing that IGF2BP1 methylation was higher and PSME4 methylation was lower in SCZ patients compared to healthy controls, while CENPI showed no significant difference. An additional AutoML classification analysis incorporating all three genes, along with age and sex, resulted in a five-feature biosignature that successfully distinguished SCZ patients from healthy individuals [AUC 0.755 (0.636, 0.862) and average precision 0.758 (0.690, 0.825)].
In conclusion, this three-step pipeline facilitated the discovery of three novel genes and an epigenetic biosignature, offering promising potential for developing blood-based diagnostic tools for schizophrenia.