Drugs are an important way to treat various diseases. However, they inevitably produce side effects, bringing great risks to human bodies and pharmaceutical companies. How to predict the side effects of drugs has become one of the essential problems in drug research. Designing efficient computational methods is an alternative way. Some studies paired the drug and side effect as a sample, thereby modeling the problem as a binary classification problem. However, the selection of negative samples is a key problem in this case. In this study, a novel negative sample selection strategy was designed for accessing high-quality negative samples. Such strategy applied the random walk with restart (RWR) algorithm on a chemical-chemical interaction network to select pairs of drugs and side effects, such that drugs were less likely to have corresponding side effects, as negative samples. Through several tests with a fixed feature extraction scheme and different machine-learning algorithms, models with selected negative samples produced high performance. The best model even yielded nearly perfect performance. These models had much higher performance than those without such strategy or with another selection strategy. Furthermore, it is not necessary to consider the balance of positive and negative samples under such a strategy.
Membrane protein is an important type of proteins and has been confirmed to play essential roles in various cellular processes. Based on their intramolecular arrangements and positions in a cell, they can be categorized into several types. However, it is time-and cost-consuming to recognize the type of a given membrane protein via traditional biophysical methods. In view of this, several computational models have been proposed in recent years. Most models adopted various information of membrane proteins, such as their sequences, domain profiles, physiochemical properties, etc. to extract different features, which were fed into downstream classification algorithms. In this study, we built two novel prediction models, which incorporated novel feature extraction methods, i.e., network embedding methods. To this end, several protein networks were constructed using the protein-protein interaction information retrieved from STRING. Among these models, one model was constructed based on features obtained by applying Mashup on seven protein networks, another model was built using features yielded by Node2Vec on one comprehensive protein network. Each model adopted random forest as the classification algorithm and employed the Synthetic Minority Over-sampling Technique (SMOTE) to overcome the influence yielded by the great difference on sizes of different membrane protein types. Furthermore, two models were integrated into one model to improve the predicted quality. The test results shown that the integrated model had good performance and was superior to any individual model. Also, we compared our models with some previous models, suggesting that our models were competitive.
An infrared target tracking framework is presented that consists of three main parts: mean shift tracking, its tracking performance evaluation, and position correction. The mean shift tracking algorithm, which is a widely used kernel-based method, has been developed for the initial tracking for its efficiency and effectiveness. A performance evaluation module is applied for the online evaluation of its tracking performance with a kernel- based metric to unify the tracking and performance metric within a kernel-based tracking framework. Then the tracking performance evaluation result is input into a controller in which a decision is made whether to trigger a position correction process. The position correction module employs a matching method with a new eigenvalue-based similarity measure computed from a local complexity degree weighted covariance matrix. Experimental results on real-life infrared image sequences are presented to demonstrate the efficacy of the proposed method.
Ischemia/reperfusion (I/R) is a well‐known injury to the myocardium, but the mechanism involved remains elusive. In addition to the well‐accepted apoptosis theory, autophagy was recently found to be involved in the process, exerting a dual role as protection in ischemia and detriment in reperfusion. Activation of autophagy is mediated by mitochondrial permeability transition pore (MPTP) opening during reperfusion. In our previous study, we showed that MPTP opening is regulated by VDAC1, a channel protein located in the outer membrane of mitochondria. Thus, upregulation of VDAC1 expression is a possible trigger to cardiomyocyte autophagy via an unclear pathway. Here, we established an anoxia/reoxygenation (A/R) model in vitro to simulate the I/R process in vivo. At the end of A/R treatment, VDAC1, Beclin 1, and LC3‐II/I were upregulated, and autophagic vacuoles were increased in cardiomyocytes, which showed a connection of VDAC1 and autophagy development. These variations also led to ROS burst, mitochondrial dysfunction, and aggravated apoptosis. Knockdown of VDAC1 by RNAi could alleviate the above‐mentioned cellular damages. Additionally, the expression of PINK1 and Parkin was enhanced after A/R injury. Furthermore, Parkin was recruited to mitochondria from the cytosol, which suggested that the PINK1/Parkin autophagic pathway was activated during A/R. Nevertheless, the PINK1/Parkin pathway was effectively inhibited when VDAC1 was knocked‐down. Taken together, the A/R‐induced cardiomyocyte injury was mediated by VDAC1 upregulation, which led to cell autophagy via the PINK1/Parkin pathway, and finally aggravated apoptosis.
Autism spectrum disorders (ASD) are generally defined as a development disorder typically characterized by social interaction and communication ailments and stereotyped actions due to combined genetic and environmental factors. Different critical aspects contribute to ASD, and consensus has been reached among autism researchers about its predominant genetic factors. However, the pathogenesis of ASD has not been fully revealed, and a systematic method must be developed to identify the genes related to this disease. Here, we predicted new ASD-associated genes by random walk method on the basis of prior-known ASD genes from autDB. New genes such as RAC3, AC1 (ADCY1), PKC (PRKC) gamma, EPH receptor A5, WNT3A, calretinin, RAS-R, KLF4, and calpain 3 were found to play an irreplaceable role in ASD pathogenesis.
Background Genetically encoded fluorescent proteins are often used to label proteins and study protein function and localization in vivo. Traditional cloning methods mediated by restriction digestion and ligation are time-consuming and sometimes difficult due to the lack of suitable restriction sites. Invitrogen developed the Gateway cloning system based on the site-specific DNA recombination, which allows for digestion-free cloning. Most gateway destination vectors available for use in plants employ either the 35S or ubiquitin promoters, which confer high-level, ubiquitous expression. There are far fewer options for moderate, cell-type specific expression. Results Here we report on the construction of a Gateway-compatible cloning system (SWU vectors) to rapidly tag various proteins and express them in a cell-type specific manner in plants. We tested the SWU vectors using the HISTONE (H2B) coding sequence in stable transgenic plants. Conclusions The SWU vectors are a valuable tool for low cost, high efficiency functional analysis of proteins of interest in specific cell types in the Arabidopsis root.
A kernel-based metric measuring tracking reliability that is based on discriminative components of a kernel target model and kernel mutual information is presented. The discriminative components of the kernel target model are selected by computing the log-likelihood ratios of classconditional sample densities of these components from a target region and background sampled region. The components selection process is embedded in a metric with kernel mutual information of the target regions of the initial frame and current frame in video infrared target tracking for online evaluation of the tracking reliability. Experimental results have shown that the metric can effectively characterize target tracking results as good or bad.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.