Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach

Deep learning techniques have recently made considerable advances in the field of artificial intelligence. These methodologies can assist psychologists in early diagnosis of mental disorders and preventing severe trauma. Major Depression Disorder (MDD) is a common and serious medical condition whose exact manifestations are not fully understood. So, early discovery of MDD patients helps to cure or limit the adverse effects. Electroencephalogram (EEG) is prominently used to study brain diseases such as MDD due to having high temporal resolution information, and being a noninvasive, inexpensive and portable method. This paper has proposed an EEG-based deep learning framework that automatically discriminates MDD patients from healthy controls. First, the relationships among EEG channels in the form of effective brain connectivity analysis are extracted by Generalized Partial Directed Coherence (GPDC) and Direct directed transfer function (dDTF) methods. A novel combination of sixteen connectivity methods (GPDC and dDTF in eight frequency bands) was used to construct an image for each individual. Finally, the constructed images of EEG signals are applied to the five different deep learning architectures. The first and second algorithms were based on one and two-dimensional convolutional neural network (1DCNN–2DCNN). The third method is based on long short-term memory (LSTM) model, while the fourth and fifth algorithms utilized a combination of CNN with LSTM model namely, 1DCNN-LSTM and 2DCNN-LSTM. The proposed deep learning architectures automatically learn patterns in the constructed image of the EEG signals. The efficiency of the proposed algorithms is evaluated on resting state EEG data obtained from 30 healthy subjects and 34 MDD patients. The experiments show that the 1DCNN-LSTM applied on constructed image of effective connectivity achieves best results with accuracy of 99.24% due to specific architecture which captures the presence of spatial and temporal relations in the brain connectivity. The proposed method as a diagnostic tool is able to help clinicians for diagnosing the MDD patients for early diagnosis and treatment.     

Relationship between the Structure and Chaperone Activity of Human αA-Crystallin after Its Modification with Diabetes-Associated Oxidative Agents and Protective Role of Antioxidant Compounds

Biochemistry (Moscow) - The study was aimed to evaluate the impact of peroxynitrite (PON, oxidative stress agent in diabetes), methylglyoxal (MGO, diabetes-associated reactive carbonyl compound),...     

Evaluation of the binding effect and cytotoxicity assay of 2-Ethyl-5-(4-methylphenyl) pyramido pyrazole ophthalazine trione on calf thymus DNA: spectroscopic,calorimetric, and molecular dynamics approaches

With advances in new drug therapies, it is essential to understand the interactions between drugs and target molecules. In this study, we applied multiple spectroscopic techniques including absorbance, fluorescence, circular dichroism spectroscopy, viscosity, thermal melting, calorimetric, and molecular dynamics (MD) simulation to study the interaction between 2-Ethyl-5-(4-methylphenyl) pyramido pyrazole ophthalazine trione (PPF) and calf thymus DNA (ct DNA) in the absence or presence of histone H1. PPF exhibits a high binding affinity towards ct DNA in binary and ternary systems. In addition, the result for the binding constant was observed within the range 10⁴ M⁻¹ achieved through fluorescence quenching data, while the values for enthalpy and entropy changes for ct DNA–PPF and (ct DNA–H1) PPF complexes were measured to be −72.54 kJ.mol⁻¹, −161.14 J.mol⁻¹ K⁻¹, −85.34 kJ.mol⁻¹, and −19.023 J.mol⁻¹ K⁻¹, respectively. Furthermore, in accordance with circular dichroism spectra, the inducement of ct DNA structural changes was observed during binding of PPF and H1 in binary and ternary system forms. The essential roles of hydrogen bonding and van der Waals forces throughout the interaction were suggested using thermodynamic parameters. According to the obtained data, the interaction mode of ct DNA–PPF and (ct DNA–H1) PPF complexes was intercalation binding. Suggested by the MD simulation study, the ct DNA–H1 complex caused a reduction in the stability of the DNA structure in the presence or absence of ligand, which demonstrated that PPF as an intercalating agent can further distort the structure. The information achieved from this study will be very helpful in understanding the effects of PPF on the conformational state of ct DNA in the absence or presence of the H1 molecule, which seems to be quite significant for clarifying the mechanisms of action and its pharmacokinetics.     

Competition and overlap of Oryzaephilus surinamensis and Plodia interpunctella populations under condition of stored date fruits

Plodia interpunctella and Oryzaephilus surinamensis are found in food storehouses including dates and palm storages. The current study aimed to determine competition and overlap potentials of the two pests of date fruits. Time series models were used to study two species populations and logistic growth model to estimate the effect of density of the species. The results revealed the environmental capacities of O. surinamensis and P. interpunctella were 433 and 1610 (maximum number per 20 g), respectively, and the population growth rates (r) were 1.2 and 1.3, respectively. Ecological balances of the two species were close to each other from the first to the third week. The population of O. surinamensis decreased in the fourth week of the competition. The highest population balance of the two species was in the 14th week. The potential of exploitable ecological niches (e_ij) and the amount of non-exploited ecological niches by any species (z_ij) for O. surinamensis was higher than for P. interpunctella from the 8th week untill the end of sampling period. The overlap of ecological niches in the two species (D) ranged from 0.94 to 1, indicating a complete overlap of temporal activity in the two populations on date palm. The current results of this study can be used by integrated pest management specialists. Information over the effects of species competition on population dynamics and their coexistence can be used to predict population status and to adopt simple pest control methods.     

ERRγ Preserves Brown Fat Innate Thermogenic Activity

1. Download high-res image (147KB)
2. Download full-size image

     

<Emphasis Type="Italic">Lactobacillus plantarum</Emphasis> as a Probiotic Potential from Kouzeh Cheese (Traditional Iranian Cheese) and Its Antimicrobial Activity

The aim of this study is to isolate and identify Lactobacillus plantarum isolates from traditional cheese, Kouzeh, and evaluate their antimicrobial activity against some food pathogens. In total, 56 lactic acid bacteria were isolated by morphological and biochemical methods, 12 of which were identified as Lactobacillus plantarum by biochemical method and 11 were confirmed by molecular method. For analyzing the antimicrobial activity of these isolates properly, diffusion method was performed. The isolates were identified by 318 bp band dedicated for L. plantarum. The isolated L. plantarum represented an inhibitory activity against four of the pathogenic bacteria and showed different inhibition halos against each other. The larger halos were observed against Staphylococcus aureus and Staphylococcus epidermidis (15 ± 0.3 and 14.8 ± 0.7 mm, respectively). The inhibition halo of Escherichia coli was smaller than that of other pathogen and some L. plantarum did not show any inhibitory activity against E. coli, which were resistant to antimicrobial compounds produced by L. plantarum. The isolated L. plantarum isolates with the antimicrobial activity in this study had strong probiotic properties. These results indicated the nutritional value of Kouzeh cheese and usage of the isolated isolates as probiotic strains.     

Transdifferentiation: a cell and molecular reprogramming process

Evidence has emerged recently indicating that differentiation is not entirely a one-way process, and that it is possible to convert one cell type to another, both in vitro and in vivo. This phenomenon is called transdifferentiation, and is generally defined as the stable switch of one cell type to another. Transdifferentiation plays critical roles during development and in regeneration pathways in nature. Although this phenomenon occurs rarely in nature, recent studies have been focused on transdifferentiation and the reprogramming ability of cells to produce specific cells with new phenotypes for use in cell therapy and regenerative medicine. Thus, understanding the principles and the mechanism of this process is important for producing desired cell types. Here some well-documented examples of transdifferentiation, and their significance in development and regeneration are reviewed. In addition, transdifferentiation pathways are considered and their potential molecular mechanisms, especially the role of master switch genes, are considered. Finally, the significance of transdifferentiation in regenerative medicine is discussed.     

Aminoguanidine Changes Hippocampal Expression of Apoptosis-Related Genes,Improves Passive Avoidance Learning and Memory in Streptozotocin-Induced Diabetic Rats

Cognitive dysfunction occurs in patients with diabetes mellitus. The objective of this study was to examine whether bilateral intrahippocampal CA1 (intra-CA1) injection of aminoguanidine (AG) can either affect the Bcl-2 family gene expression or reduce the diabetic imposing abnormalities of passive avoidance learning (PAL) and memory. Rats were divided into five groups: control (C), control treated with normal saline (CS), control treated with AG (S-AG), diabetics (D), and diabetics treated with AG (D-AG). Diabetes mellitus was induced by a single intraperitoneal injection of streptozotocin (STZ) (50 mg/kg). AG (30 μg/rat) or vehicle was administered intra-CA1 bilaterally at the onset of hyperglycemia. PAL was assessed 7 weeks later. Animals were killed, and hippocampus was dissected following the behavioral test. The expressions of Bax, Bcl-2, and Bcl-xl mRNAs were measured using semiquantitative RT-PCR technique. The result of passive avoidance task showed that AG significantly improved the cognitive performance in diabetic rats. Moreover, AG treatment decreased the levels of Bcl-2 and Bcl-x_L expressions in diabetic group. The ratio of Bax/Bcl-2 and Bax/Bcl-x_L decreased significantly in AG-treated diabetic animals. In conclusion, initial treatment with AG by intra-CA1 micro-injection improves the impaired passive avoidance task in STZ-induced diabetic rats which may be related to the decreased Bax/Bcl-2 and Bax/Bcl-x_L ratios.