A novel blood-based epigenetic biosignature in first-episode schizophrenia patients through automated machine learning.

Schizophrenia (SCZ) is a chronic, severe, and complex psychiatric disorder that affects all aspects of personal functioning. While SCZ has a very strong biological component, there are still no objective diagnostic tests. Lately, special attention has been given to epigenetic biomarkers in SCZ. In this study, we introduce a three-step, automated machine learning (AutoML)-based, data-driven, biomarker discovery pipeline approach, using genome-wide DNA methylation datasets and laboratory validation, to deliver a highly performing, blood-based epigenetic biosignature of diagnostic clinical value in SCZ. Publicly available blood methylomes from SCZ patients and healthy individuals were analyzed via AutoML, to identify SCZ-specific biomarkers. The methylation of the identified genes was then analyzed by targeted qMSP assays in blood gDNA of 30 first-episode drug-naïve SCZ patients and 30 healthy controls (CTRL). Finally, AutoML was used to produce an optimized disease-specific biosignature based on patient methylation data combined with demographics. AutoML identified a SCZ-specific set of novel gene methylation biomarkers including IGF2BP1, CENPI, and PSME4. Functional analysis investigated correlations with SCZ pathology. Methylation levels of IGF2BP1 and PSME4, but not CENPI were found to differ, IGF2BP1 being higher and PSME4 lower in the SCZ group as compared to the CTRL group. Additional AutoML classification analysis of our experimental patient data led to a five-feature biosignature including all three genes, as well as age and sex, that discriminated 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 enabled the discovery of three novel genes and an epigenetic biosignature bearing potential value as promising SCZ blood-based diagnostics.

Small-world networks and disturbed functional connectivity in schizophrenia.

Disturbances in "functional connectivity" have been proposed as a major pathophysiological mechanism for schizophrenia, and in particular, for cognitive disorganization. Detection and estimation of these disturbances would be of clinical interest. Here we characterize the spatial pattern of functional connectivity by computing the "synchronization likelihood" (SL) of EEG at rest and during performance of a 2Back working memory task using letters of the alphabet presented on a PC screen in subjects with schizophrenia and healthy controls. The spatial patterns of functional connectivity were then characterized with graph theoretical measures to test whether a disruption of an optimal spatial pattern ("small-world") of the functional connectivity network underlies schizophrenia. Twenty stabilized patients with schizophrenia, who were able to work, and 20 healthy controls participated in the study. During the working memory (WM) task healthy subjects exhibited small-world properties (a combination of local clustering and high overall integration of the functional networks) in the alpha, beta and gamma bands. These properties were not present in the schizophrenia group. These findings are in accordance with a partially inadequate organization of neuronal networks in subjects with schizophrenia. This method could be helpful for diagnosis and evaluation of the severity of the disease, as well as understanding the pathophysiologic mechanisms underlying cognitive dysfunction in schizophrenia.