Treatment and prevention of pigeon diarrhea through the application of Lactobacillus SNK-6.

In the pigeon industry, treating and preventing diarrhea is vital because it is a serious health problem for pigeons. This study investigated the incidence of diarrhea in 3 pigeon farms in Shanghai, and analyzed the microflora through 16S rDNA high-throughput sequencing. Four strains of Escherichia coli (E. coli) isolated from pigeon diarrhea feces were administered via gavage to healthy pigeons, with each pigeon receiving 2 × 108 CFU. Pigeons that developed diarrhea after E. coli challenge were treated with 3 g of Lactobacillus salivarius SNK-6 (L. salivarius SNK-6) health sand (1.6 × 107 CFU/g). Then, a mass feeding experiment expanded to 688 pairs of pigeons with 3 replicates, each receiving 3 g of health sand containing L. salivarius SNK-6 (1.6 × 107 CFU/g) every 2 wk, and fecal status monitored and recorded. The study found that the relative abundance of the Lactobacillus genus and L. salivarius in feces from pigeons with diarrhea was significantly lower than in normal pigeon feces (P < 0.05). In contrast, E. coli showed a higher abundance and diversity in feces from pigeons with diarrhea than in normal feces (P < 0.05). Three out of the 4 isolated E. coli strains caused pigeon diarrhea, resulting in a significant reduction in microbial diversity in fecal samples (P < 0.05). Both the small group attack experiment and the mass-fed additive experiment in pigeon farms demonstrated that feeding L. salivarius SNK-6 effectively cured and prevented diarrhea. Pigeons fed with L. salivarius SNK-6 exhibited no diarrhea, while the control group had a 10% diarrhea rate. In summary, a deficiency of Lactobacillus or a high abundance of E. coli in the intestine could easily cause pigeon diarrhea. Feeding L. salivarius SNK-6 could treat pigeon diarrhea, and continuous supplementation could maintain stable preventive effects.

Genome-wide association study of growth traits and validation of key mutations (MSTN c.C861T) associated with the muscle mass of meat pigeons.

Selective breeding of meat pigeons is primarily based on growth traits, especially muscle mass (MM). Identification of functional genes and molecular markers of growth and slaughter traits through a genome-wide association study (GWAS) will help to elucidate the underlying molecular mechanisms and provide a theoretical basis for the selective breeding of meat pigeons. The phenotypic data of body weight (BW) and body size (BS) of 556 meat pigeons at 52 and 80 weeks of age were collected. In total, 160 434 high-quality single nucleotide polymorphism sites were obtained by restriction site-associated DNA sequencing. The GWAS analysis revealed that MSTN, IGF2BP3 and NCAPG/LCORL were important candidate genes affecting the growth traits of meat pigeons. IGF2BP3 and NCAPG/LCORL were highly correlated to BW and BS, which are related to overall growth and development, while MSTN was associated with pectoral thickness and BW. Phenotypic association validation with the use of two meat pigeon populations found that the MSTN mutation c.C861T determines the MM. These results provide new insights into the genetic mechanisms underlying phenotypic variations of growth traits and MM in commercial meat pigeons. The identified markers and genes provide a theoretical basis for the selective breeding of meat pigeons.

DAMS-Net: Dual attention and multi-scale information fusion network for 12-lead ECG classification.

Automated 12-lead electrocardiographic (ECG) classification algorithms play an important role in the diagnosis of clinical arrhythmias. Current methods that perform well in the field of automatic ECG classification are usually based on Convolutional Neural Networks (CNN) or Transformer. However, due to the intrinsic locality of convolution operations, CNN can't extract long-dependence between series. On the other side, the Transformer design includes a built-in global self-attention mechanism, but it doesn't pay enough attention to local features. In this paper, we propose DAMS-Net, which combines the advantages of Transformer and CNN, introducing a spatial attention module and a channel attention module using a CNN-Transformer hybrid encoder to adaptively focus on the significant features of global and local parts between space and channels. In addition, our proposal fuses multi-scale information to capture high and low-level semantic information by skip-connections. We evaluate our method on the 2018 Physiological Electrical Signaling Challenge dataset, and our proposal achieves a precision rate of 83.6%, a recall rate of 84.7%, and an F1-score of 0.839. The classification performance is superior to all current single-model methods evaluated in this dataset. The experimental results demonstrate the promising application of our proposed method in 12-lead ECG automatic classification tasks.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification is limited due to the small sample size of the well-curated data. To tackle this problem, this article proposes a distance transformation-based deep forest framework with hybrid-feature fusion (DTDF-HFF) for accurate CXR image classification. In our proposed method, hybrid features of CXR images are extracted in two ways: hand-crafted feature extraction and multigrained scanning. Different types of features are fed into different classifiers in the same layer of the deep forest (DF), and the prediction vector obtained at each layer is transformed to form distance vector based on a self-adaptive scheme. The distance vectors obtained by different classifiers are fused and concatenated with the original features, then input into the corresponding classifier at the next layer. The cascade grows until DTDF-HFF can no longer gain benefits from the new layer. We compare the proposed method with other methods on the public CXR datasets, and the experimental results show that the proposed method can achieve state-of-the art (SOTA) performance. The code will be made publicly available at https://github.com/hongqq/DTDF-HFF.

Systematic review of digital twin technology and applications.

As one of the most important applications of digitalization, intelligence, and service, the digital twin (DT) breaks through the constraints of time, space, cost, and security on physical entities, expands and optimizes the relevant functions of physical entities, and enhances their application value. This phenomenon has been widely studied in academia and industry. In this study, the concept and definition of DT, as utilized by scholars and researchers in various fields of industry, are summarized. The internal association between DT and related technologies is explained. The four stages of DT development history are identified. The fundamentals of the technology, evaluation indexes, and model frameworks are reviewed. Subsequently, a conceptual ternary model of DT based on time, space, and logic is proposed. The technology and application status of typical DT systems are described. Finally, the current technical challenges of DT technology are analyzed, and directions for future development are discussed.

Micro-Expression Recognition Based on Optical Flow and PCANet.

Micro-expressions are rapid and subtle facial movements. Different from ordinary facial expressions in our daily life, micro-expressions are very difficult to detect and recognize. In recent years, due to a wide range of potential applications in many domains, micro-expression recognition has aroused extensive attention from computer vision. Because available micro-expression datasets are very small, deep neural network models with a huge number of parameters are prone to over-fitting. In this article, we propose an OF-PCANet+ method for micro-expression recognition, in which we design a spatiotemporal feature learning strategy based on shallow PCANet+ model, and we incorporate optical flow sequence stacking with the PCANet+ network to learn discriminative spatiotemporal features. We conduct comprehensive experiments on publicly available SMIC and CASME2 datasets. The results show that our lightweight model obviously outperforms popular hand-crafted methods and also achieves comparable performances with deep learning based methods, such as 3D-FCNN and ELRCN.

Whole-genome sequencing reveals the artificial selection and local environmental adaptability of pigeons (Columba livia).

To meet human needs, domestic pigeons (Columba livia) with various phenotypes have been bred to provide genetic material for our research on artificial selection and local environmental adaptation. Seven pigeon breeds were resequenced and can be divided into commercial varieties (Euro-pigeon, Shiqi, Shen King, Taishen, and Silver King), ornamental varieties (High Fliers), and local varieties (Tarim pigeon). Phylogenetic analysis based on population resequencing showed that one group contained local breeds and ornamental pigeons from China, whereas all commercial varieties were clustered together. It is revealed that the traditional Chinese ornamental pigeon is a branch of Tarim pigeon. Runs of homozygosity (ROH) and linkage disequilibrium (LD) analyses revealed significant differences in the genetic diversity of the three types of pigeons. Genome sweep analysis revealed that the selected genes of commercial breeds were related to body size, reproduction, and plumage color. The genomic imprinting genes left by the ornamental pigeon breeds were mostly related to special human facial features and muscular dystrophy. The Tarim pigeon has evolved genes related to chemical ion transport, photoreceptors, oxidative stress, organ development, and olfaction in order to adapt to local environmental stress. This research provides a molecular basis for pigeon genetic resource evaluation and genetic improvement and suggests that the understanding of adaptive evolution should integrate the effects of various natural environmental characteristics.

Using comparative genomics to detect mutations regulating plumage variations in graylag (A. anser) and swan geese (A. cygnoides).

Although graylag geese (A. anser) showed similar plumages of white, grey, and white with grey patches compared to those in swan geese (A. cygnoides), it was believed the substantial molecular mechanism for plumage variations were different. To date, studies on genes responsible for diverse plumages among graylag geese were limited and causal mutations remain unknown. In this study, genomes from 57 individuals belonging to six breeds showing different plumages were sequenced at ∼10X depth. Firstly, the allele frequency differences (AFD) of variants on the scaffold394 (NW_013185915.1) between grey and white goose breeds (A. anser) was calculated and a genomic region between 768,290-779,889 bp was detected to carry candidate variants associated with plumages, including one SNP (g. 775,151G > T, ∼18.6 kb upstream of EDNRB2) found to be fixed in white geese. This region was overlapped with the one detected by the haplotype-based sweep analysis, in which significant signals defined a candidate region of 736,610-820,622 bp on the same scaffold. Results from the transcriptomic data showed that expression levels of EDNRB2 and many other melanogenesis-related genes were significantly decreased among white geese compared to that in grey geese, especially at late embryonic stages (>E15). Modifications at transcriptional levels might result in abnormal melanocyte developments and thus the white plumages when they grow up. In addition, a frameshift mutation (C > -) in exon4 of MLANA gene on scaffold176 (NW_013185876.1) was suggested as the causal mutation for sex-linked dilution phenotype in graylag geese although this requires more demonstration experiments. Together with observed white plumages caused by EDNRB2 mutations in coding regions among swan geese and chicken, our study provided new examples to study the parallel evolution.

A Novel Molecular Representation Learning for Molecular Property Prediction with a Multiple SMILES-Based Augmentation.

Deep learning has brought a rapid development in the aspect of molecular representation for various tasks, such as molecular property prediction. The prediction of molecular properties is a crucial task in the field of drug discovery for finding specific drugs with good pharmacological activity and pharmacokinetic properties. SMILES string is always used as a kind of character approach in deep neural network models, inspired by natural language processing techniques. However, the deep learning models are hindered by the nonunique nature of the SMILES string. To efficiently learn molecular features along all message paths, in this paper we encode multiple SMILES for every molecule as an automated data augmentation for the prediction of molecular properties, which alleviates the overfitting problem caused by the small amount of data in the datasets of molecular property prediction. As a result, by using the multiple SMILES-based augmentation, we obtained better molecular representation and showed superior performance in the tasks of predicting molecular properties.

Effective knowledge graph embeddings based on multidirectional semantics relations for polypharmacy side effects prediction.

MOTIVATION: Polypharmacy is the combined use of drugs for the treatment of diseases. However, it often shows a high risk of side effects. Due to unnecessary interactions of combined drugs, the side effects of polypharmacy increase the risk of disease and even lead to death. Thus, obtaining abundant and comprehensive information on the side effects of polypharmacy is a vital task in the healthcare industry. Early traditional methods used machine learning techniques to predict side effects. However, they often make costly efforts to extract features of drugs for prediction. Later, several methods based on knowledge graphs are proposed. They are reported to outperform traditional methods. However, they still show limited performance by failing to model complex relations of side effects among drugs. RESULTS: To resolve the above problems, we propose a novel model by further incorporating complex relations of side effects into knowledge graph embeddings. Our model can translate and transmit multidirectional semantics with fewer parameters, leading to better scalability in large-scale knowledge graphs. Experimental evaluation shows that our model outperforms state-of-the-art models in terms of the average area under the ROC and precision-recall curves. AVAILABILITY AND IMPLEMENTATION: Code and data are available at: https://github.com/galaxysunwen/MSTE-master.

Geometry-Based Molecular Generation With Deep Constrained Variational Autoencoder.

Finding target molecules with specific chemical properties plays a decisive role in drug development. We proposed GEOM-CVAE, a constrained variational autoencoder based on geometric representation for molecular generation with specific properties, which is protein-context-dependent. In terms of machine learning, it includes continuous feature embedding encoder and molecular generation decoder. Our key contribution is to propose an efficient geometric embedding method, including the spatial structure representations of drug molecule (converting the 3-D coordinates into image) and the geometric graph representations of protein target (modeling the protein surface as a mesh). The 3-D geometric information is vital to successful molecular generation, which is different from previous molecular generative methods based on 1-D or 2-D. Our model framework generates specific molecules in two phases, by first generating special image with molecular 3-D information to learn latent representations and generating molecules with constrained condition based on geometric graph convolution for specific protein and then inputting the generated structural molecules into a parser network for obtaining Simplified Molecular Input Line Entry System (SMILES) strings. Our model achieves competitive performance that implies its potential effectiveness to enable the exploration of the vast chemical space for drug discovery.

3DMol-Net: Learn 3D Molecular Representation Using Adaptive Graph Convolutional Network Based on Rotation Invariance.

Studying the deep learning-based molecular representation has great significance on predicting molecular property, promoted the development of drug screening and new drug discovery, and improving human well-being for avoiding illnesses. It is essential to learn the characterization of drug for various downstream tasks, such as molecular property prediction. In particular, the 3D structure features of molecules play an important role in biochemical function and activity prediction. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most current methods merely rely on 1D or 2D properties while ignoring the 3D topological structure, thereby degrading the performance of molecular inferring. In this paper, we propose 3DMol-Net to enhance the molecular representation, considering both the topology and rotation invariance (RI) of the 3D molecular structure. Specifically, we construct a molecular graph with soft relations related to the spatial arrangement of the 3D coordinates to learn 3D topology of arbitrary graph structure and employ an adaptive graph convolutional network to predict molecular properties and biochemical activities. Comparing with current graph-based methods, 3DMol-Net demonstrates superior performance in terms of both regression and classification tasks. Further verification of RI and visualization also show better robustness and representation capacity of our model.

GPU-Based Supervoxel Generation With a Novel Anisotropic Metric.

Video over-segmentation into supervoxels is an important pre-processing technique for many computer vision tasks. Videos are an order of magnitude larger than images. Most existing methods for generating supervovels are either memory- or time-inefficient, which limits their application in subsequent video processing tasks. In this paper, we present an anisotropic supervoxel method, which is memory-efficient and can be executed on the graphics processing unit (GPU). Therefore, our algorithm achieves good balance among segmentation quality, memory usage and processing time. In order to provide accurate segmentation for moving objects in video, we use the optical flow information to design a brand new non-Euclidean metric to calculate the anisotropic distances between seeds and voxels. To efficiently compute the anisotropic metric, we adjust the classic jump flooding algorithm (which is designed for parallel execution on the GPU) to generate anisotropic Voronoi tessellation in the combined color and spatio-temporal space. We evaluate our method and the representative supervoxel algorithms for their capability on segmentation performance, computation speed and memory efficiency. We also apply supervoxel results to the application of foreground propagation in videos to test the performance on solving practical problems. Experiments show that our algorithm is much faster than the existing methods, and achieves good balance on segmentation quality and efficiency.

A spatial-temporal gated attention module for molecular property prediction based on molecular geometry.

MOTIVATION: Geometry-based properties and characteristics of drug molecules play an important role in drug development for virtual screening in computational chemistry. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most of the previous studies focused on 1D or 2D molecular descriptors while ignoring the 3D topological structure, thereby degrading the performance of molecule-related prediction. Because it is very time-consuming to use dynamics to simulate molecular 3D conformer, we aim to use machine learning to represent 3D molecules by using the generated 3D molecular coordinates from the 2D structure. RESULTS: We proposed Drug3D-Net, a novel deep neural network architecture based on the spatial geometric structure of molecules for predicting molecular properties. It is grid-based 3D convolutional neural network with spatial-temporal gated attention module, which can extract the geometric features for molecular prediction tasks in the process of convolution. The effectiveness of Drug3D-Net is verified on the public molecular datasets. Compared with other deep learning methods, Drug3D-Net shows superior performance in predicting molecular properties and biochemical activities. AVAILABILITY AND IMPLEMENTATION: https://github.com/anny0316/Drug3D-Net. SUPPLEMENTARY DATA: Supplementary data are available online at https://academic.oup.com/bib.

Comparative Genome and Transcriptome Integration Studies Reveal the Mechanism of Pectoral Muscle Development and Function in Pigeons.

Pigeon breed resources provide a genetic model for the study of phenomics. The pectoral muscles play a key role for the meat production performance of the meat pigeon and the athletic ability of the High flyers. Euro-pigeons and Silver King pigeons are commercial varieties that exhibit good meat production performance. In contrast to the domestication direction of meat pigeons, the traditional Chinese ornamental pigeon breed, High flyers, has a small and light body. Here, we investigate the molecular mechanism of the pectoral muscle development and function of pigeons using whole-genome and RNA sequencing data. The selective sweep analysis (F ST and log2 (θπ ratio)) revealed 293 and 403 positive selection genes in Euro-pigeons and Silver King, respectively, of which 65 genes were shared. With the Silver King and Euro-pigeon as the control group, the High flyers were selected for 427 and 566 genes respectively. There were 673 differentially expressed genes in the breast muscle transcriptome between the commercial meat pigeons and ornamental pigeons. Pigeon genome selection signal combined with the breast muscle transcriptome revealed that six genes (SLC16A10, S100B, SYNE1, HECW2, CASQ2 and LOC110363470) from commercial varieties of pigeons and five genes (INSC, CALCB, ZBTB21, B2M and LOC110356506) from Chinese traditional ornamental pigeons were positively selected which were involved in pathways related to muscle development and function. This study provides new insights into the selection of different directions and the genetic mechanism related to muscle development in pigeons.

Genomic analysis of GBS data reveals genes associated with facial pigmentation in Xinyang blue-shelled layers.

Facial pigmentation is an important economic trait of chickens, especially for laying hens, which will affect the carcass appearance of eliminated layers. Therefore, identifying the genomic regions and exploring the function of this region that contributes to understanding the variation of skin color traits is significant for breeding. In the study, 291 pure-line Xinyang blue-shelled laying hens were selected, of which 75 were dark-faced chickens and 216 were white-faced chickens. The population was sequenced and typed by GBS genotyping technology. The obtained high-quality SNPs and pigmentation phenotypes were analyzed by a genome-wide association study (GWAS) and a F ST scan. Based on the two analytical methods, we identified a same genomic region (10.70-11.60 Mb) on chromosome 20 with 68 significant SNPs ( - log⁡ 10 ( P ) > 6 ), mapped to 10 known genes, including NPEPL1, EDN3, GNAS, C20orf85, VAPB, BMP7, TUBB1, ELMO2, DDX27, and NCOA5, which are associated with dermal hyperpigmentation.

A Novel Computational Model for Predicting microRNA-Disease Associations Based on Heterogeneous Graph Convolutional Networks.

Identifying the interactions between disease and microRNA (miRNA) can accelerate drugs development, individualized diagnosis, and treatment for various human diseases. However, experimental methods are time-consuming and costly. So computational approaches to predict latent miRNA-disease interactions are eliciting increased attention. But most previous studies have mainly focused on designing complicated similarity-based methods to predict latent interactions between miRNAs and diseases. In this study, we propose a novel computational model, termed heterogeneous graph convolutional network for miRNA-disease associations (HGCNMDA), which is based on known human protein-protein interaction (PPI) and integrates four biological networks: miRNA-disease, miRNA-gene, disease-gene, and PPI network. HGCNMDA achieved reliable performance using leave-one-out cross-validation (LOOCV). HGCNMDA is then compared to three state-of-the-art algorithms based on five-fold cross-validation. HGCNMDA achieves an AUC of 0.9626 and an average precision of 0.9660, respectively, which is ahead of other competitive algorithms. We further analyze the top-10 unknown interactions between miRNA and disease. In summary, HGCNMDA is a useful computational model for predicting miRNA-disease interactions.

Enhanced Expression of Serotonin Receptor 5-Hydroxytryptamine 2C is Associated with Increased Feather Damage in Dongxiang Blue-Shelled Layers.

The gene encoding the serotonin receptor 5-hydroxytraptamine 2C (HTR2C) has been implicated in behavioral phenotypes in a number of species. In previous studies, a mutation in the chicken HTR2C gene was found to be associated with feather condition, thereby suggesting a relationship between the gene and receiving feather pecking activity. The present study analyzed the chicken HTR2C gene at both the genomic make-up and expression level in Dongxiang blue-shelled layer. A significant association between the single nucleotide polymorphism (SNP) rs13640917 (C/T) and feather condition was confirmed in the Chinese local layer. Enhanced HTR2C gene expression (151.1-fold) that was associated with high feather damage indicated that the right cerebrum might be the critical region for HTR2C to participate in the regulation of receiving feather pecking behavior.

3D vasculature segmentation using localized hybrid level-set method.

BACKGROUND: Intensity inhomogeneity occurs in many medical images, especially in vessel images. Overcoming the difficulty due to image inhomogeneity is crucial for the segmentation of vessel image. METHODS: This paper proposes a localized hybrid level-set method for the segmentation of 3D vessel image. The proposed method integrates both local region information and boundary information for vessel segmentation, which is essential for the accurate extraction of tiny vessel structures. The local intensity information is firstly embedded into a region-based contour model, and then incorporated into the level-set formulation of the geodesic active contour model. Compared with the preset global threshold based method, the use of automatically calculated local thresholds enables the extraction of the local image information, which is essential for the segmentation of vessel images. RESULTS: Experiments carried out on the segmentation of 3D vessel images demonstrate the strengths of using locally specified dynamic thresholds in our level-set method. Furthermore, both qualitative comparison and quantitative validations have been performed to evaluate the effectiveness of our proposed model. CONCLUSIONS: Experimental results and validations demonstrate that our proposed model can achieve more promising segmentation results than the original hybrid method does.