MR2CPPIS: Accurate prediction of protein-protein interaction sites based on multi-scale Res2Net with coordinate attention mechanism.

Proteins play a vital role in various biological processes and achieve their functions through protein-protein interactions (PPIs). Thus, accurate identification of PPI sites is essential. Traditional biological methods for identifying PPIs are costly, labor-intensive, and time-consuming. The development of computational prediction methods for PPI sites offers promising alternatives. Most known deep learning (DL) methods employ layer-wise multi-scale CNNs to extract features from protein sequences. But, these methods usually neglect the spatial positions and hierarchical information embedded within protein sequences, which are actually crucial for PPI site prediction. In this paper, we propose MR2CPPIS, a novel sequence-based DL model that utilizes the multi-scale Res2Net with coordinate attention mechanism to exploit multi-scale features and enhance PPI site prediction capability. We leverage the multi-scale Res2Net to expand the receptive field for each network layer, thus capturing multi-scale information of protein sequences at a granular level. To further explore the local contextual features of each target residue, we employ a coordinate attention block to characterize the precise spatial position information, enabling the network to effectively extract long-range dependencies. We evaluate our MR2CPPIS on three public benchmark datasets (Dset 72, Dset 186, and PDBset 164), achieving state-of-the-art performance. The source codes are available at https://github.com/YyinGong/MR2CPPIS.

A CNN-LSTM Ensemble Model for Predicting Protein-Protein Interaction Binding Sites.

Proteins commonly perform biological functions through protein-protein interactions (PPIs). The knowledge of PPI sites is imperative for the understanding of protein functions, disease mechanisms, and drug design. Traditional biological experimental methods for studying PPI sites still incur considerable drawbacks, including long experimental time and high labor costs. Therefore, many computational methods have been proposed for predicting PPI sites. However, achieving high prediction performance and overcoming severe data imbalance remain challenging issues. In this paper, we propose a new sequence-based deep learning model called CLPPIS (standing for CNN-LSTM ensemble based PPI Sites prediction). CLPPIS consists of CNN and LSTM components, which can capture spatial features and sequential features simultaneously. Further, it utilizes a novel feature group as input, which has 7 physicochemical, biophysical, and statistical properties. Besides, it adopts a batch-weighted loss function to reduce the interference of imbalance data. Our work suggests that the integration of protein spatial features and sequential features provides important information for PPI sites prediction. Evaluation on three public benchmark datasets shows that our CLPPIS model significantly outperforms existing state-of-the-art methods.

Three-Stage Global Channel Pruning for Resources-Limited Platform.

Deep neural networks (DNNs) have demonstrated remarkable performance in many fields, and deploying them on resource-limited devices has drawn more and more attention in industry and academia. Typically, there are great challenges for intelligent networked vehicles and drones to deploy object detection tasks due to the limited memory and computing power of embedded devices. To meet these challenges, hardware-friendly model compression approaches are required to reduce model parameters and computation. Three-stage global channel pruning, which involves sparsity training, channel pruning, and fine-tuning, is very popular in the field of model compression for its hardware-friendly structural pruning and ease of implementation. However, existing methods suffer from problems such as uneven sparsity, damage to the network structure, and reduced pruning ratio due to channel protection. To solve these issues, the present article makes the following significant contributions. First, we present an element-level heatmap-guided sparsity training method to achieve even sparsity, resulting in higher pruning ratio and improved performance. Second, we propose a global channel pruning method that fuses both global and local channel importance metrics to identify unimportant channels for pruning. Third, we present a channel replacement policy (CRP) to protect layers, ensuring that the pruning ratio can be guaranteed even under high pruning rate conditions. Evaluations show that our proposed method significantly outperforms the state-of-the-art (SOTA) methods in terms of pruning efficiency, making it more suitable for deployment on resource-limited devices.

Predicting miRNA-disease association through combining miRNA function and network topological similarities based on MINE.

Predicting associations between microRNAs (miRNAs) and diseases from the viewpoint of function modules has become increasingly popular. However, existing methods obtained the relations between diseases and miRNAs only through the construction of similarity networks and neglected the complex network characteristic. In this paper, a new method named combining miRNA function similarities and network topology similarities based on module identification in networks (ComSim-MINE) was developed. Combined similarity is calculated from the harmonic mean between miRNA function similarities and network topology similarities. Experimental results showed that ComSim-MINE can compete with several state-of-the-art weighted function module algorithms, such as ClusterONE, MCODE, NEMO, and SPICi, and achieved the satisfactory results in terms of the composite score of F-measure, sensitivity, and accuracy based on the generated miRNA function interaction network. From the analysis of case studies, some new findings obtained from our proposed method provide clinicians new clues for epidemic diseases, such as COVID-19.

Towards Interpretable Arrhythmia Classification With Human-Machine Collaborative Knowledge Representation.

Arrhythmia detection and classification is a crucial step for diagnosing cardiovascular diseases. However, deep learning models that are commonly used and trained in end-to-end fashion are not able to provide good interpretability. In this paper, we address this deficiency by proposing the first novel interpretable arrhythmia classification approach based on a human-machine collaborative knowledge representation. Our approach first employs an AutoEncoder to encode electrocardiogram signals into two parts: hand-encoding knowledge and machine-encoding knowledge. A classifier then takes as input the encoded knowledge to classify arrhythmia heartbeats with or without human in the loop (HIL). Experiments and evaluation on the MIT-BIH Arrhythmia Database demonstrate that our new approach not only can effectively classify arrhythmia while offering interpretability, but also can improve the classification accuracy by adjusting the hand-encoding knowledge with our HIL mechanism.

LiDAR Point Cloud Recognition and Visualization with Deep Learning for Overhead Contact Inspection.

As overhead contact (OC) is an essential part of power supply systems in high-speed railways, it is necessary to regularly inspect and repair abnormal OC components. Relative to manual inspection, applying LiDAR (light detection and ranging) to OC inspection can improve efficiency, accuracy, and safety, but it faces challenges to efficiently and effectively segment LiDAR point cloud data and identify catenary components. Recent deep learning-based recognition methods are rarely employed to recognize OC components, because they have high computational complexity, while their accuracy needs to be improved. To track these problems, we first propose a lightweight model, RobotNet, with depthwise and pointwise convolutions and an attention module to recognize the point cloud. Second, we optimize RobotNet to accelerate its recognition speed on embedded devices using an existing compilation tool. Third, we design software to facilitate the visualization of point cloud data. Our software can not only display a large amount of point cloud data, but also visualize the details of OC components. Extensive experiments demonstrate that RobotNet recognizes OC components more accurately and efficiently than others. The inference speed of the optimized RobotNet increases by an order of magnitude. RobotNet has lower computational complexity than other studies. The visualization results also show that our recognition method is effective.

The study of cooperative obstacle avoidance method for MWSN based on flocking control.

Compared with the space fixed feature of traditional wireless sensor network (WSN), mobile WSN has better robustness and adaptability in unknown environment, so that it is always applied in the research of target tracking. In order to reach the target, the nodes group should find a self-adaptive method to avoid the obstacles together in their moving directions. Previous methods, which were based on flocking control model, realized the strategy of obstacle avoidance by means of potential field. However, these may sometimes lead the nodes group to fall into a restricted area like a trap and never get out of it. Based on traditional flocking control model, this paper introduced a new cooperative obstacle avoidance model combined with improved SA obstacle avoidance algorithm. It defined the tangent line of the intersection of node's velocity line and the edge of obstacle as the steering direction. Furthermore, the cooperative obstacle avoidance model was also improved in avoiding complex obstacles. When nodes group encounters mobile obstacles, nodes will predict movement path based on the spatial location and velocity of obstacle. And when nodes group enters concave obstacles, nodes will temporarily ignore the gravity of the target and search path along the edge of the concave obstacles. Simulation results showed that cooperative obstacle avoidance model has significant improvement on average speed and time efficiency in avoiding obstacle compared with the traditional flocking control model. It is more suitable for obstacle avoidance in complex environment.

A clustering protocol for wireless sensor networks based on energy potential field.

It is the core issue of researching that how to prolong the lifetime of wireless sensor network. The purpose of this paper is to illustrate a clustering protocol LEACH-PF, which is a multihop routing algorithm with energy potential field of divided clusters. In LEACH-PF, the network is divided into a number of subnetworks and each subnetwork has a cluster head. These clusters construct an intercluster routing tree according to the potential difference of different equipotential fields. The other member nodes of the subnetworks communicate with their cluster head directly, so as to complete regional coverage. The results of simulation show that LEACH-PF can reduce energy consumption of the network effectively and prolong the network lifetime.

Multiple ant colony algorithm method for selecting tag SNPs.

The search for the association between complex disease and single nucleotide polymorphisms (SNPs) or haplotypes has recently received great attention. Finding a set of tag SNPs for haplotyping in a great number of samples is an important step to reduce cost for association study. Therefore, it is essential to select tag SNPs with more efficient algorithms. In this paper, we model problem of selection tag SNPs by MINIMUM TEST SET and use multiple ant colony algorithm (MACA) to search a smaller set of tag SNPs for haplotyping. The various experimental results on various datasets show that the running time of our method is less than GTagger and MLR. And MACA can find the most representative SNPs for haplotyping, so that MACA is more stable and the number of tag SNPs is also smaller than other evolutionary methods (like GTagger and NSGA-II). Our software is available upon request to the corresponding author.

A case for spiking neural network simulation based on configurable multiple-FPGA systems.

Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.

Coronavirus phylogeny based on triplets of nucleic acids bases.

We considered the fully overlapping triplets of nucleotide bases and proposed a 2D graphical representation of protein sequences consisting of 20 amino acids and a stop code. Based on this 2D graphical representation, we outlined a new approach to analyze the phylogenetic relationships of coronaviruses by constructing a covariance matrix. The evolutionary distances are obtained through measuring the differences among the two-dimensional curves.