Search

BackgroundProtein-protein interactions (PPIs) are intriguing targets for designing novel small-molecule inhibitors. The role of PPIs in various infectious and neurodegenerative disorders makes them potential therapeutic targets . Despite being portrayed as undruggable targets, due to their flat surfaces, disorderedness, and lack of grooves. Recent progresses in computational biology have led researchers to reconsider PPIs in drug discovery.Areas coveredIn this review, we introduce in-silico methods used to identify PPI interfaces and present an in-depth overview of various computational methodologies that are successfully applied to annotate the PPIs. We also discuss several successful case studies that use computational tools to understand PPIs modulation and their key roles in various physiological processes.Expert opinionComputational methods face challenges due to the inherent flexibility of proteins, which makes them expensive, and result in the use of rigid models. This problem becomes more significant in PPIs due to their flexible and flat interfaces. Computational methods like molecular dynamics (MD) simulation and machine learning can integrate the chemical structure data into biochemical and can be used for target identification and modulation. These computational methodologies have been crucial in understanding the structure of PPIs, designing PPI modulators, discovering new drug targets, and predicting treatment outcomes.

Deep neural networks (DNN) are in high demand because of their widespread applications in natural language processing, image processing, and a lot of other domains. However, due to their computational expense, over-parameterization, and large memory requirements, DNN applications often require the use of substantial model resources. This strict requirement of latency and limited memory availability are hurdles in the device deployment of these technologies. Therefore, a common idea could be to mitigate the DNN-based models’ size without any performance degradation using different compression techniques. During the last few years, a great deal of progress has been made in the field of Natural Language Processing (NLP) using deep learning approaches. The objective of this research is to offer a thorough overview of the various pruning methods applied in the context of NLP. In this paper, we review several recent pruning-based schemes used for converting standard networks into their compact and accelerated versions. Traditionally, pruning is a technique for improving latency, reducing model size, and computational complexity which is a viable approach to deal with the above-mentioned challenges. In general, these techniques are divided into two main categories: structural and unstructured pruning methods. Structural pruning methods are further classified into filter, channel, layer, block, and movement pruning. Whereas, neuron, magnitude-based, and iterative pruning lie in the category of unstructured pruning. For each method, we discuss the related metrics and benchmarks. Then recent work on each method is discussed in detail, which provides insightful analysis of the performance, related applications, and pros and cons. Then, a comparative analysis is provided to analyze the differences among approaches. Finally, the paper concludes with possible future directions and some technical challenges.

Glycosaminoglycans (GAGs), in particular, heparan sulfate and heparin, are found colocalized with Aβ amyloid. They have been shown to enhance fibril formation, suggesting a possible pathological connection. We have investigated heparin's assembly of the KLVFFA peptide fragment using molecular dynamics simulation, to gain a molecular-level mechanistic understanding of how GAGs enhance fibril formation. The simulations reveal an exquisite process wherein heparin accelerates peptide assembly by first "gathering" the peptide molecules and then assembling them. Heparin does not act as a mere template but is tightly coupled to the peptides, yielding a composite protofilament structure. The strong intermolecular interactions suggest composite formation to be a general feature of heparin's interaction with peptides. Heparin's chain flexibility is found to be essential to its fibril promotion activity, and the need for optimal heparin chain length and concentration has been rationalized. These insights yield design rules (flexibility; chain-length) and protocol guidance (heparin:peptide molar ratio) for developing effective heparin mimetics and other functional GAGs.

Recently, several countries have been trying hard to facilitate the integration of disabled people into their societies by ensuring equal opportunities through ease of access to social services, daily human necessities, and the labor market. Deafness is considered one of the major disabilities separating the deaf from their society. To integrate the deaf fully into society, a two-way mode of communication is required: one from the deaf to the hearing people, and the other from the hearing to the deaf. Communication from the hearing person to the deaf is generally easy and can be done through speech recognition and text-to-sign representations, but communication from the deaf to the hearing is somewhat difficult and requires a sign recognition module that recognizes the sign motions from the deaf and translates it to a text; following this, a speech synthesis module will translate this text to speech. To build the sign recognition module, a sign language dataset is required. This paper contributes to the literature by introducing a comprehensive survey of 17 Arabic sign language datasets and by developing a well-organized framework that is used to build a sign language dataset. This paper also contributes to the literature by creating the largest Saudi Sign Language (SSL) database—the King Saud University Saudi-SSL (KSU-SSL data-base)—with 293 signs, 33 signers, 145,035 samples, and 10 domains (healthcare, common, alpha-bets, verbs, pronouns and adverbs, numbers, days, kings, family, and regions). This paper also contributes to the literature by introducing a convolutional graph neural network (CGCN) architecture for sign language recognition and applying the proposed architecture to the built KSU-SSL database. The architecture is made up of a small number of separable 3DGCN layers, and is augmented with a spatial attention mechanism. This study is a part of the project that aims to develop a two-way communication system for Saudi deaf individuals.

In search of potent inhibitors of cholinesterase enzymes and antioxidant agents, synthetic derivatives of dihydroquinazolin-4(1H)-one (1–38) were evaluated as potential anti-Alzheimer agents through in vitro acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) inhibitions and radical (DPPH and ABTS) scavenging activities. The structure–activity relationship (SAR) was mainly based on the different substituents at the aryl part which showed a significant effect on the inhibitory potential of enzymes and radical scavenging activities. The kinetic studies of most active compounds showed a noncompetitive mode of inhibition for AChE and a competitive mode of inhibition for the BChE enzyme. Additionally, molecular modelling studies were carried out to investigate the possible binding interactions of quinazolinone derivatives with the active site of both enzymes.

Disabled people are facing many difficulties communicating with others and involving in society. Modern societies have dedicated significant efforts to promote the integration of disabled individuals into their societies and services. Currently, smart healthcare systems are used to facilitate disabled people. The objective of this paper is to enable two-way communication of deaf individuals with the rest of society, thus enabling their migration from marginal elements of society to mainstream contributing elements. In the proposed system, we developed three modules; the sign recognition module (SRM) that recognizes the signs of a deaf individual, the speech recognition and synthesis module (SRSM) that processes the speech of a non-deaf individual and converts it to text, and an Avatar module (AM) to generate and perform the corresponding sign of the non-deaf speech, which were integrated into the sign translation companion system called Saudi deaf companion system (SDCS) to facilitate the communication from the deaf to the hearing and vice versa. This paper also contributes to the literature by utilizing our self-developed database, the largest Saudi Sign Language (SSL) database—the King Saud University Saudi-SSL (KSU-SSL). The proposed SDCS system performs 293 Saudi signs that are recommended by the Saudi Association for Hearing Impairment (SAHI) from 10 domains (healthcare, common, alphabets, verbs, pronouns and adverbs, numbers, days, kings, family, and regions).

This article introduces a novel optimization approach known as fractional order whale optimization algorithm (FWOA). The proposed optimizer incorporates the idea of fractional calculus (FC) into the mathematical structure of the conventional whale optimization algorithm (WOA). To validate the efficiency of the proposed FWOA, it is applied to address the challenges associated with the economic load dispatch (ELD) problem, which is a nonconvex, nonlinear, and non-smooth optimization problem. The objectives associated with ELD such as fuel cost and wind power generation cost minimization are achieved by taking into consideration different practical constraints like valve point loading effect (VPLE), transmission line losses, generator constraints, and stochastically variation of renewable energy sources (RES) integration. RES, particularly wind energy, has garnered more attention in recent times due to a range of environmental and economic factors. Stochastic wind (SW) power is also included in the ELD problem formulation. The incomplete gamma function (IGF) quantifies the influence of wind power. To assess its efficacy, the suggested approach is applied to a range of power systems including 3 generating units, 13 generating units and 40 generating units, consisting of 37 thermal units and 3 wind power units. To further strengthen the performance of the optimizer, the FWOA is hybridized with the interior point algorithm (IPA) to further refine the outcomes of the FWOA. The FWOA and IPA are used to address the problem of ELD while including the unpredictable nature of wind power. The simulation results of the suggested technique are compared with the most advanced heuristic optimization methods available, and it has been observed that the proposed optimizer obtained a superior and refined solution when compared to other state of the art optimization techniques. Furthermore, the efficacy of the suggested strategy in enhancing the solution of the ELD issue is validated through statistical analysis in terms of minimum fitness value. [ABSTRACT FROM AUTHOR]

This paper addresses the enhancement of multiple Unmanned Aerial Vehicle (UAV) swarm formation control in challenging terrains through the novel fractional memetic computing approach known as fractional-order velocity-pausing particle swarm optimization (FO-VPPSO). Existing particle swarm optimization (PSO) algorithms often suffer from premature convergence and an imbalanced exploration–exploitation trade-off, which limits their effectiveness in complex optimization problems such as UAV swarm control in rugged terrains. To overcome these limitations, FO-VPPSO introduces an adaptive fractional order β and a velocity pausing mechanism, which collectively enhance the algorithm's adaptability and robustness. This study leverages the advantages of a meta-heuristic computing approach; specifically, fractional-order velocity-pausing particle swarm optimization is utilized to optimize the flying path length, mitigate the mountain terrain costs, and prevent collisions within the UAV swarm. Leveraging fractional-order dynamics, the proposed hybrid algorithm exhibits accelerated convergence rates and improved solution optimality compared to traditional PSO methods. The methodology involves integrating terrain considerations and diverse UAV control parameters. Simulations under varying conditions, including complex terrains and dynamic threats, substantiate the effectiveness of the approach, resulting in superior fitness functions for multi-UAV swarms. To validate the performance and efficiency of the proposed optimizer, it was also applied to 13 benchmark functions, including uni- and multimodal functions in terms of the mean average fitness value over 100 independent trials, and furthermore, an improvement at percentages of 29.05% and 2.26% is also obtained against PSO and VPPSO in the case of the minimum flight length, as well as 16.46% and 1.60% in mountain terrain costs and 55.88% and 31.63% in collision avoidance. This study contributes valuable insights to the optimization challenges in UAV swarm-formation control, particularly in demanding terrains. The FO-VPPSO algorithm showcases potential advancements in swarm intelligence for real-world applications. [ABSTRACT FROM AUTHOR]

Introduction: Convolutional neural networks (CNNs) have maintained their dominance in deep learning methods for human action recognition (HAR) and other computer vision tasks. However, the need for a large amount of training data always restricts the performance of CNNs. Method: This paper is inspired by the two-stream network, where a CNN is deployed to train the network by using the spatial and temporal aspects of an activity, thus exploiting the strengths of both networks to achieve better accuracy. Contributions: Our contribution is twofold: first, we deploy an enhanced spatial stream, and it is demonstrated that models pre-trained on a larger dataset, when used in the spatial stream, yield good performance instead of training the entire model from scratch. Second, a dataset augmentation technique is presented to minimize overfitting of CNNs, where we increase the dataset size by performing various transformations on the images such as rotation and flipping, etc. Results: UCF101 is a standard benchmark dataset for action videos, and our architecture has been trained and validated on it. Compared with the other two-stream networks, our results outperformed them in terms of accuracy.

Numerous sensitive applications, such as healthcare and medical services, need reliable transmission as a prerequisite for the success of the new age of communications technology. Unfortunately, these systems are highly vulnerable to attacks like Sybil, where many false nodes are created and spread with deceitful intentions. Therefore, these false nodes must be instantly identified and isolated from the network due to security concerns and the sensitivity of data utilized in healthcare applications. Especially for life-threatening diseases like COVID-19, it is crucial to have devices connected to the Internet of Medical Things (IoMT) that can be believed to respond with high reliability and accuracy. Thus, trust-based security offers a safe environment for IoMT applications. This study proposes a blockchain-based fuzzy trust management framework (BFT-IoMT) to detect and isolate Sybil nodes in IoMT networks. The results demonstrate that the proposed BFT-IoMT framework is 25.43% and 12.64%, 12.54% and 6.65%, 37.85% and 19.08%, 17.40% and 8.72%, and 13.04% and 5.05% more efficient and effective in terms of energy consumption, attack detection, trust computation reliability, packet delivery ratio, and throughput, respectively, as compared to the other state-of-the-art frameworks available in the literature.

Effort estimation is the most critical activity for the success of overall solution delivery in software engineering projects. In this context, the paper’s main contributions to the literature on software effort estimation are twofold. First, this paper examines the application of meta-heuristic algorithms to have a logical and acceptable parametric model for software effort estimation. Secondly, to unravel the benefits of nature-inspired meta-heuristic algorithms usage in optimizing Deep Learning (DL) architectures for software effort estimation, this paper presents a Deep Neural Network (DNN) model for software effort estimation based on meta-heuristic algorithms. In this paper, Grey Wolf Optimizer (GWO) and StrawBerry (SB) meta-heuristic algorithms are applied for having a logical and acceptable parametric model for software effort estimation. To validate the performances of these two algorithms, a set of nine benchmark functions having wide dimensions is applied. Results from GWO and SB algorithms are compared with five other meta-heuristic algorithms used in literature for software effort estimation. Experimental results showed that the GWO has comprehensive superiority in terms of accuracy in estimation. The proposed DNN model (GWDNNSB) using meta-heuristic algorithms for initial weights and learning rate selection, produced better results compared to existing work on using DNN for software effort estimation.

Due to the rapid developments in technology and the sudden expansion of social media use, Dialect Arabic has become an important source of data that needs to be addressed when building Arabic corpora. In this paper, thirty-three Arabic corpora are surveyed to show that despite all of the developments in the literature, Saudi dialect (SD) corpora still need further expansion. This paper contributes to the literature on SD corpora by creating the largest Saudi corpus – the King Saud University Saudi Corpus (KSUSC) – with +1B total words, including +119M SD words. The KSUSC not only is the newest and largest SD corpus but is also diverse, covering 26 domains in text collected from five different sources. This paper also contributes to the literature by developing a new incremental preprocessing system that is used to create relevant lexicons that are then used to clean and normalize the collected data. This incremental system is scalable and can be adapted for different resources and dialects. Moreover, the collection process for building the KSUSC is discussed in detail, and the challenges in collecting SD text with respect to each platform are highlighted. By the end of this paper, different design criteria are proposed and used with the KSUSC to conclude that the resulting corpus can be of great benefit to researchers who are interested in integrating the corpus with their own work or using its resulting lexicons with Saudi-based NLP tasks.

The proper coordination of directional overcurrent relays (DOCRs) is crucial in electrical power systems. The coordination of DOCRs in a multi-loop power system is expressed as an optimization problem. The aim of this study focuses on improving the protection system's performance by minimizing the total operating time of DOCRs via effective coordination with main and backup DOCRs while keeping the coordination constraints within allowable limits. The coordination problem of DOCRs is solved by developing a new application strategy called Fractional Order Derivative Moth Flame Optimizer (FODMFO). This approach involves incorporating the ideas of fractional calculus (FC) into the mathematical model of the conventional moth flame algorithm to improve the characteristics of the optimizer. The FODMFO approach is then tested on the coordination problem of DOCRs in standard power systems, specifically the IEEE 3, 8, and 15 bus systems as well as in 11 benchmark functions including uni- and multimodal functions. The results obtained from the proposed method, as well as its comparison with other recently developed algorithms, demonstrate that the combination of FOD and MFO improves the overall efficiency of the optimizer by utilizing the individual strengths of these tools and identifying the globally optimal solution and minimize the total operating time of DOCRs up to an optimal value. The reliability, strength, and dependability of FODMFO are supported by a thorough statistics study using the box-plot, histograms, empirical cumulative distribution function demonstrations, and the minimal fitness evolution seen in each distinct simulation. Based on these data, it is evident that FODMFO outperforms other modern nature-inspired and conventional algorithms. [ABSTRACT FROM AUTHOR]

The modern power generation systems are increasing their reliance on high penetrations of distributed energy resources (DERs). However, the optimal dispatching mechanisms mainly rely on central controls which receive the load demand information from the electricity utility providers and allocate the electricity production targets to participating generating units. The lack of transparency and control over the DER fuel inputs makes the physical power purchase agreements (PPAs) a cumbersome task. This research work proposes an innovative fractal moth flame optimization (FMFO) approach to tackle the problem of integrated load dispatch (ILD). The proposed methodology provides a mechanism to integrate the information of the proposed optimizer, i.e., FMFO into the smart contracts enabled by the blockchain technology. This problem entails the allocation of loads to power-generating units in a manner that minimizes the total generation cost in a decentralized manner. To improve the efficiency of dispatch operations in the presence of a substantial integration of wind energy, this study proposes a novel framework based on the principles of fractal heritage, drawing inspiration from the classical MFO method. To assess the effectiveness and adaptability of the algorithm suggested, various non-convex scenarios in the context of optimization for ILD are considered. These scenarios incorporate valve-point loading effects (VPLEs), capacity limitations, power plants with multiple fuel options, and the presence of stochastic wind (SW) power uncertainty, following a Weibull distribution. The findings demonstrate exceptional performance in terms of minimizing fuel generation costs compared to traditional algorithms. [ABSTRACT FROM AUTHOR]

The capsule is a major virulence factor for Streptococcus pneumoniae which causes global morbidity and mortality. It is already known that there are few conserved genes in the capsular biosynthesis pathway, which are common among all known serotypes, called CpsA, CpsB, CpsC and CpsD. Inhibiting capsular synthesis can render S. pneumoniae defenseless and vulnerable to phagocytosis. The Inhibitory potential of active Zingiber officinale compounds was investigated against the 3D (3-dimensional) structural products of Cps genes using in silico techniques. A 3D compound repository was created and screened for drug-likeness and the qualified compounds were used for molecular docking and dynamic simulation-based experiments using gallic acid for outcome comparison. Cavity-based docking revealed five different cavities in the CpsA, CpsB and CpsD proteins, with gallic acid and selected compounds of Zingiber in a binding affinity range of -6.8 to -8.8 kcal/mol. Gingerenone A, gingerenone B, isogingerenone B and gingerenone C showed the highest binding affinities for CpsA, CpsB and CpsD, respectively. Through the Molegro Virtual Docker re-docking strategy, the highest binding energies (-126.5 kcal/mol) were computed for CpsB with gingerenone A and CpsD with gingerenone B. These findings suggest that gingerenone A, B and C are potential inhibitors of S. pneumoniae-conserved capsule-synthesizing proteins. [ABSTRACT FROM AUTHOR]

Secure and private communication has gained much focus on the international arena recently due to the ability of certain organizations to eavesdrop on private communication. This ability is further increased in the Internet of Medical Things scenario where medical images and private data are shared over insecure channels. This work is focused on a new and exciting question related to medical image steganography: is it possible to send hidden information through a cover medium, that is a medical image, without making any alteration to the cover medium in an effective manner? The proposed work has shown that it is possible to send hidden information through a medical image without making any alteration to the original medical image. This solves two problems at the same time. The first problem is that privacy and security approaches that depend on watermarking and steganography usually need some sort of modification to the medical images. The second is the knowledge that there is steganography taking place is completely hidden as no change is made to the medical image. Experiments have shown that the proposed approach under investigation demonstrates effective robustness against attacks like filtering, compression, and addition of noise.

Glaucoma is the second leading cause of blindness worldwide, and peripapillary atrophy (PPA) is a morphological symptom associated with it. Therefore, it is necessary to clinically detect PPA for glaucoma diagnosis. This study was aimed at developing a detection method for PPA using fundus images with deep learning algorithms to be used by ophthalmologists or optometrists for screening purposes. The model was developed based on localization for the region of interest (ROI) using a mask region-based convolutional neural networks R-CNN and a classification network for the presence of PPA using CNN deep learning algorithms. A total of 2,472 images, obtained from five public sources and one Saudi-based resource (King Abdullah International Medical Research Center in Riyadh, Saudi Arabia), were used to train and test the model. First the images from public sources were analyzed, followed by those from local sources, and finally, images from both sources were analyzed together. In testing the classification model, the area under the curve’s (AUC) scores of 0.83, 0.89, and 0.87 were obtained for the local, public, and combined sets, respectively. The developed model will assist in diagnosing glaucoma in screening programs; however, more research is needed on segmenting the PPA boundaries for more detailed PPA detection, which can be combined with optic disc and cup boundaries to calculate the cup-to-disc ratio.