RESUMO
The detection of therapeutic peptides is a topic of immense interest in the biomedical field. Conventional biochemical experiment-based detection techniques are tedious and time-consuming. Computational biology has become a useful tool for improving the detection efficiency of therapeutic peptides. Most computational methods do not consider the deviation caused by noise. To improve the generalization performance of therapeutic peptide prediction methods, this work presents a sequence homology score-based deep fuzzy echo-state network with maximizing mixture correntropy (SHS-DFESN-MMC) model. Our method is compared with the existing methods on eight types of therapeutic peptide datasets. The model parameters are determined by 10 fold cross-validation on their training sets and verified by independent test sets. Across the 8 datasets, the average area under the receiver operating characteristic curve (AUC) values of SHS-DFESN-MMC are the highest on both the training (0.926) and independent sets (0.923).
Assuntos
Lógica Fuzzy , Redes Neurais de Computação , Peptídeos , Biologia Computacional/métodos , Humanos , Aprendizado Profundo , Área Sob a Curva , Curva ROC , AlgoritmosRESUMO
The eigenvalue statistics are an important tool to capture localization to delocalization transition in physical systems. Recently, a ß-Gaussian ensemble is being proposed as a single parameter to describe the intermediate eigenvalue statistics of many physical systems. It is critical to explore the universality of a ß-Gaussian ensemble in complex networks. In this work, we study the eigenvalue statistics of various network models, such as small-world, Erdos-Rényi random, and scale-free networks, as well as in comparing the intermediate level statistics of the model networks with that of a ß-Gaussian ensemble. It is found that the nearest-neighbor eigenvalue statistics of all the model networks are in excellent agreement with the ß-Gaussian ensemble. However, the ß-Gaussian ensemble fails to describe the intermediate level statistics of higher order eigenvalue statistics, though there is qualitative agreement till n<4. Additionally, we show that the nearest-neighbor eigenvalue statistics of the ß-Gaussian ensemble is in excellent agreement with the intermediate higher order eigenvalue statistics of model networks.
RESUMO
Endothelial dysfunction is a critical initiating factor contributing to cardiovascular diseases, involving the gut microbiome-derived metabolite trimethylamine N-oxide (TMAO). This study aims to clarify the time-dependent molecular pathways by which TMAO mediates endothelial dysfunction through transcriptomics and metabolomics analyses in human microvascular endothelial cells (HMEC-1). Cell viability and reactive oxygen species (ROS) generation were also evaluated. TMAO treatment for either 24H or 48H induces reduced cell viability and enhanced oxidative stress. Interestingly, the molecular signatures were distinct between the two time-points. Specifically, few Gene Ontology biological processes (BPs) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways were modulated after a short (24H) compared to a long (48H) treatment. However, the KEGG signalling pathways namely "tumour necrosis factor (TNF)" and "cytokine-cytokine receptor interaction" were downregulated at 24H but activated at 48H. In addition, at 48H, BPs linked to inflammatory phenotypes were activated (confirming KEGG results), while BPs linked to extracellular matrix (ECM) structural organisation, endothelial cell proliferation, and collagen metabolism were repressed. Lastly, metabolic profiling showed that arachidonic acid, prostaglandins, and palmitic acid were enriched at 48H. This study demonstrates that TMAO induces distinct time-dependent molecular signatures involving inflammation and remodelling pathways, while pathways such as oxidative stress are also modulated, but in a non-time-dependent manner.
Assuntos
Células Endoteliais , Doenças Vasculares , Humanos , Células Endoteliais/metabolismo , Metilaminas/metabolismo , Inflamação/induzido quimicamente , Inflamação/genética , Inflamação/metabolismo , ÓxidosRESUMO
People tend to make intuitive decisions based on certain heuristics. We have observed that there is an intuitive heuristic that tends to prioritize the most common features as the selection result. In order to study the influence of cognitive limitation and context induction on the intuitive thinking of common items, a questionnaire experiment with multidisciplinary features and similarity associations is designed. The experimental results reveal the existence of three classes of subjects. The behavioral features of Class I subjects show that cognitive limitations and task context fail to induce intuitive decision-making based on common items; instead, they rely heavily on rational analysis. The behavioral features of Class II subjects show a mixture of intuitive decision-making and rational analysis, with priority given to rational analysis. The behavioral features of Class III subjects indicate that the induction of the task context reinforces the reliance on intuitive decision-making. The electroencephalogram (EEG) feature responses (mainly in the ß and γ bands) of the three classes of subjects reflect their respective decision-making thinking characteristics. The event-related potential (ERP) results demonstrate that Class III subjects induce a late positive P600 component with a significantly higher average wave amplitude than the other two classes, which may be related to the "oh yes" behavior for the common item intuitive decision method.
Assuntos
Tomada de Decisões , Heurística , Humanos , Tomada de Decisões/fisiologia , Potenciais Evocados , EletroencefalografiaRESUMO
Modern computer vision algorithms are based on convolutional neural networks (CNNs), and both end-to-end learning and transfer learning modes have been used with CNN for image classification. Thus, automated brain tumor classification models have been proposed by deploying CNNs to help medical professionals. Our primary objective is to increase the classification performance using CNN. Therefore, a patch-based deep feature engineering model has been proposed in this work. Nowadays, patch division techniques have been used to attain high classification performance, and variable-sized patches have achieved good results. In this work, we have used three types of patches of different sizes (32 × 32, 56 × 56, 112 × 112). Six feature vectors have been obtained using these patches and two layers of the pretrained ResNet50 (global average pooling and fully connected layers). In the feature selection phase, three selectors-neighborhood component analysis (NCA), Chi2, and ReliefF-have been used, and 18 final feature vectors have been obtained. By deploying k nearest neighbors (kNN), 18 results have been calculated. Iterative hard majority voting (IHMV) has been applied to compute the general classification accuracy of this framework. This model uses different patches, feature extractors (two layers of the ResNet50 have been utilized as feature extractors), and selectors, making this a framework that we have named PatchResNet. A public brain image dataset containing four classes (glioblastoma multiforme (GBM), meningioma, pituitary tumor, healthy) has been used to develop the proposed PatchResNet model. Our proposed PatchResNet attained 98.10% classification accuracy using the public brain tumor image dataset. The developed PatchResNet model obtained high classification accuracy and has the advantage of being a self-organized framework. Therefore, the proposed method can choose the best result validation prediction vectors and achieve high image classification performance.
Assuntos
Neoplasias Encefálicas , Redes Neurais de Computação , Humanos , Algoritmos , Neoplasias Encefálicas/diagnóstico por imagem , Imageamento por Ressonância Magnética , EncéfaloRESUMO
The usage of social media around the world is ever-increasing. Social media statistics from 2019 show that there are 3.5 billion social media users worldwide. However, the existence of community structure renders the network vulnerable to attacks and large-scale losses. How does one comprehensively consider the multiple information sources and effectively evaluate the vulnerability of the community? To answer this question, we design a gravity-based community vulnerability evaluation (GBCVE) model for multiple information considerations. Specifically, we construct the community network by the Jensen-Shannon divergence and log-sigmoid transition function to show the relationship between communities. The number of edges inside community and outside of each community, as well as the gravity index are the three important factors used in this model for evaluating the community vulnerability. These three factors correspond to the interior information of the community, small-scale interaction relationship, and large-scale interaction relationship, respectively. A fuzzy ranking algorithm is then used to describe the vulnerability relationship between different communities, and the sensitivity of different weighting parameters is then analyzed by Sobol' indices. We validate and demonstrate the applicability of our proposed community vulnerability evaluation method via three real-world complex network test examples. Our proposed model can be applied to find vulnerable components in a network to mitigate the influence of public opinions or natural disasters in real time. The community vulnerability evaluation results from our proposed model are expected to shed light on other properties of communities within social networks and have real-world applications across network science.
RESUMO
The analysis of time series and images is significant across different fields due to their widespread applications. In the past few decades, many approaches have been developed, including data-driven artificial intelligence methods, mechanism-driven physical methods, and hybrid mechanism and data-driven models. Complex networks have been used to model numerous complex systems due to its characteristics, including time series prediction and image classification. In order to map time series and images into complex networks, many visibility graph algorithms have been developed, such as horizontal visibility graph, limited penetrable visibility graph, multiplex visibility graph, and image visibility graph. The family of visibility graph algorithms will construct different types of complex networks, including (un-) weighted, (un-) directed, and (single-) multi-layered networks, thereby focusing on different kinds of properties. Different types of visibility graph algorithms will be reviewed in this paper. Through exploring the topological structure and information in the network based on statistical physics, the property of time series and images can be discovered. In order to forecast (multivariate) time series, several variations of local random walk algorithms and different information fusion approaches are applied to measure the similarity between nodes in the network. Different forecasting frameworks are also proposed to consider the information in the time series based on the similarity. In order to classify the image, several machine learning models (such as support vector machine and linear discriminant) are used to classify images based on global features, local features, and multiplex features. Through various simulations on a variety of datasets, researchers have found that the visibility graph algorithm outperformed existing algorithms, both in time series prediction and image classification. Clearly, complex networks are closely connected with time series and images by visibility graph algorithms, rendering complex networks to be an important tool for understanding the characteristics of time series and images. Finally, we conclude in the last section with future outlooks for the visibility graph.
RESUMO
Individuals can make choices for themselves that are beneficial or detrimental to the entire group. Consider two losing choices that some individuals have to make on behalf of the group. Is it possible that the losing choices combine to give a winning outcome? We show that it is possible through a variant of Parrondo's paradox-the preference aggregation Parrondo's paradox (PAPP). This new variant of Parrondo's paradox makes use of an aggregate rule that combines with a decision-making heuristic that can be applied to individuals or parts of the social group. The aim of this work is to discuss this PAPP framework and exemplify it on a social network. This work enhances existing research by constructing a feedback loop that allows individuals in the social network to adapt its behavior according to the outcome of the Parrondo's games played.
RESUMO
To reduce the pace of climate change and achieve the goals set in Paris Agreement by 2030, Association of Southeast Asian Nations (ASEAN) countries have started to prioritize sustainability as one of their top agendas. Numerous studies have demonstrated that one of the most important issues that must be addressed to halt climate change is the urban heat island (UHI). Given the different mitigation strategies available, the focus of our study here is to assess the influence of green spaces and Green Mark commercial buildings on Singapore's temperature distribution using non-exhaustive factors related to energy consumption and efficiency. Additionally, this paper examines the effectiveness of green spaces and commercial buildings in reducing the rate of temperature change. This study uses ArcGIS software to map data, perform spatial analysis through cloud-based mapping, and produce visual representations with geographic information systems (GIS) to promote greater insight on the formulation of goals and policy making for strategic management. In comparison to non-commercial districts, our findings show that commercial districts have the lowest percentage of temperature change, an estimated 1.6 percent, due to a high concentration of green spaces and Green Mark commercial buildings. Our research also helps to close the research gaps in determining the efficacy of Green Mark commercial buildings, skyrise greeneries, gardens, and national parks. It also helps to minimize the bottleneck of expensive building costs and environmental damage that would have occurred from a design flaw found too late in the urban planning and construction process.
Assuntos
Sistemas de Informação Geográfica , Temperatura Alta , Cidades , Planejamento de Cidades , SingapuraRESUMO
Building Information Modeling (BIM) has been increasingly used in coordinating the different mechanical, electrical, and plumbing (MEP) services in the construction industries. As the construction industries are slowly adapting to BIM, the use of 2D software may become obsolete in the future as MEP services are technically more complicated to coordinate, due to respective services' codes of practice to follow and limit ceiling height. The 3D MEP designs are easy to visualize before installing the respective MEP services on the construction site to prevent delay in the construction process. The aid of current advanced technology has brought BIM to the next level to reduce manual work through automation. Combining both innovative technology and suitable management methods not only improves the workflow in design coordination, but also decreases conflict on the construction site and lowers labor costs. Therefore, this paper tries to explore possible advance technology in BIM and management strategies that could help MEP services to increase productivity, accuracy, and efficiency with a lower cost of finalizing the design of the building. This will assist the contractors to complete construction works before the targeted schedule and meet the client's expectations.
Assuntos
Indústria da Construção , Engenharia Sanitária , Automação , Humanos , Tecnologia da Informação , SoftwareRESUMO
Resolution of the intrinsic conflict between the reproduction of single cells and the homeostasis of a multicellular organism is central to animal biology and has direct impact on aging and cancer. Intercellular competition is indispensable in multicellular organisms because it weeds out senescent cells, thereby increasing the organism's fitness and delaying aging. In this Letter, we describe the growth dynamics of multicellular organisms in the presence of intercellular competition and show that the lifespan of organisms can be extended and the onset of cancer can be delayed if cells alternate between competition (a fair strategy) and noncompetitive growth, or cooperation (a losing strategy). This effect recapitulates the weak form of the game-theoretic Parrondo's paradox, whereby strategies that are individually fair or losing achieve a winning outcome when alternated. We show in a population model that periodic and stochastic switching between competitive and cooperative cellular strategies substantially extends the organism lifespan and reduces cancer incidence, which cannot be achieved simply by optimizing the competitive ability of the cells. These results indicate that cells could have evolved to optimally mix competitive and cooperative strategies, and that periodic intercellular competition could potentially be exploited and tuned to delay aging.
Assuntos
Longevidade , Neoplasias , Envelhecimento , AnimaisRESUMO
One common cause of vision loss after retinal detachment surgery is the formation of proliferative and contractile fibrocellular membranes. This aberrant wound healing process is mediated by epithelial-mesenchymal transition (EMT) and hyper-proliferation of retinal pigment epithelial (RPE) cells. Current treatment relies primarily on surgical removal of these membranes. Here, we demonstrate that a bio-functional polymer by itself is able to prevent retinal scarring in an experimental rabbit model of proliferative vitreoretinopathy. This is mediated primarily via clathrin-dependent internalisation of polymeric micelles, downstream suppression of canonical EMT transcription factors, reduction of RPE cell hyper-proliferation and migration. Nuclear factor erythroid 2-related factor 2 signalling pathway was identified in a genome-wide transcriptomic profiling as a key sensor and effector. This study highlights the potential of using synthetic bio-functional polymer to modulate RPE cellular behaviour and offers a potential therapy for retinal scarring prevention.
Assuntos
Fator 2 Relacionado a NF-E2 , Epitélio Pigmentado da Retina , Animais , Linhagem Celular , Movimento Celular , Cicatriz/metabolismo , Transição Epitelial-Mesenquimal , Fator 2 Relacionado a NF-E2/genética , Fator 2 Relacionado a NF-E2/metabolismo , Polímeros/metabolismo , Coelhos , Epitélio Pigmentado da Retina/metabolismoRESUMO
Intracerebral hemorrhage (ICH) is the most common type of hemorrhagic stroke which occurs due to ruptures of weakened blood vessel in brain tissue. It is a serious medical emergency issues that needs immediate treatment. Large numbers of noncontrast-computed tomography (NCCT) brain images are analyzed manually by radiologists to diagnose the hemorrhagic stroke, which is a difficult and time-consuming process. In this study, we propose an automated transfer deep learning method that combines ResNet-50 and dense layer for accurate prediction of intracranial hemorrhage on NCCT brain images. A total of 1164 NCCT brain images were collected from 62 patients with hemorrhagic stroke from Kalinga Institute of Medical Science, Bhubaneswar and used for evaluating the model. The proposed model takes individual CT images as input and classifies them as hemorrhagic or normal. This deep transfer learning approach reached 99.6% accuracy, 99.7% specificity, and 99.4% sensitivity which are better results than that of ResNet-50 only. It is evident that the deep transfer learning model has advantages for automatic diagnosis of hemorrhagic stroke and has the potential to be used as a clinical decision support tool to assist radiologists in stroke diagnosis.
Assuntos
Aprendizado Profundo , Acidente Vascular Cerebral Hemorrágico , Acidente Vascular Cerebral , Hemorragia Cerebral/diagnóstico por imagem , Humanos , Hemorragias Intracranianas/diagnóstico por imagem , Acidente Vascular Cerebral/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodosRESUMO
SignificanceBacteriophages, the most widespread reproducing biological entity on Earth, employ two strategies of virus-host interaction: lysis of the host cell and lysogeny whereby the virus genome integrates into the host genome and propagates vertically with it. We present a population model that reveals an effect known as Parrondo's paradox in game theory: Alternating between lysis and lysogeny is a winning strategy for a bacteriophage, even when each strategy individually is at a disadvantage compared with a competing bacteriophage. Thus, evolution of bacteriophages appears to optimize the ratio between the lysis and lysogeny propensities rather than the phage burst size in any individual phase. This phenomenon is likely to be relevant for understanding evolution of other host-parasites systems.
Assuntos
Bacteriófagos , Lisogenia , Bacteriófagos/genética , Teoria dos Jogos , Genoma ViralRESUMO
Recently, deep models have been very popular because they achieve excellent performance with many classification problems. Deep networks have high computational complexities and require specific hardware. To overcome this problem (without decreasing classification ability), a hand-modeled feature selection method is proposed in this paper. A new shape-based local feature extractor is presented which uses the geometric shape of the frustum. By using a frustum pattern, textural features are generated. Moreover, statistical features have been extracted in this model. Textures and statistics features are fused, and a hybrid feature extraction phase is obtained; these features are low-level. To generate high level features, tunable Q factor wavelet transform (TQWT) is used. The presented hybrid feature generator creates 154 feature vectors; hence, it is named Frustum154. In the multilevel feature creation phase, this model can select the appropriate feature vectors automatically and create the final feature vector by merging the appropriate feature vectors. Iterative neighborhood component analysis (INCA) chooses the best feature vector, and shallow classifiers are then used. Frustum154 has been tested on three basic hand-movement sEMG datasets. Hand-movement sEMG datasets are commonly used in biomedical engineering, but there are some problems in this area. The presented models generally required one dataset to achieve high classification ability. In this work, three sEMG datasets have been used to test the performance of Frustum154. The presented model is self-organized and selects the most informative subbands and features automatically. It achieved 98.89%, 94.94%, and 95.30% classification accuracies using shallow classifiers, indicating that Frustum154 can improve classification accuracy.
Assuntos
Algoritmos , Análise de Ondaletas , Mãos , Força da Mão , MovimentoRESUMO
For a certain kind of decision event, the decision maker does not know the internal mechanism and knowledge information of the decision events.When this kind of decision events gives multiple selection branches, it is found that there is a decision psychological tendency to find the most common features by comparing the selection branches. Based on this, a zero-knowledge decision making (ZKDM) method is proposed. By defining the feature points and feature sets of the selection branches of the decision events, the characteristic moments of the system are constructed and the branch with the most common characteristics is obtained. It is observed that through the findings of investigation the probability of arriving at the correct choice based on the ZKDM method is high. The effectiveness of the ZKDM method may be related to the fact that the designers of decision events usually determine the correct selection branch first, before changing it to design other branches. A questionnaire survey of 279 respondents reveals that more than half of them actually adopt such a design idea. Furthermore, a separate questionnaire survey of 465 decision-makers reveal that 19.14% of the respondents clearly adopt ZKDM.
Assuntos
Tomada de Decisões , Psicofísica/métodos , Comportamento de Escolha , Humanos , Intuição , Conhecimento , Inquéritos e QuestionáriosRESUMO
In this article, an expert system-based multiagent deep deterministic policy gradient (ESB-MADDPG) is proposed to realize the decision making for swarm robots. Multiagent deep deterministic policy gradient (MADDPG) is a multiagent reinforcement learning algorithm proposed to utilize a centralized critic within the actor-critic learning framework, which can reduce policy gradient variance. However, it is difficult to apply traditional MADDPG to swarm robots directly as it is time consuming during the path planning, rendering it necessary to propose a faster method to gather the trajectories. Besides, the trajectories obtained by the MADDPG are continuous by straight lines, which is not smooth and will be difficult for the swarm robots to track. This article aims to solve these problems by closing the above gaps. First, the ESB-MADDPG method is proposed to improve the training speed. The smooth processing of the trajectory is designed in the ESB-MADDPG. Furthermore, the expert system also provides us with many trained offline trajectories, which avoid the retraining each time we use the swarm robots. Considering the gathered trajectories, the model predictive control (MPC) algorithm is introduced to realize the optimal tracking of the offline trajectories. Simulation results show that combining ESB-MADDPG and MPC can realize swarm robot decision making efficiently.
RESUMO
The traditional intravitreal injection delivery of antivascular endothelial growth factor (anti-VEGF) to the posterior segment of the eye for treatment of retinal diseases is invasive and associated with sight-threatening complications. To avoid such complications, there has been significant interest in developing polymers for topical drug delivery to the retina. This study reports a nanomicelle drug delivery system made of a copolymer EPC (nEPCs), which is capable of delivering aflibercept to the posterior segment topically through corneal-scleral routes. EPC is composed of poly(ethylene glycol) (PEG), poly(propylene glycol) (PPG), and polycaprolactone (PCL) segments. In this study, aflibercept-loaded nEPCs (nEPCs + A) are capable of penetrating the cornea in ex vivo porcine eye models and deliver a clinically significant amount of aflibercept to the retina in laser-induced choroidal neovascularization (CNV) murine models, causing CNV regression. nEPCs + A also demonstrate biocompatibility in vitro and in vivo. Interestingly, this study also suggests that nEPCs have intrinsic antiangiogenic properties. The ability to deliver anti-VEGF drugs and the intrinsic antiangiogenic properties of nEPCs may result in synergistic effects, which can be harnessed for effective therapeutics. nEPCs may be a promising topical anti-VEGF delivery platform for the treatment of retinal diseases.
Assuntos
Neovascularização de Coroide , Doenças Retinianas , Inibidores da Angiogênese/farmacologia , Inibidores da Angiogênese/uso terapêutico , Animais , Neovascularização de Coroide/tratamento farmacológico , Neovascularização de Coroide/etiologia , Sistemas de Liberação de Medicamentos , Camundongos , Receptores de Fatores de Crescimento do Endotélio Vascular/uso terapêutico , Proteínas Recombinantes de Fusão , Doenças Retinianas/complicações , Doenças Retinianas/tratamento farmacológico , Suínos , Fator A de Crescimento do Endotélio VascularRESUMO
Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.