Exosomes secreted from bone marrow mesenchymal stem cells suppress cardiomyocyte hypertrophy through Hippo-YAP pathway in heart failure.

Mesenchymal stem cells-derived exosomes (MSCs-exosomes) reportedly possess cardioprotective effects. This study investigated the therapeutic potential and mechanisms of MSCs-exosomes on heart failure (HF). H9c2 cells were used to establish a cardiomyocyte hypertrophy model by angiotensin II (Ang II) treatment. Isolated MSCs-exosomes were identified by transmission electron microscope and CD63 detection. Apoptosis rate was measured by terminal deoxynucleotidyl transferase (TdT) dUTP Nick-End Labeling (TUNEL) assay. Levels of inflammatory factors [interleukin (IL)-1ß, IL-4, IL-6, and tumor necrosis factor (TNF)-α] and brain natriuretic peptide (BNP) were determined by ELISA. Expression of apoptosis-related proteins [Bax, B-cell lymphoma-2 (Bcl-2), and caspase 3] and Hippo-Yes-associated protein (YAP) pathway-related proteins [YAP, phosphor (p)-YAP, and tafazzin (TAZ)] was detected by western blotting. Cardiomyocyte hypertrophy of H9c2 cells induced by Ang II was ameliorated by MSCs-exosomes treatment. MSCs-exosomes downregulated Bax and caspase 3 levels and upregulated Bcl-2 level in Ang II-induced H9c2 cells. MSCs-exosomes also reduced the levels of BNP, IL-1ß, IL-4, IL-6, and TNF-α in Ang II-induced H9c2 cells. Meanwhile, p-YAP was downregulated and TAZ was upregulated after MSCs-exosomes administration. In conclusion, MSCs-exosomes alleviate the apoptosis and inflammatory response of cardiomyocyte via deactivating Hippo-YAP pathway in HF.

[Heart sound classification algorithm based on time-frequency combination feature and adaptive fuzzy neural network].

Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100-300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm's significant potential for aiding in the diagnosis of congenital heart disease.

Automatic diagnosis of COVID-19 infection based on ontology reasoning.

BACKGROUND: 2019-nCoV has been spreading around the world and becoming a global concern. To prevent further widespread of 2019-nCoV, confirmed and suspected cases of COVID-19 infection are suggested to be kept in quarantine. However, the diagnose of COVID-19 infection is quite time-consuming and labor-intensive. To alleviate the burden on the medical staff, we have done some research on the intelligent diagnosis of COVID-19. METHODS: In this paper, we constructed a COVID-19 Diagnosis Ontology (CDO) by utilizing Protégé, which includes the basic knowledge graph of COVID-19 as well as diagnostic rules translated from Chinese government documents. Besides, SWRL rules were added into the ontology to infer intimate relationships between people, thus facilitating the efficient diagnosis of the suspected cases of COVID-19 infection. We downloaded real-case data and extracted patients' syndromes from the descriptive text, so as to verify the accuracy of this experiment. RESULTS: After importing those real instances into Protégé, we demonstrated that the COVID-19 Diagnosis Ontology showed good performances to diagnose cases of COVID-19 infection automatically. CONCLUSIONS: In conclusion, the COVID-19 Diagnosis Ontology will not only significantly reduce the manual input in the diagnosis process of COVID-19, but also uncover hidden cases and help prevent the widespread of this epidemic.

Long noncoding RNA GAS5 ameliorates chronic constriction injury induced neuropathic pain in rats by modulation of the miR-452-5p/CELF2 axis.

Neuropathic pain is a type of spontaneous pain that causes damage to the central nervous system. Long noncoding RNAs (lncRNAs) participate in the progression of various nervous system diseases, including neuropathic pain. However, the biological function of GAS5 in neuropathic pain remains unclear. Our findings revealed that GAS5 was downregulated in chronic constriction injury (CCI) rats. Besides, ELISA showed that the concentration of IL-6, TNF-α, and IL-1ß were reduced by overexpressed GAS5 in spinal cord homogenates of CCI rats. Moreover, mechanical allodynia and thermal hyperalgesia in CCI rats were inhibited by GAS5 overexpression, suggesting that GAS5 overexpression attenuated neuropathic pain. Subsequently, we found that GAS5 served as a sponge for miR-452-5p in CCI rats and CELF2 was the downstream target of miR-452-5p. Finally, through a rescue assay, we found that GAS5 ameliorated neuropathic pain in CCI rats by sponging miR-452-5p to regulate CELF2 expression. Our study confirmed that GAS5 ameliorated neuropathic pain in rats by modulation of the miR-452-5p/CELF2 axis, which may provide some clues for neuropathic pain treatment.

[Relationship between rs2282679 gene locus polymorphism and vitamin D deficiency in college students].

OBJECTIVE: To investigate the relationship between vitamin D binding protein gene rs2282679 A/C polymorphism with blood vitamin D levels. METHODS: A total of 286 eligible subjects were selected from one university in Hebei Province. Serum 25-hydroxylated vitamin D levels were measured by liquid chromatography-mass spectrometry, and gene chip was used for genotyping of rs2282679 locus. Statistical analysis was performed using R software. RESULTS: A total of 285 participants in the study completed the experiment, and result indicated that the distribution of the rs2282679 locus A/C polymorphism in the participants was consistent with the Hardy-Weinberg equilibrium. The genotype of rs2282679 was significantly associated with serum vitamin D insufficiency and deficiency(P=0. 031). Allele A was a risk factor for vitamin D insufficiency and deficiency. The OR value of allele C relative to A was 0. 65, and the genetic pattern of allele C relative to A was dominant(P=0. 03). CONCLUSION: The vitamin D-binding protein gene rs2282679 was significantly associated with serum vitamin D insufficiency and deficiency in college students, and A-allele is a risk factor accounting for vitamin D insufficiency and deficiency in college students.

Prediction of posttranslational modification sites from amino acid sequences with kernel methods.

Post-translational modification (PTM) is the chemical modification of a protein after its translation and one of the later steps in protein biosynthesis for many proteins. It plays an important role which modifies the end product of gene expression and contributes to biological processes and diseased conditions. However, the experimental methods for identifying PTM sites are both costly and time-consuming. Hence computational methods are highly desired. In this work, a novel encoding method PSPM (position-specific propensity matrices) is developed. Then a support vector machine (SVM) with the kernel matrix computed by PSPM is applied to predict the PTM sites. The experimental results indicate that the performance of new method is better or comparable with the existing methods. Therefore, the new method is a useful computational resource for the identification of PTM sites. A unified standalone software PTMPred is developed. It can be used to predict all types of PTM sites if the user provides the training datasets. The software can be freely downloaded from http://www.aporc.org/doc/wiki/PTMPred.

ComCo: Complementary supervised contrastive learning for complementary label learning.

Complementary label learning (CLL) is an important problem that aims to reduce the cost of obtaining large-scale accurate datasets by only allowing each training sample to be equipped with labels the sample does not belong. Despite its promise, CLL remains a challenging task. Previous methods have proposed new loss functions or introduced deep learning-based models to CLL, but they mostly overlook the semantic information that may be implicit in the complementary labels. In this work, we propose a novel method, ComCo, which leverages a contrastive learning framework to assist CLL. Our method includes two key strategies: a positive selection strategy that identifies reliable positive samples and a negative selection strategy that skillfully integrates and leverages the information in the complementary labels to construct a negative set. These strategies bring ComCo closer to supervised contrastive learning. Empirically, ComCo significantly achieves better representation learning and outperforms the baseline models and the current state-of-the-art by up to 14.61% in CLL.

Decoupled graph knowledge distillation: A general logits-based method for learning MLPs on graphs.

While Graph Neural Networks (GNNs) have demonstrated their effectiveness in processing non-Euclidean structured data, the neighborhood fetching of GNNs is time-consuming and computationally intensive, making them difficult to deploy in low-latency industrial applications. To address the issue, a feasible solution is graph knowledge distillation (KD), which can learn high-performance student Multi-layer Perceptrons (MLPs) to replace GNNs by mimicking the superior output of teacher GNNs. However, state-of-the-art graph knowledge distillation methods are mainly based on distilling deep features from intermediate hidden layers, this leads to the significance of logit layer distillation being greatly overlooked. To provide a novel viewpoint for studying logits-based KD methods, we introduce the idea of decoupling into graph knowledge distillation. Specifically, we first reformulate the classical graph knowledge distillation loss into two parts, i.e., the target class graph distillation (TCGD) loss and the non-target class graph distillation (NCGD) loss. Next, we decouple the negative correlation between GNN's prediction confidence and NCGD loss, as well as eliminate the fixed weight between TCGD and NCGD. We named this logits-based method Decoupled Graph Knowledge Distillation (DGKD). It can flexibly adjust the weights of TCGD and NCGD for different data samples, thereby improving the prediction accuracy of the student MLP. Extensive experiments conducted on public benchmark datasets show the effectiveness of our method. Additionally, DGKD can be incorporated into any existing graph knowledge distillation framework as a plug-and-play loss function, further improving distillation performance. The code is available at https://github.com/xsk160/DGKD.

Generalized robust loss functions for machine learning.

Loss function is a critical component of machine learning. Some robust loss functions are proposed to mitigate the adverse effects caused by noise. However, they still face many challenges. Firstly, there is currently a lack of unified frameworks for building robust loss functions in machine learning. Secondly, most of them only care about the occurring noise and pay little attention to those normal points. Thirdly, the resulting performance gain is limited. To this end, we put forward a general framework of robust loss functions for machine learning (RML) with rigorous theoretical analyses, which can smoothly and adaptively flatten any unbounded loss function and apply to various machine learning problems. In RML, an unbounded loss function serves as the target, with the aim of being flattened. A scale parameter is utilized to limit the maximum value of noise points, while a shape parameter is introduced to control both the compactness and the growth rate of the flattened loss function. Later, this framework is employed to flatten the Hinge loss function and the Square loss function. Based on this, we build two robust kernel classifiers called FHSVM and FLSSVM, which can distinguish different types of data. The stochastic variance reduced gradient (SVRG) approach is used to optimize FHSVM and FLSSVM. Extensive experiments demonstrate their superiority, with both consistently occupying the top two positions among all evaluated methods, achieving an average accuracy of 81.07% (accompanied by an F-score of 73.25%) for FHSVM and 81.54% (with an F-score of 75.71%) for FLSSVM.

Probiotics combined with atorvastatin administration in the treatment of hyperlipidemia: A randomized, double-blind, placebo-controlled clinical trial.

BACKGROUND: Hyperlipidemia is a common feature of chronic diseases. The aim of this work was designed to assess the role of probiotics (Lactobacillus casei Zhang, Bifidobactetium animalis subsp. lactis V9, and Lactobacillus plantarum P-8) in the treatment of hyperlipidemia. METHODS: Thirty three patients with hyperlipidemia were randomly divided into a probiotic group (n = 18) and a control group (n = 15). The probiotic group was administered probiotics (2 g once daily) and atorvastatin 20 mg (once daily), and the control group was administered a placebo (2 g once daily) and atorvastatin 20 mg (once daily). Serum and fecal samples were gathered for subsequent analyses. RESULTS: Time had a significant effect on the total cholesterol (TC), triglycerides (TG), and low-density lipoprotein-cholesterol (LDL-C) levels in the probiotic and control groups (P < .05). The gut microbial abundance in the probiotic group was markedly higher than that in the control group following 3-month probiotic treatment (P < .05). At the phylum level, probiotics exerted no notable effects on the relative abundance of Firmicutes, Bacteroidetes, and Actinobacteria but elevated that of Tenericutes and reduced Proteobacteria. At the genus level, probiotics increased the relative abundance of Bifidobacterium, Lactobacillus, and Akkermansia, and decreased that of Escherichia, Eggerthella, and Sutterella relative to the control group in months 1, 2, and 3 (P < .05). CONCLUSIONS: Probiotics optimize the gut microbiota structure and decrease the amount of harmful bacteria in patients with hyperlipidemia. Probiotics can influence the composition of gut microorganisms and increase their diversity and abundance in vivo. It is recommended to use probiotics combined with atorvastatin to treat patients with hyperlipidemia.

End-to-End Multitask Learning With Vision Transformer.

Multitask learning (MTL) is a challenging puzzle, particularly in the realm of computer vision (CV). Setting up vanilla deep MTL requires either hard or soft parameter sharing schemes that employ greedy search to find the optimal network designs. Despite its widespread application, the performance of MTL models is vulnerable to under-constrained parameters. In this article, we draw on the recent success of vision transformer (ViT) to propose a multitask representation learning method called multitask ViT (MTViT), which proposes a multiple branch transformer to sequentially process the image patches (i.e., tokens in transformer) that are associated with various tasks. Through the proposed cross-task attention (CA) module, a task token from each task branch is regarded as a query for exchanging information with other task branches. In contrast to prior models, our proposed method extracts intrinsic features using the built-in self-attention mechanism of the ViT and requires just linear time on memory and computation complexity, rather than quadratic time. Comprehensive experiments are carried out on two benchmark datasets, including NYU-Depth V2 (NYUDv2) and CityScapes, after which it is found that our proposed MTViT outperforms or is on par with existing convolutional neural network (CNN)-based MTL methods. In addition, we apply our method to a synthetic dataset in which task relatedness is controlled. Surprisingly, experimental results reveal that the MTViT exhibits excellent performance when tasks are less related.

Partial label learning: Taxonomy, analysis and outlook.

Partial label learning (PLL) is an emerging framework in weakly supervised machine learning with broad application prospects. It handles the case in which each training example corresponds to a candidate label set and only one label concealed in the set is the ground-truth label. In this paper, we propose a novel taxonomy framework for PLL including four categories: disambiguation strategy, transformation strategy, theory-oriented strategy and extensions. We analyze and evaluate methods in each category and sort out synthetic and real-world PLL datasets which are all hyperlinked to the source data. Future work of PLL is profoundly discussed in this article based on the proposed taxonomy framework.

CSAST: Content self-supervised and style contrastive learning for arbitrary style transfer.

Arbitrary artistic style transfer has achieved great success with deep neural networks, but it is still difficult for existing methods to tackle the dilemma of content preservation and style translation due to the inherent content-and-style conflict. In this paper, we introduce content self-supervised learning and style contrastive learning to arbitrary style transfer for improved content preservation and style translation, respectively. The former one is based on the assumption that stylization of a geometrically transformed image is perceptually similar to applying the same transformation to the stylized result of the original image. This content self-supervised constraint noticeably improves content consistency before and after style translation, and contributes to reducing noises and artifacts as well. Furthermore, it is especially suitable to video style transfer, due to its ability to promote inter-frame continuity, which is of crucial importance to visual stability of video sequences. For the latter one, we construct a contrastive learning that pull close style representations (Gram matrices) of the same style and push away that of different styles. This brings more accurate style translation and more appealing visual effect. A large number of qualitative and quantitative experiments demonstrate superiority of our method in improving arbitrary style transfer quality, both for images and videos.

A simple and reliable instance selection for fast training support vector machine: Valid Border Recognition.

Support vector machines (SVMs) are powerful statistical learning tools, but their application to large datasets can cause time-consuming training complexity. To address this issue, various instance selection (IS) approaches have been proposed, which choose a small fraction of critical instances and screen out others before training. However, existing methods have not been able to balance accuracy and efficiency well. Some methods miss critical instances, while others use complicated selection schemes that require even more execution time than training with all original instances, thus violating the initial intention of IS. In this work, we present a newly developed IS method called Valid Border Recognition (VBR). VBR selects the closest heterogeneous neighbors as valid border instances and incorporates this process into the creation of a reduced Gaussian kernel matrix, thus minimizing the execution time. To improve reliability, we propose a strengthened version of VBR (SVBR). Based on VBR, SVBR gradually adds farther heterogeneous neighbors as complements until the Lagrange multipliers of already selected instances become stable. In numerical experiments, the effectiveness of our proposed methods is verified on benchmark and synthetic datasets in terms of accuracy, execution time and inference time.

Causal multi-label learning for image classification.

In this paper, we investigate the problem of causal image classification with multi-label learning. As multi-label learning involves a diversity of supervision signals, it is considered a challenging issue to solve. Previous approaches have attempted to improve performance by identifying label-related image areas or exploiting the co-occurrence of labels. However, these methods are often characterized by complicated procedures, tedious computations, and a lack of intuitive interpretations. To overcome these limitations, we propose a novel approach that incorporates the concept of causal inference, which has been shown to be beneficial in other computer vision problems. Our method, called causal multi-label learning (CMLL), enables the selection of multiple objects from the original image through a multi-class attention module. These objects are then subjected to causal intervention to learn the causal relationships between different labels. Our proposed approach is both elegant and effective, with low computational cost and few parameters required for the multi-class causal intervention approach. Extensive tests and ablation studies demonstrate that the proposed method significantly improves prediction performance without a significant increase in training and inference times.

Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function.

Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function appears to solve this puzzle once and for all. In this article, we propose a pixel-based adaptive weighted cross-entropy (WCE) loss in conjunction with Jaccard distance to facilitate high-quality pixel-level road crack detection. Our work profoundly demonstrates the influence of loss functions on detection outcomes and sheds light on the sophisticated consecutive improvements in the realm of crack detection. Specifically, to verify the effectiveness of the proposed loss, we conduct extensive experiments on four public databases, that is, CrackForest, AigleRN, Crack360, and BJN260. Compared to the vanilla WCE, the proposed loss significantly speeds up the training process while retaining the performance.

SMOC2 plays a role in heart failure via regulating TGF-ß1/Smad3 pathway-mediated autophagy.

Heart failure (HF) is a major global cause of morbidity and mortality. This study aimed to elucidate the role of secreted protein acidic and rich in cysteine-related modular calcium-binding protein 2 (SMOC2) in HF development and its underlying mechanism. Using a rat HF model, SMOC2 expression was examined and then knocked down via transfection to assess its impact on cardiac function and damage. The study also evaluated the effects of SMOC2 knockdown on autophagy-related molecules and the transforming growth factor beta 1 (TGF-ß1)/SMAD family member 3 (Smad3) signaling pathway. Intraperitoneal injection of the TGF-ß agonist (SRI-011381) into the HF rat model was performed to explore the SMOC2-TGF-ß1/Smad3 pathway relationship. SMOC2 expression was elevated in HF rats, while its downregulation improved cardiac function and damage. SMOC2 knockdown reversed alterations in the LC3-II/I ratio, Beclin-1, and p62 levels in HF rats. Through transmission electron microscope, we observed that SMOC2 knockdown restored autophagosome levels. Furthermore, SMOC2 downregulation inhibited the TGF-ß1/Smad3 signaling pathway, which was counteracted by SRI-011381. In conclusion, SMOC2 knockdown inhibits HF development by modulating TGF-ß1/Smad3 signaling-mediated autophagy, suggesting its potential as a therapeutic target for HF.

Linear-exponential loss incorporated deep learning for imbalanced classification.

The class imbalance issue is a pretty common and enduring topic all the time. When encountering unbalanced data distribution, conventional methods are prone to classify minority samples as majority ones, which may cause severe consequences in reality. It is crucial yet challenging to cope with such problems. In this paper, inspired by our previous work, we borrow the linear-exponential (LINEX) loss function in statistics into deep learning for the first time and extend it into a multi-class form, denoted as DLINEX. Compared with existing loss functions in class imbalance learning (e.g., the weighted cross entropy-loss and the focal loss), DLINEX has an asymmetric geometry interpretation, which can adaptively focus more on the minority and hard-to-classify samples by solely adjusting one parameter. Besides, it simultaneously achieves between and within class diversities via caring about the inherent properties of each instance. As a result, DLINEX achieves 42.08% G-means on the CIFAR-10 dataset at the imbalance ratio of 200, 79.06% G-means on the HAM10000 dataset, 82.74% F1 on the DRIVE dataset, 83.93% F1 on the CHASEDB1 dataset and 79.55% F1 on the STARE dataset The quantitative and qualitative experiments convincingly demonstrate that DLINEX can work favorably in imbalanced classifications, either at the image-level or the pixel-level.

GAN-CL: Generative Adversarial Networks for Learning From Complementary Labels.

Learning from complementary labels (CLs) is a useful learning paradigm, where the CL specifies the classes that the instance does not belong to, instead of providing the ground truth as in the ordinary supervised learning scenario. In general, although it is less laborious and more efficient to collect CLs compared with ordinary labels, the less informative signal in the complementary supervision is less helpful to learn competent feature representation. Consequently, the final classifier's performance greatly deteriorates. In this article, we leverage generative adversarial networks (GANs) to derive an algorithm GAN-CL to effectively learn from CLs. In addition to the role in original GAN, the discriminator also serves as a normal classifier in GAN-CL, with the objective constructed partly with the complementary information. To further prove the effectiveness of our schema, we study the global optimality of both generator and discriminator for the GAN-CL under mild assumptions. We conduct extensive experiments on benchmark image datasets using deep models, to demonstrate the compelling improvements, compared with state-of-the-art CL learning approaches.

LLP-GAN: A GAN-Based Algorithm for Learning From Label Proportions.

Learning from label proportions (LLP) is a widespread and important learning paradigm: only the bag-level proportional information of the grouped training instances is available for the classification task, instead of the instance-level labels in the fully supervised scenario. As a result, LLP is a typical weakly supervised learning protocol and commonly exists in privacy protection circumstances due to the sensitivity in label information for real-world applications. In general, it is less laborious and more efficient to collect label proportions as the bag-level supervised information than the instance-level one. However, the hint for learning the discriminative feature representation is also limited as a less informative signal directly associated with the labels is provided, thus deteriorating the performance of the final instance-level classifier. In this article, delving into the label proportions, we bypass this weak supervision by leveraging generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN. Endowed with an end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism without imposing restricted assumptions on distribution. Accordingly, the final instance-level classifier can be directly induced upon the discriminator with minor modification. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. In addition, compared with existing methods, our work empowers LLP solvers with desirable scalability inheriting from deep models. Extensive experiments on benchmark datasets and a real-world application demonstrate the vivid advantages of the proposed approach.