Functional near-infrared spectroscopy-based neurofeedback training regulates time-on-task effects and enhances sustained cognitive performance.

Time-on-task effect is a common consequence of long-term cognitive demand work, which reflects reduced behavioral performance and increases the risk of accidents. Neurofeedback is a neuromodulation method that can guide individuals to regulate their brain activity and manifest as changes in related symptoms and cognitive behaviors. This study aimed to examine the effects of functional near-infrared spectroscopy-based neurofeedback training on time-on-task effects and sustained cognitive performance. A randomized, single-blind, sham-controlled study was performed: 17 participants received feedback signals of their own dorsolateral prefrontal cortex activity (neurofeedback group), and 16 participants received feedback signals of dorsolateral prefrontal cortex activity from the neurofeedback group (sham-neurofeedback group). All participants received 5 neurofeedback training sessions and completed 2 sustained cognitive tasks, including a 2-back task and a psychomotor vigilance task, to evaluate behavioral performance changes following neurofeedback training. Results showed that neurofeedback relative to the sham-neurofeedback group exhibited increased dorsolateral prefrontal cortex activation, increased accuracy in the 2-back task, and decreased mean response time in the psychomotor vigilance task after neurofeedback training. In addition, the neurofeedback group showed slower decline performance during the sustained 2-back task after neurofeedback training compared with sham-neurofeedback group. These findings demonstrate that neurofeedback training could regulate time-on-task effects on difficult task and enhance performance on sustained cognitive tasks by increasing dorsolateral prefrontal cortex activity.

Essential genes identification model based on sequence feature map and graph convolutional neural network.

BACKGROUND: Essential genes encode functions that play a vital role in the life activities of organisms, encompassing growth, development, immune system functioning, and cell structure maintenance. Conventional experimental techniques for identifying essential genes are resource-intensive and time-consuming, and the accuracy of current machine learning models needs further enhancement. Therefore, it is crucial to develop a robust computational model to accurately predict essential genes. RESULTS: In this study, we introduce GCNN-SFM, a computational model for identifying essential genes in organisms, based on graph convolutional neural networks (GCNN). GCNN-SFM integrates a graph convolutional layer, a convolutional layer, and a fully connected layer to model and extract features from gene sequences of essential genes. Initially, the gene sequence is transformed into a feature map using coding techniques. Subsequently, a multi-layer GCN is employed to perform graph convolution operations, effectively capturing both local and global features of the gene sequence. Further feature extraction is performed, followed by integrating convolution and fully-connected layers to generate prediction results for essential genes. The gradient descent algorithm is utilized to iteratively update the cross-entropy loss function, thereby enhancing the accuracy of the prediction results. Meanwhile, model parameters are tuned to determine the optimal parameter combination that yields the best prediction performance during training. CONCLUSIONS: Experimental evaluation demonstrates that GCNN-SFM surpasses various advanced essential gene prediction models and achieves an average accuracy of 94.53%. This study presents a novel and effective approach for identifying essential genes, which has significant implications for biology and genomics research.

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network.

DNA methylation takes on critical significance to the regulation of gene expression by affecting the stability of DNA and changing the structure of chromosomes. DNA methylation modification sites should be identified, which lays a solid basis for gaining more insights into their biological functions. Existing machine learning-based methods of predicting DNA methylation have not fully exploited the hidden multidimensional information in DNA gene sequences, such that the prediction accuracy of models is significantly limited. Besides, most models have been built in terms of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model is capable of extracting feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). Moreover, the proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm using the cross-entropy loss function to increase the prediction accuracy of the model. Besides, the MEDCNN model can predict different types of DNA methylation sites. As indicated by the experimental results,the deep learning method based on coding from multiple dimensions outperformed single coding methods, and the MEDCNN model was highly applicable and outperformed existing models in predicting DNA methylation between different species. As revealed by the above-described findings, the MEDCNN model can be effective in predicting DNA methylation sites.

A facile covalent strategy for ultrafast negative photoconductance hybrid graphene/porphyrin-based photodetector.

As a powerful complement to positive photoconductance (PPC), negative photoconductance (NPC) holds great potential for photodetector. However, the slow response of NPC relative to PPC devices limits their integration. Here, we propose a facile covalent strategy for an ultrafast NPC hybrid 2D photodetector. Our transistor-based graphene/porphyrin model device with a rise time of 0.2 ms and decay time of 0.3 ms has the fastest response time in the so far reported NPC hybrid photodetectors, which is attributed to efficient photogenerated charge transport and transfer. Both the photosensitive porphyrin with an electron-rich and large rigid structure and the built-in graphene frame with high carrier mobility are prone to the photogenerated charge transport. Especially, the intramolecular donor-acceptor system formed by graphene and porphyrin through covalent bonding promotes photoinduced charge transfer. This covalent strategy can be applied to other nanosystems for high-performance NPC hybrid photodetector.

Modification of interface and electronic transport in van der Waals heterojunctions by UV/O3.

Two-dimensional (2D) van der Waals heterojunctions have many unique properties, and energy band modulation is central to applying these properties to electronic devices. Taking the 2D graphene/MoS2heterojunction as a model system, we demonstrate that the band structure can be finely tuned by changing the graphene structure of the 2D heterojunction via ultraviolet/ozone (UV/O3). With increasing UV/O3exposure time, graphene in the heterojunction has more defect structures. The varied defect levels in graphene modulate the interfacial charge transfer, accordingly the band structure of the heterojunction. And the corresponding performance change of the graphene/MoS2field effect transistor indicates the shift of the Schottky barrier height after UV/O3treatment. The result further proves the effective band structure modulation of the graphene/MoS2heterojunction by UV/O3. This work will be beneficial to both fundamental research and practical applications of 2D van der Waals heterojunction in electronic devices.

A deep learning model for DNA enhancer prediction based on nucleotide position aware feature encoding.

Enhancers, genomic DNA elements, regulate neighboring gene expression crucial for biological processes like cell differentiation and stress response. However, current machine learning methods for predicting DNA enhancers often underutilize hidden features in gene sequences, limiting model accuracy. Hence, this article proposes the PDCNN model, a deep learning-based enhancer prediction method. PDCNN extracts statistical nucleotide representations from gene sequences, discerning positional distribution information of nucleotides in modifier-like DNA sequences. With a convolutional neural network structure, PDCNN employs dual convolutional and fully connected layers. The cross-entropy loss function iteratively updates using a gradient descent algorithm, enhancing prediction accuracy. Model parameters are fine-tuned to select optimal combinations for training, achieving over 95% accuracy. Comparative analysis with traditional methods and existing models demonstrates PDCNN's robust feature extraction capability. It outperforms advanced machine learning methods in identifying DNA enhancers, presenting an effective method with broad implications for genomics, biology, and medical research.

Detection of Chylous Plasma Based on Machine Learning and Hyperspectral Techniques.

Chylous blood is the main cause of unqualified and scrapped blood among volunteer blood donors. Therefore, a diagnostic method that can quickly and accurately identify chylous blood before donation is needed. In this study, the GaiaSorter "Gaia" hyperspectral sorter was used to extract 254 bands of plasma images, ranging from 900 nm to 1700 nm. Four different machine learning algorithms were used, including decision tree, Gaussian Naive Bayes (GaussianNB), perceptron, and stochastic gradient descent models. First, the preliminary classification accuracies were compared with the original data, which showed that the effects of the decision tree and GaussianNB models were better; their average accuracies could reach over 90%. Then, the feature dimension reduction was performed on the original data. The results showed that the effects of the decision tree were better with a classification accuracy of 93.33%. the classification of chylous plasma using different chylous indices suggested that the accuracies of the decision trees model both before and after the feature dimension reductions were the best with over 80% accuracy. The results of feature dimension reduction showed that the characteristic bands corresponded to all kinds of plasma, thereby showing their classification and identification potential. By applying the spectral characteristics of plasma to medical technology, this study suggested a rapid and effective method for the identification of chylous plasma and provided a reference for the blood detection technology to achieve the goal of reducing wasting blood resources and improving the work efficiency of the medical staff.

Biological Activity Predictions of Ligands Based on Hybrid Molecular Fingerprinting and Ensemble Learning.

The biological activity predictions of ligands are an important research direction, which can improve the efficiency and success probability of drug screening. However, the traditional prediction method has the disadvantages of complex modeling and low screening efficiency. Machine learning is considered an important research direction to solve these traditional method problems in the near future. This paper proposes a machine learning model with high predictive accuracy and stable prediction ability, namely, the back propagation neural network cross-support vector regression model (BPCSVR). By comparing multiple molecular descriptors, MACCS fingerprint and ECFP6 fingerprint were selected as inputs, and the stable prediction ability of the model was improved by integrating multiple models and correcting similar samples. We used leave-one-out cross-validation on 3038 samples from six data sets. The coefficient of determination, root mean square error, and absolute error were used as the evaluation parameters. After comparing the multiclass models, the results show that the BPCSVR model has stable prediction ability in different data sets, and the prediction accuracy is higher than other comparison models.

Tuberculosis-associated hemophagocytic lymphohistiocytosis misdiagnosed as systemic lupus erythematosus: A case report.

BACKGROUND: Hemophagocytic lymphohistiocytosis (HLH) is a rare disorder with rapid progression and high mortality. HLH occurs mostly due to infection, malignant tumors, and immune disorders. Among infections that cause HLH, viral infections, especially Epstein-Barr virus infections, are common, whereas tuberculosis is rare. Tuberculosis-associated HLH has a wide range of serological and clinical manifestations that are similar to those of systemic lupus erythematosus (SLE). CASE SUMMARY: This study describes a case of tuberculosis-associated HLH misdiagnosed as SLE because of antinuclear antibody (ANA), Smith (Sm) antibody and lupus anticoagulant positivity; leukopenia; thrombocytopenia; pleural effusion; decreased C3, quantitatively increased 24 h urinary protein and fever. The patient was initially treated with glucocorticoids, which resulted in peripheral blood cytopenia and symptom recurrence. Then, caseating granulomas and hemophagocytosis were observed in her bone marrow. She was successfully treated with conventional category 1 antituberculous drugs. In addition, we reviewed the literature on tuberculosis-associated HLH documented in PubMed, including all full-text articles published in English from December 2009 to December 2019, and summarized the key points, including the epidemiology, clinical manifestations, diagnosis, and treatment of tuberculosis-associated HLH and the differences of the present case from previous reports. CONCLUSION: Tuberculosis should be considered in patients with fever or respiratory symptoms. Antituberculous drugs are important for treating tuberculosis-associated HLH.

Prediction of the Aqueous Solubility of Compounds Based on Light Gradient Boosting Machines with Molecular Fingerprints and the Cuckoo Search Algorithm.

Aqueous solubility is one of the most important physicochemical properties in drug discovery. At present, the prediction of aqueous solubility of compounds is still a challenging problem. Machine learning has shown great potential in solubility prediction. Most machine learning models largely rely on the setting of hyperparameters, and their performance can be improved by setting the hyperparameters in a better way. In this paper, we used MACCS fingerprints to represent the structural features and optimized the hyperparameters of the light gradient boosting machine (LightGBM) with the cuckoo search algorithm (CS). Based on the above representation and optimization, the CS-LightGBM model was established to predict the aqueous solubility of 2446 organic compounds and the obtained prediction results were compared with those obtained with the other six different machine learning models (RF, GBDT, XGBoost, LightGBM, SVR, and BO-LightGBM). The comparison results showed that the CS-LightGBM model had a better prediction performance than the other six different models. RMSE, MAE, and R 2 of the CS-LightGBM model were, respectively, 0.7785, 0.5117, and 0.8575. In addition, this model has good scalability and can be used to solve solubility prediction problems in other fields such as solvent selection and drug screening.

A double-population chaotic self-adaptive evolutionary dynamics model for the prediction of supercritical carbon dioxide solubility in polymers.

Solubility of gas in polymers is an important physico-chemical property of foam materials and widely used in the preparation and modification of new materials. Under the conditions of high temperature and high pressure, the dissolution process is a nonlinear, non-equilibrium and dynamic process, so it is difficult to establish an accurate solubility calculation model. Inspired by particle dynamics and evolutionary algorithm, this paper proposes a hybrid model based on chaotic self-adaptive particle dynamics evolutionary algorithm (CSA-PD-EA), which can use the iterative process of particles in evolutionary algorithms at the dynamic level to simulate the mutual diffusion process of molecules during dissolution. The predicted solubility of supercritical CO2 in poly(d,l-lactide-co-glycolide), poly(l-lactide) and poly(vinyl acetate) indicated that the comprehensive prediction performance of the CSA-PD-EA model was high. The calculation error and correlation coefficient were, respectively, 0.3842 and 0.9187. The CSA-PD-EA model showed prominent advantages in accuracy, efficiency and correlation over other computational models, and its calculation time was 4.144-15.012% of that of other dynamic models. The CSA-PD-EA model has wide application prospects in the computation of physical and chemical properties and can provide the basis for the theoretical calculation of multi-scale complex systems in chemistry, materials, biology and physics.

Response to belimumab in thrombotic thrombocytopenic purpura associated with systemic lupus erythematosus: a case-based review.

Thrombotic thrombocytopenic purpura (TTP), a life-threatening syndrome characterized by acute microangiopathic hemolytic anemia, thrombocytopenia, and visceral ischemia, can be classified as congenital TTP (inherited due to a mutation in ADAMTS13) and acquired TTP. The acquired TTP is further classified as idiopathic and secondary TTP. Systemic lupus erythematosus (SLE) is regarded as one of the most common causes of secondary TTP (SLE-TTP). In contrast to patients with idiopathic TTP, some patients with SLE-TTP, especially those diagnosed with refractory TTP, are resistant to plasma exchange and high-dose corticosteroids and usually require second-line drugs, including newly developed biologicals. Belimumab, a B-lymphocyte stimulator-specific inhibitor, was the first approved new therapy for SLE in the past 50 years. Only two cases of SLE-TTP using belimumab have been reported; however, detailed information has not been made available. Herein, we describe a 28-year-old female patient who presented with palm petechiae, strong tawny urine, and yellow stained skin and sclera, and was diagnosed with SLE-TTP supported by high anti-ANA titers; positive anti-SSA/SM; pleural effusion; decreased platelet count, hemoglobin, and complement C3/C4 counts; increased lactate dehydrogenase level, along with increased schistocytes; and a significant deficiency of ADAMTS13 activity. Belimumab (10 mg/kg) was administered after six plasma exchanges. Good efficiency and outcomes without any adverse events, SLE, or TTP relapse were observed during 12 months of follow-up. Therefore, belimumab is a promising choice for SLE-TTP management. In addition, we provide a focused review of the existing literature on the pathogenesis, diagnosis, and therapeutic strategies for SLE-TTP.

Increasing the cytotoxicity of Ru(II) polypyridyl complexes by tuning the electron-donating ability of 1,10-phenanthroline ligands.

Ruthenium (Ru)-based chemotherapeutic agents are a choice to replace traditional platinum-containing metallodrugs due to fewer side effects. It has been proved that the mechanism of Ru complex drugs is to highly likely bind with DNA and certain proteins, which also highly depends on the electronic structures of Ru complexes. However, the relationship between electronic properties and chemotherapeutic activities has not yet been completely systemically investigated, which limits the effective drug design strategies. Herein, we propose that increasing the electron densities of Ru would enhance the nucleophilic substitution rate of chlorine atoms (Cl) on Ru, providing better bioactivity against both amino acids and nucleic acids. A series of complexes with various optimized electron-donating groups (EDGs) were synthesized according to DFT calculations. In addition, kinetics substitution with L-histidine, DNA binding experiments, and cell cytotoxicity studies verified our assumptions. Surprisingly, these complexes could also be potential cellular imaging probes via an unprecedented "off-on" light-switching mechanism of living cells, which was caused by the "HOMO-LUMO" distribution changes of Ru complexes after interaction with DNA. Accordingly, the reactivity and selectivity demonstrated by these compounds support the further development of these Ru complexes in cancer treatments and afford strategic perspectives on the development of metal complexes as chemotherapeutic agents and bioimaging probes.

Prediction Model of Organic Molecular Absorption Energies based on Deep Learning trained by Chaos-enhanced Accelerated Evolutionary algorithm.

As an important physical property of molecules, absorption energy can characterize the electronic property and structural information of molecules. Moreover, the accurate calculation of molecular absorption energies is highly valuable. Present linear and nonlinear methods hold low calculation accuracies due to great errors, especially irregular complicated molecular systems for structures. Thus, developing a prediction model for molecular absorption energies with enhanced accuracy, efficiency, and stability is highly beneficial. By combining deep learning and intelligence algorithms, we propose a prediction model based on the chaos-enhanced accelerated particle swarm optimization algorithm and deep artificial neural network (CAPSO BP DNN) that possesses a seven-layer 8-4-4-4-4-4-1 structure. Eight parameters related to molecular absorption energies are selected as inputs, such as a theoretical calculating value Ec of absorption energy (B3LYP/STO-3G), molecular electron number Ne, oscillator strength Os, number of double bonds Ndb, total number of atoms Na, number of hydrogen atoms Nh, number of carbon atoms Nc, and number of nitrogen atoms NN; and one parameter representing the molecular absorption energy is regarded as the output. A prediction experiment on organic molecular absorption energies indicates that CAPSO BP DNN exhibits a favourable predictive effect, accuracy, and correlation. The tested absolute average relative error, predicted root-mean-square error, and square correlation coefficient are 0.033, 0.0153, and 0.9957, respectively. Relative to other prediction models, the CAPSO BP DNN model exhibits a good comprehensive prediction performance and can provide references for other materials, chemistry and physics fields, such as nonlinear prediction of chemical and physical properties, QSAR/QAPR and chemical information modelling, etc.

Association between ABCB1 C3435T polymorphism and methotrexate treatment outcomes in rheumatoid arthritis patients: a meta-analysis.

Aim: This study was conducted to investigate the relationship between ABCB1 gene C3435T polymorphism and methotrexate treatment outcomes in rheumatoid arthritis patients. Methods: Seven electronic databases (PubMed, EMBASE, Web of Science, Cochrane, OVID, Chinese biomedical literature [CBM], China National Knowledge Infrastructure [CNKI] and Wanfang databases) were searched to select eligible publications until 18 July 2018. The references of relevant articles were also manually searched. The quality evaluation of the included studies was carried out according to the guidelines of the Newcastle-Ottawa Scale. Data were analyzed with Review Manager 5.3 and Stata 13.0 software. In total, 12 articles involving 2014 patients were included. Conclusion: Our results demonstrated that the ABCB1 gene C3435T polymorphism might be a reliable predictor of response to methotrexate in rheumatoid arthritis patients. However, well-designed, multicenter and large-scale prospective studies are required to further confirm the validity of our results.

Experimental and Simulation Study on the Dissolved Amount and Dissolution Rate of Supercritical CO2 in Polystyrene Melt.

The amount of supercritical CO2 dissolved in polystyrene (PS), dissolution rate, and solubility under static conditions at 170-190 °C and 7.5-9.5 MPa were calculated by utilizing volume-changing-method experiments and numerical simulations. By comparison, the instantaneous error can be guaranteed to be less than 15%. The two results are in good agreement, and the reliability of the simulation method is verified. Based on the obtained results, another parameter was added to the tested model, and the dissolution rate of supercritical CO2 in PS under different shear conditions was numerically simulated. The effects of temperature, pressure, and shear rate on dissolution were analyzed. The results show that when the temperature and pressure are constant, the dissolution rate of supercritical CO2 in PS with shear increases significantly compared with that without shear. The conditions that enable the maximum dissolution rate are 190 °C, 9.5 MPa, and a shear rate of 240/π. With the abovementioned pressure and shear rate conditions, the maximum solubility can be obtained under the temperature of 170 °C.

Prediction of pKa Values for Neutral and Basic Drugs based on Hybrid Artificial Intelligence Methods.

The pKa value of drugs is an important parameter in drug design and pharmacology. In this paper, an improved particle swarm optimization (PSO) algorithm was proposed based on the population entropy diversity. In the improved algorithm, when the population entropy was higher than the set maximum threshold, the convergence strategy was adopted; when the population entropy was lower than the set minimum threshold the divergence strategy was adopted; when the population entropy was between the maximum and minimum threshold, the self-adaptive adjustment strategy was maintained. The improved PSO algorithm was applied in the training of radial basis function artificial neural network (RBF ANN) model and the selection of molecular descriptors. A quantitative structure-activity relationship model based on RBF ANN trained by the improved PSO algorithm was proposed to predict the pKa values of 74 kinds of neutral and basic drugs and then validated by another database containing 20 molecules. The validation results showed that the model had a good prediction performance. The absolute average relative error, root mean square error, and squared correlation coefficient were 0.3105, 0.0411, and 0.9685, respectively. The model can be used as a reference for exploring other quantitative structure-activity relationships.

Intervention for diagnosis of deep vein thrombosis in acute stroke patients: a hospital-based study.

BACKGROUND: Immobile stroke patients are at high risk of deep vein thrombosis (DVT). Demographic studies suggest a low incidence of DVT in Asian patients, but that might be underestimated. OBJECTIVE: Intervention by in-hospital case management for diagnosis of DVT in patients with acute stroke. PATIENTS AND METHODS: Intervention was defined as: recommendation of D-dimer test for patients who are immobile by day 4 after stroke onset and compression ultrasonography if the level of D-dimer is ≥500 ng/ml. Treating physicians were notified by case managers before they failed to do so for qualified patients. Data of patients hospitalized 12 months before and 8 months after the intervention, including basic demographics, Glasgow Coma Scale score, National Institute of Health Stroke Scale (NIHSS) score, laboratory results, and examination reports, was retrieved from electronic medical records for analysis by code searches for acute stroke. RESULTS: A total of 2523 patients were identified. 1528 were before and 995 after intervention. More patients after intervention had D-dimer test and ultrasound examination than that before intervention (22.1% vs 8.6%, P<0.001 and 15.1% vs 1.2%, P<0.001, respectively). Ultrasound diagnosis of DVT was significantly more after than before intervention (2.0% vs 0.3%, P<0.001). DVT was 55.7 per 1000 in patients with a NIHSS score≧18. Male sex (Odds ratio 0.33, 95% confidence intervals: 0.11-0.98), NIHSS score (Odds ratio 1.05, 95% confidence intervals: 1.00-1.09), and intervention (Odds ratio 5.39, 95% confidence intervals: 1.88-15.44) were independent predictors of ultrasound diagnosis of DVT. CONCLUSIONS: Intervention by in-hospital case management may be an effective strategy for improvement of under-diagnosis of DVT in acute stroke patients.