Construction of an exposure-pathway-phenotype in children with depression due to transfusion-dependent thalassemia: Results of (un)supervised machine learning

Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis

Thalassemia represents one of the most common genetic disorders worldwide, characterized by defects in hemoglobin synthesis. The affected individuals suffer from malfunctioning of one or more of the four globin genes, leading to chronic hemolytic anemia, an imbalance in the hemoglobin chain ratio, iron overload, and ineffective erythropoiesis. Despite the challenges posed by this condition, recent years have witnessed significant advancements in diagnosis, therapy, and transfusion support, significantly improving the prognosis for thalassemia patients. This research empirically evaluates the efficacy of models constructed using classification methods and explores the effectiveness of relevant features that are derived using various machine-learning techniques. Five feature selection approaches, namely Chi-Square (χ2), Exploratory Factor Score (EFS), tree-based Recursive Feature Elimination (RFE), gradient-based RFE, and Linear Regression Coefficient, were employed to determine the optimal feature set. Nine classifiers, namely K-Nearest Neighbors (KNN), Decision Trees (DT), Gradient Boosting Classifier (GBC), Linear Regression (LR), AdaBoost, Extreme Gradient Boosting (XGB), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Support Vector Machine (SVM), were utilized to evaluate the performance. The χ2 method achieved accuracy, registering 91.56% precision, 91.04% recall, and 92.65% f-score when aligned with the LR classifier. Moreover, the results underscore that amalgamating over-sampling with Synthetic Minority Over-sampling Technique (SMOTE), RFE, and 10-fold cross-validation markedly elevates the detection accuracy for αT patients. Notably, the Gradient Boosting Classifier (GBC) achieves 93.46% accuracy, 93.89% recall, and 92.72% F1 score.

Brain Iron Homeostasis and Mental Disorders

Iron plays an essential role in various physiological processes. A disruption in iron homeostasis can lead to severe consequences, including impaired neurodevelopment, neurodegenerative disorders, stroke, and cancer. Interestingly, the link between mental health disorders and iron homeostasis has not received significant attention. Therefore, our understanding of iron metabolism in the context of psychological diseases is incomplete. In this review, we aim to discuss the pathologies and potential mechanisms that relate to iron homeostasis in associated mental disorders. We propose the hypothesis that maintaining brain iron homeostasis can support neuronal physiological functions by impacting key enzymatic activities during neurotransmission, redox balance, and myelination. In conclusion, our review highlights the importance of investigating the relationship between trace element nutrition and the pathological process of mental disorders, focusing on iron. This nutritional perspective can offer valuable insights for the clinical treatment of mental disorders.

Uncovering PFAS and Other Xenobiotics in the Dark Metabolome Using Ion Mobility Spectrometry, Mass Defect Analysis, and Machine Learning

The identification of xenobiotics in nontargeted metabolomic analyses is a vital step in understanding human exposure. Xenobiotic metabolism, transformation, excretion, and coexistence with other endogenous molecules, however, greatly complicate the interpretation of features detected in nontargeted studies. While mass spectrometry (MS)-based platforms are commonly used in metabolomic measurements, deconvoluting endogenous metabolites from xenobiotics is also often challenged by the lack of xenobiotic parent and metabolite standards as well as the numerous isomers possible for each small molecule m/z feature. Here, we evaluate a xenobiotic structural annotation workflow using ion mobility spectrometry coupled with MS (IMS-MS), mass defect filtering, and machine learning to uncover potential xenobiotic classes and species in large metabolomic feature lists. Xenobiotic classes examined included those of known high toxicities, including per- and polyfluoroalkyl substances (PFAS), polycyclic aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), polybrominated diphenyl ethers (PBDEs), and pesticides. Specifically, when the workflow was applied to identify PFAS in the NIST SRM 1957 and 909c human serum samples, it greatly reduced the hundreds of detected liquid chromatography (LC)-IMS-MS features by utilizing both mass defect filtering and m/z versus IMS collision cross sections relationships. These potential PFAS features were then compared to the EPA CompTox entries, and while some matched within specific m/z tolerances, there were still many unknowns illustrating the importance of nontargeted studies for detecting new molecules with known chemical characteristics. Additionally, this workflow can also be utilized to evaluate other xenobiotics and enable more confident annotations from nontargeted studies.

False dogmas in mood disorders research: Towards a nomothetic network approach

The current understanding of major depressive disorder (MDD) and bipolar disorder (BD) is plagued by a cacophony of controversies as evidenced by competing schools to understand MDD/BD. The DSM/ICD taxonomies have cemented their status as the gold standard for diagnosing MDD/BD. The aim of this review is to discuss the false dogmas that reign in current MDD/BD research with respect to the new, data-driven, machine learning method to model psychiatric illness, namely nomothetic network psychiatry (NNP). This review discusses many false dogmas including: MDD/BD are mind-brain disorders that are best conceptualized using a bio-psycho-social model or mind-brain interactions; mood disorders due to medical disease are attributable to psychosocial stress or chemical imbalances; DSM/ICD are the gold standards to make the MDD/BD diagnosis; severity of illness should be measured using rating scales; clinical remission should be defined using threshold values on rating scale scores; existing diagnostic BD boundaries are too restrictive; and mood disorder spectra are the rule. In contrast, our NNP models show that MDD/BD are not mind-brain or psycho-social but systemic medical disorders; the DSM/ICD taxonomies are counterproductive; a shared core, namely the reoccurrence of illness (ROI), underpins the intertwined recurrence of depressive and manic episodes and suicidal behaviors; mood disorders should be ROI-defined; ROI mediates the effects of nitro-oxidative stress pathways and early lifetime trauma on the phenome of mood disorders; severity of illness and treatment response should be delineated using the NNP-derived causome, pathway, ROI and integrated phenome scores; and MDD and BD are the same illness.