Prediction of miRNA-Disease Associations by Cascade Forest Model Based on Stacked Autoencoder.

Numerous pieces of evidence have indicated that microRNA (miRNA) plays a crucial role in a series of significant biological processes and is closely related to complex disease. However, the traditional biological experimental methods used to verify disease-related miRNAs are inefficient and expensive. Thus, it is necessary to design some excellent approaches to improve efficiency. In this work, a novel method (CFSAEMDA) is proposed for the prediction of unknown miRNA-disease associations (MDAs). Specifically, we first capture the interactive features of miRNA and disease by integrating multi-source information. Then, the stacked autoencoder is applied for obtaining the underlying feature representation. Finally, the modified cascade forest model is employed to complete the final prediction. The experimental results present that the AUC value obtained by our method is 97.67%. The performance of CFSAEMDA is superior to several of the latest methods. In addition, case studies conducted on lung neoplasms, breast neoplasms and hepatocellular carcinoma further show that the CFSAEMDA method may be regarded as a utility approach to infer unknown disease-miRNA relationships.

A feature selection method based on graph theory for cancer classification.

OBJECTIVE: Gene expression profile data is a good data source for people to study tumors, but gene expression data has the characteristics of high dimension and redundancy. Therefore, gene selection is a very important step in microarray data classification. METHOD: In this paper, a feature selection method based on the maximum mutual information coefficient and graph theory is proposed. Each feature of gene expression data is treated as a vertex of the graph, and the maximum mutual information coefficient between genes is used to measure the relationship between the vertices to construct an undirected graph, and then the core and coritivity theory is used to determine the feature subset of gene data. RESULTS: In this work, we used three different classification models and three different evaluation metrics such as accuracy, F1-Score, and AUC to evaluate the classification performance to avoid reliance on any one classifier or evaluation metric. The experimental results on six different types of genetic data show that our proposed algorithm has high accuracy and robustness compared to other advanced feature selection methods. CONCLUSION: In this method, the importance and correlation of features are considered at the same time, and the problem of gene selection in microarray data classification is solved.

Clinical types and fungal pathogens of children′s tinea capitis analysis of 542 cases in a tertiary first-class hospital of Wuhan / 中国热带医学

@#Abstract: Objective To investigate the clinical types of children's tinea capitis and the distribution of fungal pathogens in Wuhan from 2011 to 2020, and to provide scientific basis for the prevention, diagnosis and treatment of children's tinea capitis. Methods Laboratory data of children with tinea capitis in outpatient and inpatient department of dermatology in Wuhan No.1 Hospital from January 2011 to December 2020 were collected. A total of 542 cases of pediatric tinea capitis were included, with 239 male cases and 303 female cases. Microscopic examination of fungi and culture identification were performed on the affected skin lesions of the children. Chi-square test was used to analyze the differences in pathogen spectrum of children with different age groups and clinical type. Results Among the pediatric tinea capitis patients, the age group with the highest prevalence was preschool children（3 to <7 years old), accounting for 48.52%（263/542). The top three pathogenic fungi were Trichophytes violaceum（49.26%, 267/542), Microsporum canis（31.55%, 171/542) and Trichophyton mentagrophytes （9.96%, 54/542). Trichophyton violaceum was the main pathogen in all ages, followed by Microsporum canis. The infection rate of Microsporum canis in children over 7 years old was lower than that in children under 7 years old, and the infection rate of Trichophyton rubrum in infants was higher than that in other ages. The distribution of Trichophytes violaceum, Trichophyton mentagrophytes, Nannizzia gypseum and Microsporum ferrugineum was uniform in all age groups. Trichophytes violaceum and Trichophyton tousurans mainly caused black-dot ringworm, Microsporum canis mainly caused tinea alba, Trichophyton mentagrophytes,Nannizzia gypseum and Trichophytonrubrum mainly caused kerion. Except for Microsporum ferrugineum, the composition ratios of other fungi species showed statistically significant differences among different clinical types of tinea capitis（P<0.05). Conclusions Preschool children are the most commonly affected age group by pediatric tinea capitis, and black-dot ringworm caused by Trichophytes violaceum is the main clinical type. Analysis of the high-riskage group, pathogenic fungi and clinical types of tinea capitis in children can enhance the understanding of its epidemiological characteristics, which is helpful for early diagnosis and targeted standardized treatment of pediatric tinea capitis.

Cascade Forest-Based Model for Prediction of RNA Velocity.

In recent years, single-cell RNA sequencing technology (scRNA-seq) has developed rapidly and has been widely used in biological and medical research, such as in expression heterogeneity and transcriptome dynamics of single cells. The investigation of RNA velocity is a new topic in the study of cellular dynamics using single-cell RNA sequencing data. It can recover directional dynamic information from single-cell transcriptomics by linking measurements to the underlying dynamics of gene expression. Predicting the RNA velocity vector of each cell based on its gene expression data and formulating RNA velocity prediction as a classification problem is a new research direction. In this paper, we develop a cascade forest model to predict RNA velocity. Compared with other popular ensemble classifiers, such as XGBoost, RandomForest, LightGBM, NGBoost, and TabNet, it performs better in predicting RNA velocity. This paper provides guidance for researchers in selecting and applying appropriate classification tools in their analytical work and suggests some possible directions for future improvement of classification tools.

Deep Colormap Extraction From Visualizations.

This article presents a new approach based on deep learning to automatically extract colormaps from visualizations. After summarizing colors in an input visualization image as a Lab color histogram, we pass the histogram to a pre-trained deep neural network, which learns to predict the colormap that produces the visualization. To train the network, we create a new dataset of  âˆ¼ 64K visualizations that cover a wide variety of data distributions, chart types, and colormaps. The network adopts an atrous spatial pyramid pooling module to capture color features at multiple scales in the input color histograms. We then classify the predicted colormap as discrete or continuous, and refine the predicted colormap based on its color histogram. Quantitative comparisons to existing methods show the superior performance of our approach on both synthetic and real-world visualizations. We further demonstrate the utility of our method with two use cases, i.e., color transfer and color remapping.

LGBMDF: A cascade forest framework with LightGBM for predicting drug-target interactions.

Prediction of drug-target interactions (DTIs) plays an important role in drug development. However, traditional laboratory methods to determine DTIs require a lot of time and capital costs. In recent years, many studies have shown that using machine learning methods to predict DTIs can speed up the drug development process and reduce capital costs. An excellent DTI prediction method should have both high prediction accuracy and low computational cost. In this study, we noticed that the previous research based on deep forests used XGBoost as the estimator in the cascade, we applied LightGBM instead of XGBoost to the cascade forest as the estimator, then the estimator group was determined experimentally as three LightGBMs and three ExtraTrees, this new model is called LGBMDF. We conducted 5-fold cross-validation on LGBMDF and other state-of-the-art methods using the same dataset, and compared their Sn, Sp, MCC, AUC and AUPR. Finally, we found that our method has better performance and faster calculation speed.

Deep Recognition of Vanishing-Point-Constrained Building Planes in Urban Street Views.

This paper presents a new approach to recognizing vanishing-point-constrained building planes from a single image of street view. We first design a novel convolutional neural network (CNN) architecture that generates geometric segmentation of per-pixel orientations from a single street-view image. The network combines two-stream features of general visual cues and surface normals in gated convolution layers, and employs a deeply supervised loss that encapsulates multi-scale convolutional features. Our experiments on a new benchmark with fine-grained plane segmentations of real-world street views show that our network outperforms state-of-the-arts methods of both semantic and geometric segmentation. The pixel-wise segmentation exhibits coarse boundaries and discontinuities. We then propose to rectify the pixel-wise segmentation into perspectively-projected quads based on spatial proximity between the segmentation masks and exterior line segments detected through an image processing. We demonstrate how the results can be utilized to perspectively overlay images and icons on building planes in input photos, and provide visual cues for various applications.

Preliminary treatment of bovine mastitis caused by Staphylococcus aureus, with trx-SA1, recombinant endolysin of S. aureus bacteriophage IME-SA1.

Methicillin-resistant Staphylococcus aureus (MRSA) has become a great threat to human and animal health and there is an urgent need to develop novel antibacterial agents to control this pathogen. The objective of this study was to obtain an active recombinant endolysin from the novel bacteriophage (IME-SA1), and conduct an efficacy trial of its effectiveness against bovine mastitis. We isolated a phage that was virulent and specific for S. aureus with an optimal multiplicity of infection of 0.01. Electron microscopy revealed that IME-SA1 was a member of the family Myoviridae, with an isometric head (98nm) and a long contractile tail (200nm). Experimental lysis experiments indicated the phage had an incubation period of 20min with a burst size of 80. When host bacteria were in early exponential growth stages, a multiplicity of infection of 0.01 resulted in a complete bacterial lysis after 9h. The endolysin gene (804bp) was cloned into the pET-32a bacterial expression vector and recombinant endolysin Trx-SA1 was successfully obtained with molecular size of about 47kDa. Preliminary results of therapeutic trials in cow udders showed that Trx-SA1 could effectively control mild clinical mastitis caused by S. aureus. The endolysin Trx-SA1 might be an alternative treatment strategy for infections caused by S. aureus, including MRSA.

Association between polymorphisms in the flanking region of the TAFI gene and atherosclerotic cerebral infarction in a Chinese population.

BACKGROUND: Atherosclerosis is the leading etiologic factor of Atherosclerotic Cerebral Infarction (ACI). Previous studies have shown that thrombin activatable fibrinolysis inhibitor (TAFI) may play an important role in the occurrence of acute cerebral infarction, and the levels of TAFI are affected by several single nucleotide polymorphisms (SNPs) located in the regulatory and coding regions of the gene encoding TAFI. The present study aimed to determine whether polymorphisms (TAFI -2345 2G/1G, -1690 A/G, -438 A/G, +1583 A/T) of the TAFI gene were associated with ACI in a Han Chinese population. METHODS: The variant genotypes were identified by restriction fragment length polymorphism (RFLP) and allele-specific polymerase chain reactions (AS-PCR) in 225 patients with ACI and 184 age-matched healthy individuals. RESULTS: There was a significant difference in the genotype and allele frequencies of TAFI -2345 2G/1G and -1690 A/G polymorphisms between the ACI and control subjects. Further stratification analysis by gender revealed that the presence of the -438 AA genotype and the A allele conferred a higher risk of developing ACI in male patients (p < 0.05). Haplotype analysis demonstrated that four haplotypes of TAFI are significantly associated with ACI. CONCLUSIONS: Our study provides preliminary evidence that the TAFI -2345 2G/1G and -1690 A/G polymorphisms are associated with ACI susceptibility in a Han Chinese population.

Progesterone suppresses Th17 cell responses, and enhances the development of regulatory T cells, through thymic stromal lymphopoietin-dependent mechanisms in experimental gonococcal genital tract infection.

In most female patients, the symptoms of genital infection due to Neisseria gonorrhoeae tend to be slight or even absent. Our previous studies suggested that progesterone might play a role in female asymptomatic gonococcal infection. In this study, we demonstrated that progesterone induced the expression of thymic stromal lymphopoietin (TSLP) and regulatory T cells (Treg)-related transcription factor Foxp3, and inhibited the expression of Th17 related transcription factor RORγt, and reduced the influx of neutrophils in murine vaginal gonococcal infection. Blockade of TSLP with antibody partially reversed the effects of progesterone on the murine model of gonococcal vaginal infection. In in vitro experiments, progesterone induced a rapid up-regulation of TSLP in vaginal epithelial cells stimulated with N. gonorrhoeae. Blocking thymic stromal lymphopoietin receptor (TSLPR) with a TSLPR monoclonal antibody partially prevented progesterone suppression of IL-17-producing T cells differentiation, and progesterone promotion of CD4⁺CD25⁺Foxp3⁺ regulatory T cells differentiation. Altogether, our results indicate that the progesterone suppresses Th17 cell responses, and enhances the development of Treg cells, through TSLP-dependent mechanisms, and play a role in female asymptomatic gonococcal infections.

Complete genome sequence of novel porcine epidemic diarrhea virus strain GD-1 in China.

Porcine epidemic diarrhea virus (PEDV) infection, which causes acute diarrhea and dehydration in suckling piglets, has become a serious problem for the swine industry of China in recent years. In this study, a virulent PEDV strain, GD-1, was obtained from fecal samples from suckling piglets that suffered from severe diarrhea in 2011 in Guangdong, China. Here we describe the complete genome sequence of strain GD-1, which may be helpful in further understanding the molecular epidemiology and genetic diversity of PEDV field isolates in China.