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.     

In silico identification of novel lncRNAs with a potential role in diagnosis of gastric cancer

Abstract

Gastric cancer (GC) is the second leading cause of cancer-related deaths in the world. Due to the shortage of adequate symptoms in the early stages, it is diagnosed when the tumor has spread to distant organs. Early recognition of GC enhances the chance of successful treatment. Molecular mechanisms of GC are still poorly understood. LncRNAs are emerging as new players in cancer in both oncogene and tumor suppressor roles. High-throughput technologies such as RNA-Seq, have revealed thousands of lncRNAs which are dysregulated in GC. In this study, we retrieved lncRNAs obtained by High-throughput technologies from OncoLnc database. Consequently, retrieved lncRNAs were compared in literature-based databases including PubMed. As a result, two lists, including experimentally validated lncRNAs and predicted lncRNAs were provided. We found 43 predicted lncRNAs that had not been experimentally validated in GC, so far. Further Bioinformatics analyses were performed to obtain the expression profile of predicted lncRNAs in tumor and normal tissues. Also, the roles and targets of predicted lncRNAs in GC were identified by related databases. Finally, using the GEPIA database was reviewed the significant relationship of predicted lncRNAs with the survival of GC patients. By recognizing the lncRNAs involved in initiation and progression of GC, they may be considered as potential biomarkers in the GC early diagnosis or targeted treatment and lead to novel therapeutic strategies.

Communicated by Ramaswamy H. Sarma     

Inhibition of oxidative stress-induced amyloid β formation in NT2 neurons by culture filtrate of a strain of Streptomyces antibioticus

Actinomycetes isolated from Iran soil habitats were tested for the capacity to produce compounds which can protect neurons from cell death generated by oxidative stress in NT2 neurons. Confirmation of our initial hit was accomplished via the determination of amyloid β level using the enzyme-linked immunosorbent assay test. The most interesting amyloid β formation inhibitor discovered in our study was a secondary metabolite which was produced by strain HM45. This bioactive strain was identified as a strain of Streptomyces antibioticus DSM 40234 using polyphasic approach. The strain HM45 was deposited in Deutsche Sammlung von Mikroorganismen und Zellkulturen as S. antibioticus DSM 41955 and University of Tehran Microorganisms Sollection as S. antibioticus UTMC 00105. This work is the first report on efficiency of an actinomycete metabolite in prohibition of neurons death caused by amyloid β formation.     

Improving purification of recombinant human interferon gamma expressed in Escherichia coli; effect of removal of impurity on the process yield

Process development and optimization studies were performed in order to improve the purification process of (rhIFN-gamma). The objective was to generate material with higher purity and quantity. An in-process control screening was developed to obtain the optimal condition for column chromatographic purification by measuring LPS, nucleic acids, rhIFN- gamma, monomer and its covalent dimers. A new resin screening method was applied to select optimal resin for each of the chromatographic columns. The resulting process used Butyl and Q-Sepharose, refolding and SP-Sepharose for purification of IFN-gamma. Effects of different process conditions such as cell lysis, removal of impurity and oxygen concentration were evaluated. Removal of impurities was evaluated by washing of inclusion bodies with 1% Triton X-100 and 3M urea and different chromatography steps. The results reveal that Triton removed about 43% of the LPS but urea had no effect on removal of nucleic acids and LPS. Further analysis show that removal of impurities by column chromatography decreases aggregation and increases the process yield. Oxygen concentration was identified as parameter that could have a significant impact on covalent dimers formation, as an unacceptable pharmaceutical form of rhIFN-gamma. On the basis of small-scale studies, optimum operating conditions were chosen and the purification process was successfully scaled-up to a pilot scale process with step yield and product quality that were better than previous reports.     

Homology modeling, docking, molecular dynamics simulation, and structural analyses of coxsakievirus B3 2A protease: an enzyme involved in the pathogenesis of inflammatory myocarditis

2A protease of the pathogenic coxsackievirus B3 is key to the pathogenesis of inflammatory myocarditis and, therefore, an attractive drug target. However lack of a crystal structure impedes design of inhibitors. Here we predict 3D structure of CVB3 2A^pro based on sequence comparison and homology modeling with human rhinovirus 2A^pro. The two enzymes are remarkably similar in their core regions. However they have different conformations at the N-terminal. A large number of N-terminal hydrophobic residues reduce the thermal stability of CVB3 2A^pro, as we confirmed by fluorescence, western blot and turbidity measurement. Molecular dynamic simulation revealed that elevated temperature induces protein motion that results in frequent movement of the N-terminal coil. This may therefore induce successive active site changes and thus play an important role in destabilization of CVB3 2A^pro structure.     

Microarray blob-defect removal improves array analysis

MOTIVATION: New generation Affymetrix oligonucleotide microarrays often have blob-like image defects that will require investigators to either repeat their hybridization assays or analyze their data with the defects left in place. We investigated the effect of analyzing a spike-in experiment on Affymetrix ENCODE tiling arrays in the presence of simulated blobs covering between 1 and 9% of the array area. Using two different ChIP-chip tiling array analysis programs (Affymetrix tiling array software, TAS, and model-based analysis of tiling arrays, MAT), we found that even the smallest blob defects significantly decreased the sensitivity and increased the false discovery rate (FDR) of the spike-in target prediction. RESULTS: We introduced a new software tool, the microarray blob remover (MBR), which allows rapid visualization, detection and removal of various blob defects from the .CEL files of different types of Affymetrix microarrays. It is shown that using MBR significantly improves the sensitivity and FDR of a tiling array analysis compared to leaving the affected probes in the analysis. AVAILABILITY: The MBR software and the sample array .CEL files used in this article are available at: http://liulab.dfci.harvard.edu/Software/MBR/MBR.htm     

A novel amino acid supplementation strategy based on a stoichiometric model to enhance human IL-2 (interleukin-2) expression in high-cell-density Escherichia coli cultures

A novel amino acid supplementation strategy was developed for enhancing the production of IL-2 (interleukin-2; as a model protein) by recombinant Escherichia coli BL21 (pET21a-hil2) in fed-batch high-cell-density cultures. The amino acids most needed and their amounts were determined using a stoichiometric model, and full factorial design experiments were conducted to determine the effects of single amino acids and amino acid mixtures on production. One of the most effective amino acid mixtures was found to be leucine, aspartic acid and glycine. This amino acid mixture was utilized for the production of IL-2 in batch and fed-batch fermentations. The amount of IL-2 produced increased from 403 to 722 mg/l and from 5.15 × 103 to 8.08 × 103 mg/l in batch and fed-batch cultures respectively. The results also revealed that the above amino acid mixture specifically increases IL-2 concentration in the cells.