MUSCLE: multi-view and multi-scale attentional feature fusion for microRNA-disease associations prediction.

MicroRNAs (miRNAs) synergize with various biomolecules in human cells resulting in diverse functions in regulating a wide range of biological processes. Predicting potential disease-associated miRNAs as valuable biomarkers contributes to the treatment of human diseases. However, few previous methods take a holistic perspective and only concentrate on isolated miRNA and disease objects, thereby ignoring that human cells are responsible for multiple relationships. In this work, we first constructed a multi-view graph based on the relationships between miRNAs and various biomolecules, and then utilized graph attention neural network to learn the graph topology features of miRNAs and diseases for each view. Next, we added an attention mechanism again, and developed a multi-scale feature fusion module, aiming to determine the optimal fusion results for the multi-view topology features of miRNAs and diseases. In addition, the prior attribute knowledge of miRNAs and diseases was simultaneously added to achieve better prediction results and solve the cold start problem. Finally, the learned miRNA and disease representations were then concatenated and fed into a multi-layer perceptron for end-to-end training and predicting potential miRNA-disease associations. To assess the efficacy of our model (called MUSCLE), we performed 5- and 10-fold cross-validation (CV), which got average the Area under ROC curves of 0.966${\pm }$0.0102 and 0.973${\pm }$0.0135, respectively, outperforming most current state-of-the-art models. We then examined the impact of crucial parameters on prediction performance and performed ablation experiments on the feature combination and model architecture. Furthermore, the case studies about colon cancer, lung cancer and breast cancer also fully demonstrate the good inductive capability of MUSCLE. Our data and code are free available at a public GitHub repository: https://github.com/zht-code/MUSCLE.git.

OAS Deep Q-Learning-Based Fast and Smooth Control Method for Traffic Signal Transition in Urban Arterial Tidal Lanes.

To address traffic flow fluctuations caused by changes in traffic signal control schemes on tidal lanes and maintain smooth traffic operations, this paper proposes a method for controlling traffic signal transitions on tidal lanes. Firstly, the proposed method includes designing an intersection overlap phase scheme based on the traffic flow conflict matrix in the tidal lane scenario and a fast and smooth transition method for key intersections based on the flow ratio. The aim of the control is to equalize average queue lengths and minimize average vehicle delays for different flow directions at the intersection. This study also analyses various tidal lane scenarios based on the different opening states of the tidal lanes at related intersections. The transitions of phase offsets are emphasized after a comprehensive analysis of transition time and smoothing characteristics. In addition, this paper proposes a coordinated method for tidal lanes to optimize the phase offset at arterial intersections for smooth and rapid transitions. The method uses Deep Q-Learning, a reinforcement learning algorithm for optimal action selection (OSA), to develop an adaptive traffic signal transition control and enhance its efficiency. Finally, a simulation experiment using a traffic control interface is presented to validate the proposed approach. This study shows that this method leads to smoother and faster traffic signal transitions across different tidal lane scenarios compared to the conventional method. Implementing this solution can benefit intersection groups by reducing traffic delays, improving traffic efficiency, and decreasing air pollution caused by congestion.

MiR133b-mediated inhibition of EGFR-PTK pathway promotes rAAV2 transduction by facilitating intracellular trafficking and augmenting second-strand synthesis.

Recombinant adeno-associated virus (rAAV) is an extremely attractive vector in the in vivo delivery of gene therapy as it is safe and its genome is simple. However, challenges including low permissiveness to specific cells and restricted tissue specificity have hindered its clinical application. Based on the previous studies, epidermal growth factor receptor-protein tyrosine kinase (EGFR-PTK) negatively regulated rAAV transduction, and EGFR-positive cells were hardly permissive to rAAV transduction. We constructed a novel rAAV-miRNA133b vector, which co-expressed miRNA133b and transgene, and investigated its in vivo and in vitro transduction efficiency. Confocal microscopy, live-cell imaging, pharmacological reagents and labelled virion tracking were used to analyse the effect of miRNA133b on rAAV2 transduction and the underlying mechanisms. The results demonstrated that miRNA133b could promote rAAV2 transduction and the effects were limited to EGFR-positive cells. The increased transduction was found to be a direct result of decreased rAAV particles degradation in the cytoplasm and enhanced second-strand synthesis. ss-rAAV2-miRNA133b vector specifically increased rAAV2 transduction in EGFR-positive cells or tissues, while ss-rAAV2-Fluc-miRNA133b exerted an antitumor effect. rAAV-miRNA133b vector might emerge as a promising platform for delivering various transgene to treat EGFR-positive cell-related diseases, such as non-small-cell lung cancer.

Reactive oxygen species enhance rAAV transduction by promoting its escape from late endosomes.

BACKGROUND: Recent seminal studies have revealed that endosomal reactive oxygen species (ROS) promote rather than inhibit viral infection. Some ROS generators, including shikonin and H2O2, have the potential to enhance recombinant adeno-associated virus (rAAV) transduction. However, the impact of ROS on rAAV intracellular trafficking remains unclear. METHODS: To understand the effects of ROS on the transduction of rAAV vectors, especially the rAAV subcellular distribution profiles, this study systematically explored the effect of ROS on each step of rAAV intracellular trafficking pathway using fluorescently-labeled rAAV and qPCR quantification determination. RESULTS: The results showed promoted in-vivo and in-vitro rAAV transduction by ROS exposure, regardless of vector serotype or cell type. ROS treatment directed rAAV intracellular trafficking towards a more productive pathway by upregulating the expression of cathepsins B and L, accelerating the rAAV transit in late endosomes, and increasing the rAAV nucleus entry. CONCLUSIONS: These data support that ROS generative drugs, such as shikonin, have the potential to promote rAAV vector transduction by promoting rAAV's escape from late endosomes, and enhancing its productive trafficking to the nucleus.

DYNet: A Printed Book Detection Model Using Dual Kernel Neural Networks.

Target detection has always been a hotspot in image processing/computer vision research, and small-target detection is a frequently encountered problem in the field of target detection. With the continuous innovation of target detection technology, people always hope that the detection of small targets can reach the real-time accuracy of large-target detection. In this paper, a small-target detection model based on dual-core convolutional neural networks (CNN) is proposed, which is mainly used for the intelligent detection of books in the production line of printed books. The model is mainly composed of two modules, including a region prediction module and suspicious target search module. The region prediction module uses a CNN to predict suspicious region blocks in a large context. The suspicious target search module uses a different CNN from the above to find tiny targets in the predicted region blocks. Comparative testing of four small book target samples using this model shows that this model has better book small-target detection accuracy compared to other models.

MultiDTI: drug-target interaction prediction based on multi-modal representation learning to bridge the gap between new chemical entities and known heterogeneous network.

MOTIVATION: Predicting new drug-target interactions is an important step in new drug development, understanding of its side effects and drug repositioning. Heterogeneous data sources can provide comprehensive information and different perspectives for drug-target interaction prediction. Thus, there have been many calculation methods relying on heterogeneous networks. Most of them use graph-related algorithms to characterize nodes in heterogeneous networks for predicting new drug-target interactions (DTI). However, these methods can only make predictions in known heterogeneous network datasets, and cannot support the prediction of new chemical entities outside the heterogeneous network, which hinder further drug discovery and development. RESULTS: To solve this problem, we proposed a multi-modal DTI prediction model named 'MultiDTI' which uses our proposed joint learning framework based on heterogeneous networks. It combines the interaction or association information of the heterogeneous network and the drug/target sequence information, and maps the drugs, targets, side effects and disease nodes in the heterogeneous network into a common space. In this way, 'MultiDTI' can map the new chemical entity to this learned common space based on the chemical structure of the new entity. That is, bridging the gap between new chemical entities and known heterogeneous network. Our model has strong predictive performance, and the area under the receiver operating characteristic curve of the model is 0.961 and the area under the precision recall curve is 0.947 with 10-fold cross validation. In addition, some predicted new DTIs have been confirmed by ChEMBL database. Our results indicate that 'MultiDTI' is a powerful and practical tool for predicting new DTI, which can promote the development of drug discovery or drug repositioning. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at https://github.com/Deshan-Zhou/MultiDTI/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

AQMDRL: Automatic Quality of Service Architecture Based on Multistep Deep Reinforcement Learning in Software-Defined Networking.

Software-defined networking (SDN) has become one of the critical technologies for data center networks, as it can improve network performance from a global perspective using artificial intelligence algorithms. Due to the strong decision-making and generalization ability, deep reinforcement learning (DRL) has been used in SDN intelligent routing and scheduling mechanisms. However, traditional deep reinforcement learning algorithms present the problems of slow convergence rate and instability, resulting in poor network quality of service (QoS) for an extended period before convergence. Aiming at the above problems, we propose an automatic QoS architecture based on multistep DRL (AQMDRL) to optimize the QoS performance of SDN. AQMDRL uses a multistep approach to solve the overestimation and underestimation problems of the deep deterministic policy gradient (DDPG) algorithm. The multistep approach uses the maximum value of the n-step action currently estimated by the neural network instead of the one-step Q-value function, as it reduces the possibility of positive error generated by the Q-value function and can effectively improve convergence stability. In addition, we adapt a prioritized experience sampling based on SumTree binary trees to improve the convergence rate of the multistep DDPG algorithm. Our experiments show that the AQMDRL we proposed significantly improves the convergence performance and effectively reduces the network transmission delay of SDN over existing DRL algorithms.

Dexmedetomidine Ameliorates Postoperative Cognitive Dysfunction in Aged Mice.

Neuroinflammation and oxidative stress coexist and interact in the progression of postoperative cognitive dysfunction (POCD) and other neurodegenerative disease. Mounting studies reveal that Dexmedetomidine (Dex) possesses anti-inflammatory and antioxidant properties. Nevertheless, whether Dex exerts neuroprotective effect on the cognitive sequelae of oxidative stress and inflammatory process remains unclear. A mouse model of abdominal exploratory laparotomy-induced cognitive dysfunction was employed to explore the underlying mechanism of neuroprotective effects exerted by Dex in POCD. Aged mice were treated with Dex (20 µg/kg) 20 min prior to surgery. Open field test (OFT) and Morris water maze (MWM) were employed to examine the cognitive function on postoperative day 3 (POD 3) or POD 7. In the present study, mice underwent surgery exhibited cognitive impairment without altering spontaneous locomotor activity, while the surgery-induced cognitive impairment could be alleviated by Dex pretreatment. Dex inhibited surgery-induced pro-inflammatory cytokines accumulation and microglial activation in the hippocampi of mice. Furthermore, Dex decreased MDA levels, enhanced SOD activity, modulated CDK5 activity and increased BDNF expression in the hippocampus. In addition, Dex remarkably reduced the surgery-induced increased ratio of Bax/Bcl-2 and apoptotic neurons in the hippocampi of aged mice. Collectively, our study provides evidence that Dex may exert neuroprotective effects against surgery-induced cognitive impairment through mechanisms involving its anti-inflammatory and antioxidant properties, as well as the suppression on the mitochondrial permeability transition pore and apoptosis-related pathway.

Structural and mechanistic insights into modified G-quadruplex thrombin-binding DNA aptamers.

Thrombin-binding aptamer (TBA) can fold into a G-quadruplex structure necessary for interacting with thrombin. When one thymidine residue of the TGT loop at position 7 is replaced with unlocked uracil (UNA), d-isothymidine (D-isoT) or l-isothymidine (L-isoT), these modified sequences display different activities. To date, the mechanisms of how D/L-isoT and UNA influence the biological properties of TBA have not been illustrated in the literature. In this paper, we fill this gap by probing the structure variations and binding modes of these modified TBAs via molecular dynamics (MD) simulation and free energy calculation. Comparative structural analyses demonstrated that both D-IsoT and UNA changed the local conformation of TGT loop and formed stronger interactions with the target protein. Particularly, D-IsoT and UNA adopted similar conformation which can well explain their similar biological activities. In addition, the flexibility of the two TT loops were described clearly. In contrast, L-IsoT at position 7 led to an obvious tendency to unfold. Free energy calculation and the analysis of key residues energy contributions eventually provide a clear picture of interactions for further understanding of the structure-activity relationships. Collectively, our findings open the way for a rational design of modified aptamers.

Performance and cost evaluation of health information systems using micro-costing and discrete-event simulation.

Innovation and health-care funding reforms have contributed to the deployment of Information and Communication Technology (ICT) to improve patient care. Many health-care organizations considered the application of ICT as a crucial key to enhance health-care management. The purpose of this paper is to provide a methodology to assess the organizational impact of high-level Health Information System (HIS) on patient pathway. We propose an integrated performance evaluation of HIS approach through the combination of formal modeling using the Architecture of Integrated Information Systems (ARIS) models, a micro-costing approach for cost evaluation, and a Discrete-Event Simulation (DES) approach. The methodology is applied to the consultation for cancer treatment process. Simulation scenarios are established to conclude about the impact of HIS on patient pathway. We demonstrated that although high level HIS lengthen the consultation, occupation rate of oncologists are lower and quality of service is higher (through the number of available information accessed during the consultation to formulate the diagnostic). The provided method allows also to determine the most cost-effective ICT elements to improve the care process quality while minimizing costs. The methodology is flexible enough to be applied to other health-care systems.

Inhibition of integrin ß3, a binding partner of kallistatin, leads to reduced viability, invasion and proliferation in NCI-H446 cells.

BACKGROUND: Kallistatin is a serine proteinase inhibitor and heparin-binding protein. It is considered an endogenous angiogenic inhibitor. In addition, multiple studies demonstrated that kallistatin directly inhibits cancer cell growth. However, the molecular mechanisms underlying these effects remain unclear. METHODS: Pull-down, immunoprecipitation, and immunoblotting were used for binding experiments. To elucidate the mechanisms, integrin ß3 knockdown (siRNA) or blockage (antibody treatment) on the cell surface of small the cell lung cancer NCI-H446 cell line was used. RESULTS: Interestingly, kallistatin was capable of binding integrin ß3 on the cell surface of NCI-H446 cells. Meanwhile, integrin ß3 knockdown or blockage resulted in loss of antitumor activities induced by kallistatin. Furthermore, kallistatin suppressed tyrosine phosphorylation of integrin ß3 and its downstream signaling pathways, including FAK/-Src, AKT and Erk/MAPK. Viability, proliferation and migration of NCI-H446 cells were inhibited by kallistatin, with Bcl-2 and Grb2 downregulation, and Bax, cleaved caspase-9 and caspase 3 upregulation. CONCLUSIONS: These findings reveal a novel role for kallistatin in preventing small cell lung cancer growth and mobility, by direct interaction with integrin ß3, leading to blockade of the related signaling pathway.

A stochastic optimization model for shift scheduling in emergency departments.

Excessive waiting time in Emergency Departments (ED) can be both a cause of frustration and more importantly, a health concern for patients. Waiting time arises when the demand for work goes beyond the facility's service capacity. ED service capacity mainly depends on human resources and on beds available for patients. In this paper, we focus on human resources organization in an ED and seek to best balance between service quality and working conditions. More specifically, we address the personnel scheduling problem in order to optimize the shift distribution among employees and minimize the total expected patients' waiting time. The problem is also characterized by a multi-stage re-entrant service process. With an appropriate approximation of patients' waiting times, we first propose a stochastic mixed-integer programming model that is solved by a sample average approximation (SAA) approach. The resulting personnel schedules are then evaluated using a discrete-event simulation model. Numerical experiments are then performed with data from a French hospital to compare different personnel scheduling strategies.

A multi-source molecular network representation model for protein-protein interactions prediction.

The prediction of potential protein-protein interactions (PPIs) is a critical step in decoding diseases and understanding cellular mechanisms. Traditional biological experiments have identified plenty of potential PPIs in recent years, but this problem is still far from being solved. Hence, there is urgent to develop computational models with good performance and high efficiency to predict potential PPIs. In this study, we propose a multi-source molecular network representation learning model (called MultiPPIs) to predict potential protein-protein interactions. Specifically, we first extract the protein sequence features according to the physicochemical properties of amino acids by utilizing the auto covariance method. Second, a multi-source association network is constructed by integrating the known associations among miRNAs, proteins, lncRNAs, drugs, and diseases. The graph representation learning method, DeepWalk, is adopted to extract the multisource association information of proteins with other biomolecules. In this way, the known protein-protein interaction pairs can be represented as a concatenation of the protein sequence and the multi-source association features of proteins. Finally, the Random Forest classifier and corresponding optimal parameters are used for training and prediction. In the results, MultiPPIs obtains an average 86.03% prediction accuracy with 82.69% sensitivity at the AUC of 93.03% under five-fold cross-validation. The experimental results indicate that MultiPPIs has a good prediction performance and provides valuable insights into the field of potential protein-protein interactions prediction. MultiPPIs is free available at https://github.com/jiboyalab/multiPPIs .

MHGTMDA: Molecular heterogeneous graph transformer based on biological entity graph for miRNA-disease associations prediction.

MicroRNAs (miRNAs) play a crucial role in the prevention, prognosis, diagnosis, and treatment of complex diseases. Existing computational methods primarily focus on biologically relevant molecules directly associated with miRNA or disease, overlooking the fact that the human body is a highly complex system where miRNA or disease may indirectly correlate with various types of biomolecules. To address this, we propose a novel prediction model named MHGTMDA (miRNA and disease association prediction using heterogeneous graph transformer based on molecular heterogeneous graph). MHGTMDA integrates biological entity relationships of eight biomolecules, constructing a relatively comprehensive heterogeneous biological entity graph. MHGTMDA serves as a powerful molecular heterogeneity map transformer, capturing structural elements and properties of miRNAs and diseases, revealing potential associations. In a 5-fold cross-validation study, MHGTMDA achieved an area under the receiver operating characteristic curve of 0.9569, surpassing state-of-the-art methods by at least 3%. Feature ablation experiments suggest that considering features among multiple biomolecules is more effective in uncovering miRNA-disease correlations. Furthermore, we conducted differential expression analyses on breast cancer and lung cancer, using MHGTMDA to further validate differentially expressed miRNAs. The results demonstrate MHGTMDA's capability to identify novel MDAs.

Bleomycin promotes rAAV2 transduction via DNA-PKcs/Artemis-mediated DNA break repair pathways.

Because it is safe and has a simple genome, recombinant adeno-associated virus (rAAV) is an extremely appealing vector for delivery in in vivo gene therapy. However, its low transduction efficiency for some cells, limits its further application in the field of gene therapy. Bleomycin is a chemotherapeutic agent approved by the FDA whose effect on rAAV transduction has not been studied. In this study, we systematically investigated the effect of Bleomycin on the second-strand synthesis and used CRISPR/CAS9 and RNAi methods to understand the effects of Bleomycin on rAAV vector transduction, particularly the effect of DNA repair enzymes. The results showed that Bleomycin could promote rAAV2 transduction both in vivo and in vitro. Increased transduction was discovered to be a direct result of decreased cytoplasmic rAAV particle degradation and increased second-strand synthesis. TDP1, PNKP, and SETMAR are required to repair the DNA damage gap caused by Bleomycin, TDP1, PNKP, and SETMAR promote rAAV second-strand synthesis. Bleomycin induced DNA-PKcs phosphorylation and phosphorylated DNA-PKcs and Artemis promoted second-strand synthesis. The current study identifies an effective method for increasing the capability and scope of in-vivo and in-vitro rAAV applications, which can amplify cell transduction at Bleomycin concentrations. It also supplies information on combining tumor gene therapy with chemotherapy.

Copper-Catalyzed C(sp)-H Bond Hydrazidation.

A catalytic, direct synthetic strategy for preparing ynehydrazides with terminal alkynes and dialkyl azodicarboxylates is described. The protocol utilizes a cheap copper catalyst in combination with a catalytic amount of a weak base. The high sustainability, good practicality, broad substrate scope, and wide functional group tolerance comprised the advantages of this reaction. Synthetic applications and preliminary mechanistic studies have been conducted.

Modeling analysis of armed conflict risk in sub-Saharan Africa, 2000-2019.

Sub-Saharan Africa has suffered frequent outbreaks of armed conflict since the end of the Cold War. Although several efforts have been made to understand the underlying causes of armed conflict and establish an early warning mechanism, there is still a lack of a comprehensive assessment approach to model the incidence risk of armed conflict well. Based on a large database of armed conflict events and related spatial datasets covering the period 2000-2019, this study uses a boosted regression tree (BRT) approach to model the spatiotemporal distribution of armed conflict risk in sub-Saharan Africa. Evaluation of accuracy indicates that the simulated models obtain high performance with an area under the receiver operator characteristic curve (ROC-AUC) mean value of 0.937 and an area under the precision recall curves (PR-AUC) mean value of 0.891. The result of the relative contribution indicates that the background context factors (i.e., social welfare and the political system) are the main driving factors of armed conflict risk, with a mean relative contribution of 92.599%. By comparison, the climate change-related variables have relatively little effect on armed conflict risk, accounting for only 7.401% of the total. These results provide novel insight into modelling the incidence risk of armed conflict, which may help implement interventions to prevent and minimize the harm of armed conflict.

HF-DDI: Predicting Drug-Drug Interaction Events Based on Multimodal Hybrid Fusion.

Drug-drug interactions (DDIs) can have a significant impact on patient safety and health. Predicting potential DDIs before administering drugs to patients is a critical step in drug development and can help prevent adverse drug events. In this study, we propose a novel method called HF-DDI for predicting DDI events based on various drug features, including molecular structure, target, and enzyme information. Specifically, we design our model with both early fusion and late fusion strategies and utilize a score calculation module to predict the likelihood of interactions between drugs. Our model was trained and tested on a large data set of known DDIs, achieving an overall accuracy of 0.948. The results suggest that incorporating multiple drug features can improve the accuracy of DDI event prediction and may be useful for improving drug safety and patient outcomes.

Adjuvant therapeutic strategy decision support for an elderly population with localized breast cancer: A monocentric cohort retrospective study.

Guidelines for the management of elderly patients with early breast cancer are scarce. Additional adjuvant systemic treatment to surgery for early breast cancer in elderly populations is challenged by increasing comorbidities with age. In non-metastatic settings, treatment decisions are often made under considerable uncertainty; this commonly leads to undertreatment and, consequently, poorer outcomes. This study aimed to develop a decision support tool that can help to identify candidate adjuvant post-surgery treatment schemes for elderly breast cancer patients based on tumor and patient characteristics. Our approach was to generate predictions of patient outcomes for different courses of action; these predictions can, in turn, be used to inform clinical decisions for new patients. We used a cohort of elderly patients (≥ 70 years) who underwent surgery with curative intent for early breast cancer to train the models. We tested seven classification algorithms using 5-fold cross-validation, with 80% of the data being randomly selected for training and the remaining 20% for testing. We assessed model performance using accuracy, precision, recall, F1-score, and AUC score. We used an autoencoder to perform dimensionality reduction prior to classification. We observed consistently better performance using logistic regression and linear discriminant analysis models when compared to the other models we tested. Classification performance generally improved when an autoencoder was used, except for when we predicted the need for adjuvant treatment. We obtained overall best results using a logistic regression model without autoencoding to predict the need for adjuvant treatment (F1-score = 0.869).

An integrated deep-learning and multi-level framework for understanding the behavior of terrorist groups.

Human security is threatened by terrorism in the 21st century. A rapidly growing field of study aims to understand terrorist attack patterns for counter-terrorism policies. Existing research aimed at predicting terrorism from a single perspective, typically employing only background contextual information or past attacks of terrorist groups, has reached its limits. Here, we propose an integrated deep-learning framework that incorporates the background context of past attacked locations, social networks, and past actions of individual terrorist groups to discover the behavior patterns of terrorist groups. The results show that our framework outperforms the conventional base model at different spatio-temporal resolutions. Further, our model can project future targets of active terrorist groups to identify high-risk areas and offer other attack-related information in sequence for a specific terrorist group. Our findings highlight that the combination of a deep-learning approach and multi-scalar data can provide groundbreaking insights into terrorism and other organized violent crimes.