Current diagnoses of mood disorders are not cross validated. The aim of the current paper is to explain how machine learning techniques can be used to a) construct a model which ensembles risk/resilience (R/R), adverse outcome pathways (AOPs), staging, and the phenome of mood disorders, and b) disclose new classes based on these feature sets. This study was conducted using data of 67 healthy controls and 105 mood disordered patients. The R/R ratio, assessed as a combination of the paraoxonase 1 (PON1) gene, PON1 enzymatic activity, and early life time trauma (ELT), predicted the high-density lipoprotein cholesterol – paraoxonase 1 complex (HDL-PON1), reactive oxygen and nitrogen species (RONS), nitro-oxidative stress toxicity (NOSTOX), staging (number of depression and hypomanic episodes and suicidal attempts), and phenome (the Hamilton Depression and Anxiety scores and the Clinical Global Impression; current suicidal ideation; quality of life and disability measurements) scores. Partial Least Squares pathway analysis showed that 44.2% of the variance in the phenome was explained by ELT, RONS/NOSTOX, and staging scores. Cluster analysis conducted on all those feature sets discovered two distinct patient clusters, namely 69.5% of the patients were allocated to a class with high R/R, RONS/NOSTOX, staging, and phenome scores, and 30.5% to a class with increased staging and phenome scores. This classification cut across the bipolar (BP1/BP2) and major depression disorder classification and was more distinctive than the latter classifications. We constructed a nomothetic network model which reunited all features of mood disorders into a mechanistically transdiagnostic model.

Background: There is a strong comorbidity between mood disorders and metabolic syndrome (MetS). Increased levels of reactive oxygen and nitrogen species (RONS) and nitro-oxidative stress toxicity (NOSTOX) partially underpin this comorbidity.Aims: To examine the associations of RONS/NOSTOX biomarkers with MetS after adjusting for the significant effects of mood disorders (major depression, and bipolar type 1 and 2), generalized anxiety disorder (GAD), tobacco use disorder (TUD), and male sex.Methods: The study included subjects with (n=65) and without (n=107) MetS and measured levels of superoxide dismutase 1 (SOD1), lipid hydroperoxides (LOOH), nitric oxide metabolites (NOx), malondialdehyde (MDA), and advanced oxidation protein products (AOPP) and computed z unit-weighted composite scores which reflect RONS/NOSTOX. The study included 105 patients with mood disorders, 46 with GAD, and 95 with TUD.Results: MetS was associated with increased levels of MDA and AOPP, independently from mood disorders, TUD, sex and GAD. Atherogenicity and insulin resistance (IR) were significantly associated with a NOSTOX composite score. Mood disorders, TUD, GAD, male sex and MetS independently contribute to increased RONS/NOSTOX. The RONS/NOSTOX profile of MetS was different from that of GAD, which showed increased SOD1 and NOx levels. TUD was accompanied by increased SOD1, LOOH and MDA, and male sex by increased LOOH and AOPP.Conclusions: MetS is characterized by increased lipid peroxidation with aldehyde formation and chlorinative stress, and atherogenicity and IR are strongly mediated by RONS/NOSTOX. Partially shared RONS/NOSTOX pathways underpin the comorbidity of MetS with mood disorders, GAD, and TUD.