Prefrontal Cortex Cytosolic Proteome and Machine Learning-Based Predictors of Resilience toward Chronic Social Isolation in Rats.

Chronic social isolation (CSIS) generates two stress-related phenotypes: resilience and susceptibility. However, the molecular mechanisms underlying CSIS resilience remain unclear. We identified altered proteome components and biochemical pathways and processes in the prefrontal cortex cytosolic fraction in CSIS-resilient rats compared to CSIS-susceptible and control rats using liquid chromatography coupled with tandem mass spectrometry followed by label-free quantification and STRING bioinformatics. A sucrose preference test was performed to distinguish rat phenotypes. Potential predictive proteins discriminating between the CSIS-resilient and CSIS-susceptible groups were identified using machine learning (ML) algorithms: support vector machine-based sequential feature selection and random forest-based feature importance scores. Predominantly, decreased levels of some glycolytic enzymes, G protein-coupled receptor proteins, the Ras subfamily of GTPases proteins, and antioxidant proteins were found in the CSIS-resilient vs. CSIS-susceptible groups. Altered levels of Gapdh, microtubular, cytoskeletal, and calcium-binding proteins were identified between the two phenotypes. Increased levels of proteins involved in GABA synthesis, the proteasome system, nitrogen metabolism, and chaperone-mediated protein folding were identified. Predictive proteins make CSIS-resilient vs. CSIS-susceptible groups linearly separable, whereby a 100% validation accuracy was achieved by ML models. The overall ratio of significantly up- and downregulated cytosolic proteins suggests adaptive cellular alterations as part of the stress-coping process specific for the CSIS-resilient phenotype.

Prefrontal cortical synaptoproteome profile combined with machine learning predicts resilience towards chronic social isolation in rats.

Chronic social isolation (CSIS) of rats serves as an animal model of depression and generates CSIS-resilient and CSIS-susceptible phenotypes. We aimed to investigate the prefrontal cortical synaptoproteome profile of CSIS-resilient, CSIS-susceptible, and control rats to delineate biochemical pathways and predictive biomarker proteins characteristic for the resilient phenotype. A sucrose preference test was performed to distinguish rat phenotypes. Class separation and machine learning (ML) algorithms support vector machine with greedy forward search and random forest were then used for discriminating CSIS-resilient from CSIS-susceptible and control rats. CSIS-resilient compared to CSIS-susceptible rat proteome analysis revealed, among other proteins, downregulated glycolysis intermediate fructose-bisphosphate aldolase C (Aldoc), and upregulated clathrin heavy chain 1 (Cltc), calcium/calmodulin-dependent protein kinase type II (Cam2a), synaptophysin (Syp) and fatty acid synthase (Fasn) that are involved in neuronal transmission, synaptic vesicular trafficking, and fatty acid synthesis. Comparison of CSIS-resilient and control rats identified downregulated mitochondrial proteins ATP synthase subunit beta (Atp5f1b) and citrate synthase (Cs), and upregulated protein kinase C gamma type (Prkcg), vesicular glutamate transporter 1 (Slc17a7), and synaptic vesicle glycoprotein 2 A (Sv2a) involved in signal transduction and synaptic trafficking. The combined protein differences make the rat groups linearly separable, and 100% validation accuracy is achieved by standard ML models. ML algorithms resulted in four panels of discriminative proteins. Proteomics-data-driven class separation and ML algorithms can provide a platform for accessing predictive features and insight into the molecular mechanisms underlying synaptic neurotransmission involved in stress resilience.

Metabolic Fingerprints of Effective Fluoxetine Treatment in the Prefrontal Cortex of Chronically Socially Isolated Rats: Marker Candidates and Predictive Metabolites.

The increasing prevalence of depression requires more effective therapy and the understanding of antidepressants' mode of action. We carried out untargeted metabolomics of the prefrontal cortex of rats exposed to chronic social isolation (CSIS), a rat model of depression, and/or fluoxetine treatment using liquid chromatography-high resolution mass spectrometry. The behavioral phenotype was assessed by the forced swim test. To analyze the metabolomics data, we employed univariate and multivariate analysis and biomarker capacity assessment using the receiver operating characteristic (ROC) curve. We also identified the most predictive biomarkers using a support vector machine with linear kernel (SVM-LK). Upregulated myo-inositol following CSIS may represent a potential marker of depressive phenotype. Effective fluoxetine treatment reversed depressive-like behavior and increased sedoheptulose 7-phosphate, hypotaurine, and acetyl-L-carnitine contents, which were identified as marker candidates for fluoxetine efficacy. ROC analysis revealed 4 significant marker candidates for CSIS group discrimination, and 10 for fluoxetine efficacy. SVM-LK with accuracies of 61.50% or 93.30% identified a panel of 7 or 25 predictive metabolites for depressive-like behavior or fluoxetine effectiveness, respectively. Overall, metabolic fingerprints combined with the ROC curve and SVM-LK may represent a new approach to identifying marker candidates or predictive metabolites for ongoing disease or disease risk and treatment outcome.