MRDPDA: A multi-Laplacian regularized deepFM model for predicting piRNA-disease associations.

PIWI-interacting RNAs (piRNAs) are a typical class of small non-coding RNAs, which are essential for gene regulation, genome stability and so on. Accumulating studies have revealed that piRNAs have significant potential as biomarkers and therapeutic targets for a variety of diseases. However current computational methods face the challenge in effectively capturing piRNA-disease associations (PDAs) from limited data. In this study, we propose a novel method, MRDPDA, for predicting PDAs based on limited data from multiple sources. Specifically, MRDPDA integrates a deep factorization machine (deepFM) model with regularizations derived from multiple yet limited datasets, utilizing separate Laplacians instead of a simple average similarity network. Moreover, a unified objective function to combine embedding loss about similarities is proposed to ensure that the embedding is suitable for the prediction task. In addition, a balanced benchmark dataset based on piRPheno is constructed and a deep autoencoder is applied for creating reliable negative set from the unlabeled dataset. Compared with three latest methods, MRDPDA achieves the best performance on the pirpheno dataset in terms of the five-fold cross validation test and independent test set, and case studies further demonstrate the effectiveness of MRDPDA.

PLEKv2: predicting lncRNAs and mRNAs based on intrinsic sequence features and the coding-net model.

BACKGROUND: Long non-coding RNAs (lncRNAs) are RNA transcripts of more than 200 nucleotides that do not encode canonical proteins. Their biological structure is similar to messenger RNAs (mRNAs). To distinguish between lncRNA and mRNA transcripts quickly and accurately, we upgraded the PLEK alignment-free tool to its next version, PLEKv2, and constructed models tailored for both animals and plants. RESULTS: PLEKv2 can achieve 98.7% prediction accuracy for human datasets. Compared with classical tools and deep learning-based models, this is 8.1%, 3.7%, 16.6%, 1.4%, 4.9%, and 48.9% higher than CPC2, CNCI, Wen et al.'s CNN, LncADeep, PLEK, and NcResNet, respectively. The accuracy of PLEKv2 was > 90% for cross-species prediction. PLEKv2 is more effective and robust than CPC2, CNCI, LncADeep, PLEK, and NcResNet for primate datasets (including chimpanzees, macaques, and gorillas). Moreover, PLEKv2 is not only suitable for non-human primates that are closely related to humans, but can also predict the coding ability of RNA sequences in plants such as Arabidopsis. CONCLUSIONS: The experimental results illustrate that the model constructed by PLEKv2 can distinguish lncRNAs and mRNAs better than PLEK. The PLEKv2 software is freely available at https://sourceforge.net/projects/plek2/ .

A high-performance deep-learning-based pipeline for whole-brain vasculature segmentation at the capillary resolution.

MOTIVATION: Reconstructing and analyzing all blood vessels throughout the brain is significant for understanding brain function, revealing the mechanisms of brain disease, and mapping the whole-brain vascular atlas. Vessel segmentation is a fundamental step in reconstruction and analysis. The whole-brain optical microscopic imaging method enables the acquisition of whole-brain vessel images at the capillary resolution. Due to the massive amount of data and the complex vascular features generated by high-resolution whole-brain imaging, achieving rapid and accurate segmentation of whole-brain vasculature becomes a challenge. RESULTS: We introduce HP-VSP, a high-performance vessel segmentation pipeline based on deep learning. The pipeline consists of three processes: data blocking, block prediction, and block fusion. We used parallel computing to parallelize this pipeline to improve the efficiency of whole-brain vessel segmentation. We also designed a lightweight deep neural network based on multi-resolution vessel feature extraction to segment vessels at different scales throughout the brain accurately. We validated our approach on whole-brain vascular data from three transgenic mice collected by HD-fMOST. The results show that our proposed segmentation network achieves the state-of-the-art level under various evaluation metrics. In contrast, the parameters of the network are only 1% of those of similar networks. The established segmentation pipeline could be used on various computing platforms and complete the whole-brain vessel segmentation in 3 h. We also demonstrated that our pipeline could be applied to the vascular analysis. AVAILABILITY AND IMPLEMENTATION: The dataset is available at http://atlas.brainsmatics.org/a/li2301. The source code is freely available at https://github.com/visionlyx/HP-VSP.

Semi-supervised correction model for turbulence-distorted images.

Significant progress has been made in addressing turbulence distortion in recent years, but persistent challenges remain. Firstly, existing methods heavily rely on fully supervised optimization strategies and synthetic datasets, posing difficulties in effectively utilizing unlabeled real data for training. Secondly, most approaches construct networks in a straightforward manner, overlooking the representation model of phase distortion and point spread function (PSF) in spatial and channel dimensions. This oversight restricts the potential for distortion correction. To address these challenges, this paper proposes a semi-supervised atmospheric turbulence correction method based on the mean-teacher framework. Our approach imposes constraints on the unlabeled data of student networks using pseudo-labels generated by teacher networks, thereby enhancing the generalization ability by leveraging information from unlabeled data. Furthermore, we introduce to use no-reference image quality assessment criterion to select the most reliable pseudo-label for each unlabeled sample by predicting physical parameters that indicating the level of degradation. Additionally, we propose to combine sliding window-based self-attention with channel attention to facilitate local-global context interaction. This design is inspired by the representation of phase distortion and PSF, which can be characterized by coefficients and basis functions corresponding to the channel-wise representation of convolutional neural network features. Moreover, the base functions exhibit spatial correlation, akin to Zenike and Airy disks. Experimental results show that the proposed method surpasses state-of-the-art models.

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography.

During robot-assisted rehabilitation, failure to recognize lower limb movement may efficiently limit the development of exoskeleton robots, especially for individuals with knee pathology. A major challenge encountered with surface electromyography (sEMG) signals generated by lower limb movements is variability between subjects, such as motion patterns and muscle structure. To this end, this paper proposes an sEMG-based lower limb motion recognition using an improved support vector machine (SVM). Firstly, non-negative matrix factorization (NMF) is leveraged to analyze muscle synergy for multi-channel sEMG signals. Secondly, the multi-nonlinear sEMG features are extracted, which reflect the complexity of muscle status change during various lower limb movements. The Fisher discriminant function method is utilized to perform feature selection and reduce feature dimension. Then, a hybrid genetic algorithm-particle swarm optimization (GA-PSO) method is leveraged to determine the best parameters for SVM. Finally, the experiments are carried out to distinguish 11 healthy and 11 knee pathological subjects by performing three different lower limb movements. Results demonstrate the effectiveness and feasibility of the proposed approach in three different lower limb movements with an average accuracy of 96.03% in healthy subjects and 93.65% in knee pathological subjects, respectively.

A Novel Device-Free Counting Method Based on Channel Status Information.

Crowd counting is of significant importance for numerous applications, e.g., urban security, intelligent surveillance and crowd management. Existing crowd counting methods typically require specialized hardware deployment and strict operating conditions, thereby hindering their widespread application. To acquire a more effective crowd counting approach, a device-free counting method based on Channel Status Information (CSI) is proposed. The wavelet domain denoising is introduced to mitigate environment noise. Furthermore, the amplitude or phase covariance matrix is extracted as the eigenmatrix. Moreover, both the spatial diversity and frequency diversity are leveraged to improve detection robustness. At the same experimental environment, the accuracy of the proposed CSI-based method is compared with a renowned crowd counting one, i.e., Electronic Frog Eye: Counting Crowd Using WiFi (FCC). The experimental results reveal an accuracy improvement of 30% over FCC.

MFCA-Net: a deep learning method for semantic segmentation of remote sensing images.

Semantic segmentation of remote sensing images (RSI) is an important research direction in remote sensing technology. This paper proposes a multi-feature fusion and channel attention network, MFCA-Net, aiming to improve the segmentation accuracy of remote sensing images and the recognition performance of small target objects. The architecture is built on an encoding-decoding structure. The encoding structure includes the improved MobileNet V2 (IMV2) and multi-feature dense fusion (MFDF). In IMV2, the attention mechanism is introduced twice to enhance the feature extraction capability, and the design of MFDF can obtain more dense feature sampling points and larger receptive fields. In the decoding section, three branches of shallow features of the backbone network are fused with deep features, and upsampling is performed to achieve the pixel-level classification. Comparative experimental results of the six most advanced methods effectively prove that the segmentation accuracy of the proposed network has been significantly improved. Furthermore, the recognition degree of small target objects is higher. For example, the proposed MFCA-Net achieves about 3.65-23.55% MIoU improvement on the dataset Vaihingen.

Precise reconstruction of the entire mouse kidney at cellular resolution.

The kidney is an important organ for excreting metabolic waste and maintaining the stability of the body's internal environment. The renal function involves multiple complex and fine structures in the whole kidney, and any change in these structures may cause impaired nephric function. Consequently, achieving three-dimensional (3D) reconstruction of the entire kidney at a single-cell resolution is of significant importance for understanding the kidney's structural characteristics and exploring the pathogenesis of kidney diseases. In this paper, we propose a pipeline from sample preparation to optical microscopic imaging of the entire kidney, followed by data processing for 3D reconstruction of the whole mouse kidney. We employed transgenic fluorescent labeling and propidium iodide (PI) labeling to obtain detailed information about the vascular structure and cytoarchitecture of the kidney. Subsequently, the entire mouse kidney was imaged at submicron-resolution using high-definition fluorescent micro-optical sectioning tomography (HD-fMOST). Finally, we reconstructed the structures of interest through various data processing methods on the original images. This included detecting glomeruli throughout the entire kidney, as well as the segmentation and visualization of the renal arteries, veins, and three different types of nephrons. Our method provides a powerful tool for studying the renal microstructure and its spatial relationships throughout the entire kidney.

AngClust: Angle Feature-Based Clustering for Short Time Series Gene Expression Profiles.

When clustering gene expression, it is expected that correlation coefficients of genes in the same clusters are high, and that gene ontology (GO) enrichment analysis of most clusters will be significant. However, existing short-term gene expression clustering algorithms have limitations. To address this problem, we proposed a novel clustering process based on angular features for short-term gene expression. Our method (named AngClust) uses angular features to indicate the change of trend in gene expression levels at two neighboring time points. The changes of angles at multiple time points reflects the change of trend of the overall expression levels. Such changes are used to measure whether the expression trends of different genes are similar. To obtain functionally significant clusters from the clustering results, we evaluated numbers of genes in clusters, average correlation coefficient, fluctuation, and their correlation with GO term enrichment. The efficacy of AngClust outperform two other measures, Euclidean distance (ED) and dynamic time warping of correlation (DTW), on a dataset of yeast gene expression. The ratios of GO and pathway term-enriched of clusters of AngClust is higher than or equal to that of STEM and TMixClust on human, mouse, and yeast time series of gene expression.

Multi-perspective label based deep learning framework for cerebral vasculature segmentation in whole-brain fluorescence images.

The popularity of fluorescent labelling and mesoscopic optical imaging techniques enable the acquisition of whole mammalian brain vasculature images at capillary resolution. Segmentation of the cerebrovascular network is essential for analyzing the cerebrovascular structure and revealing the pathogenesis of brain diseases. Existing deep learning methods use a single type of annotated labels with the same pixel weight to train the neural network and segment vessels. Due to the variation in the shape, density and brightness of vessels in whole-brain fluorescence images, it is difficult for a neural network trained with a single type of label to segment all vessels accurately. To address this problem, we proposed a deep learning cerebral vasculature segmentation framework based on multi-perspective labels. First, the pixels in the central region of thick vessels and the skeleton region of vessels were extracted separately using morphological operations based on the binary annotated labels to generate two different labels. Then, we designed a three-stage 3D convolutional neural network containing three sub-networks, namely thick-vessel enhancement network, vessel skeleton enhancement network and multi-channel fusion segmentation network. The first two sub-networks were trained by the two labels generated in the previous step, respectively, and pre-segmented the vessels. The third sub-network was responsible for fusing the pre-segmented results to precisely segment the vessels. We validated our method on two mouse cerebral vascular datasets generated by different fluorescence imaging modalities. The results showed that our method outperforms the state-of-the-art methods, and the proposed method can be applied to segment the vasculature on large-scale volumes.

VBNet: An end-to-end 3D neural network for vessel bifurcation point detection in mesoscopic brain images.

BACKGROUND AND OBJECTIVE: Accurate detection of vessel bifurcation points from mesoscopic whole-brain images plays an important role in reconstructing cerebrovascular networks and understanding the pathogenesis of brain diseases. Existing detection methods are either less accurate or inefficient. In this paper, we propose VBNet, an end-to-end, one-stage neural network to detect vessel bifurcation points in 3D images. METHODS: Firstly, we designed a 3D convolutional neural network (CNN), which input a 3D image and output the coordinates of bifurcation points in this image. The network contains a two-scale architecture to detect large bifurcation points and small bifurcation points, respectively, which takes into account the accuracy and efficiency of detection. Then, to solve the problem of low accuracy caused by the imbalance between the numbers of large bifurcations and small bifurcations, we designed a weighted loss function based on the radius distribution of blood vessels. Finally, we extended the method to detect bifurcation points in large-scale volumes. RESULTS: The proposed method was tested on two mouse cerebral vascular datasets and a synthetic dataset. In the synthetic dataset, the F1-score of the proposed method reached 96.37%. In two real datasets, the F1-score was 92.35% and 86.18%, respectively. The detection effect of the proposed method reached the state-of-the-art level. CONCLUSIONS: We proposed a novel method for detecting vessel bifurcation points in 3D images. It can be used to precisely locate vessel bifurcations from various cerebrovascular images. This method can be further used to reconstruct and analyze vascular networks, and also for researchers to design detection methods for other targets in 3D biomedical images.

webTDat: A Web-Based, Real-Time, 3D Visualization Framework for Mesoscopic Whole-Brain Images.

The popularity of mesoscopic whole-brain imaging techniques has increased dramatically, but these techniques generate teravoxel-sized volumetric image data. Visualizing or interacting with these massive data is both necessary and essential in the bioimage analysis pipeline; however, due to their size, researchers have difficulty using typical computers to process them. The existing solutions do not consider applying web visualization and three-dimensional (3D) volume rendering methods simultaneously to reduce the number of data copy operations and provide a better way to visualize 3D structures in bioimage data. Here, we propose webTDat, an open-source, web-based, real-time 3D visualization framework for mesoscopic-scale whole-brain imaging datasets. webTDat uses an advanced rendering visualization method designed with an innovative data storage format and parallel rendering algorithms. webTDat loads the primary information in the image first and then decides whether it needs to load the secondary information in the image. By performing validation on TB-scale whole-brain datasets, webTDat achieves real-time performance during web visualization. The webTDat framework also provides a rich interface for annotation, making it a useful tool for visualizing mesoscopic whole-brain imaging data.

A density-based approach for detecting complexes in weighted PPI networks by semantic similarity.

Protein complex detection in PPI networks plays an important role in analyzing biological processes. A new algorithm-DBGPWN-is proposed for predicting complexes in PPI networks. Firstly, a method based on gene ontology is used to measure semantic similarities between interacted proteins, and the similarity values are used as their weights. Then, a density-based graph partitioning algorithm is developed to find clusters in the weighted PPI networks, and the identified ones are considered to be dense and similar. Experimental results demonstrate that our approach achieves good performance as compared with such algorithms as MCL, CMC, MCODE, RNSC, CORE, ClusterOne and FGN.