Explore the vast range of titles available.

Background Affinity prediction between molecule and protein is an important step of virtual screening, which is usually called drug-target affinity (DTA) prediction. Its accuracy directly influences the progress of drug development. Sequence-based drug-target affinity prediction can predict the affinity according to protein sequence, which is fast and can be applied to large datasets. However, due to the lack of protein structure information, the accuracy needs to be improved. Results The proposed model which is called WGNN-DTA can be competent in drug-target affinity (DTA) and compound-protein interaction (CPI) prediction tasks. Various experiments are designed to verify the performance of the proposed method in different scenarios, which proves that WGNN-DTA has the advantages of simplicity and high accuracy. Moreover, because it does not need complex steps such as multiple sequence alignment (MSA), it has fast execution speed, and can be suitable for the screening of large databases. Conclusion We construct protein and molecular graphs through sequence and SMILES that can effectively reflect their structures. To utilize the detail contact information of protein, graph neural network is used to extract features and predict the binding affinity based on the graphs, which is called weighted graph neural networks drug-target affinity predictor (WGNN-DTA). The proposed method has the advantages of simplicity and high accuracy.

The semi-enclosed bays impacted by heavy anthropogenic activities have weak water exchange and purification capacities. Most of the sea bays have suffered severe eutrophication, water quality deterioration, ecosystem degradation and other problems. Although many countries and local governments have carried out corresponding environmental protection actions, the evaluation of their effectiveness still requires monitoring technology and data support for long-term water environment change. In this study, we take Yueqing Bay, the fourth largest bay in China, as a case to study the satellite-based water quality monitoring and variation analysis. We established a nutrient retrieval model for Yueqing Bay to produce a long-term series of nutrient concentration products in Yueqing Bay from 2013 to 2020, based on Landsat remote sensing images and long-term observation data, combined with support vector machine learning and water temperature and satellite spectra as input parameters, and then we analyzed its spatiotemporal variations and driving factors. In general, nutrient concentrations in the western part of the bay were higher than those in the eastern part. Levels of dissolved inorganic nitrogen (DIN) were lower in summer than in spring and winter, and reactive phosphate (PO4-P) levels were lower in summer and higher in autumn. In terms of natural factors, physical effects (e.g., seasonal variations in flow field) and biological effects (e.g., seasonal differences in the intensity of plankton photosynthesis) were the main causes of seasonal differences in nutrient concentration in Yueqing Bay. Nutrient concentration generally increased from 2013 to 2015 but decreased slightly after 2015. Over the past decade, the economy and industry of Yueqing Bay basin have developed rapidly. Wastewater resulting from anthropogenic production and consumption was transported via streams into Yueqing Bay, leading to the continuous increase in nutrient concentrations (the variation rates: aDIN>0, aPO4−P>0), which directly or indirectly caused high nutrient concentrations in some areas of the bay (e.g., Southwest Shoal at the mouth of Yueqing Bay). After 2015, the various ecological remediation policies adopted by cities around Yueqing Bay have mitigated, to some extent, the increasing nutrient concentration trends (the variation rates: aDIN<0, aPO4−P<0), but not significantly (P > 0.1). The environmental restoration of Yueqing Bay also requires continuous and long-term ecological protection and restoration work to be effective. This research can provide a reference for ecological environment monitoring and remote sensing data application for similar semi-enclosed bays, and support the sustainable development of the bay.

Understanding the functions of proteins is of great importance for deciphering the mechanisms of life activities. To date, there have been over 200 million known proteins, but only 0.2% of them have well-annotated functional terms. By measuring the contacts among residues, proteins can be described as graphs so that the graph leaning approaches can be applied to learn protein representations. However, existing graph-based methods put efforts in enriching the residue node information and did not fully exploit the edge information, which leads to suboptimal representations considering the strong association of residue contacts to protein structures and to the functions. In this article, we propose SuperEdgeGO, which introduces the supervision of edges in protein graphs to learn a better graph representation for protein function prediction. Different from common graph convolution methods that uses edge information in a plain or unsupervised way, we introduce a supervised attention to encode the residue contacts explicitly into the protein representation. Comprehensive experiments demonstrate that SuperEdgeGO achieves state-of-the-art performance on all three categories of protein functions. Additional ablation analysis further proves the effectiveness of the devised edge supervision strategy. The implementation of edge supervision in SuperEdgeGO resulted in enhanced graph representations for protein function prediction, as demonstrated by its superior performance across all the evaluated categories. This superior performance was confirmed through ablation analysis, which validated the effectiveness of the edge supervision strategy. This strategy has a broad application prospect in the study of protein function and related fields.

Molecular toxicity prediction is one of the key studies in drug design. In this paper, a deep learning network based on a two-dimension grid of molecules is proposed to predict toxicity. At first, the van der Waals force and hydrogen bond were calculated according to different descriptors of molecules, and multi-channel grids were generated, which could discover more detail and helpful molecular information for toxicity prediction. The generated grids were fed into a convolutional neural network to obtain the result. A Tox21 dataset was used for the evaluation. This dataset contains more than 12,000 molecules. It can be seen from the experiment that the proposed method performs better compared to other traditional deep learning and machine learning methods.

In the process of drug discovery, identifying the interaction between the protein and the novel compound plays an important role. With the development of technology, deep learning methods have shown excellent performance in various situations. However, the compound–protein interaction is complicated and the features extracted by most deep models are not comprehensive, which limits the performance to a certain extent. In this paper, we proposed a multiscale convolutional network that extracted the local and global features of the protein and the topological feature of the compound using different types of convolutional networks. The results showed that our model obtained the best performance compared with the existing deep learning methods.

Objective Long QT interval syndrome (LQTS) is a highly dangerous cardiac disease that can lead to sudden cardiac death; however, its underlying mechanism remains largely unknown. This study is conceived to investigate the impact of two general genotypes of LQTS type 2, and also the therapeutic effects of an emerging immunology-based treatment named KCNQ1 antibody. Methods A multiscale virtual heart is developed, which contains multiple biological levels ranging from ion channels to a three-dimensional cardiac structure with realistic geometry. Critical biomarkers at different biological levels are monitored to investigate the remodeling of cardiac electrophysiology induced by mutations. Results Simulations revealed multiple important mechanisms that are hard to capture via conventional clinical techniques, including the augmented dispersion of repolarization, the increased vulnerability to arrhythmias, the impaired adaptability in tissue to high heart rates, and so on. An emerging KCNQ1 antibody-based therapy could rescue the prolonged QT interval but did not reduce the vulnerable window. Conclusions Tiny molecular alterations can lead to cardiac electrophysiological remodeling at multiple biological levels, which in turn contributes to higher susceptibility to lethal arrhythmias in long QT syndrome type 2 patients. The KCNQ1 antibody-based therapy has proarrhythmic risks notwithstanding its QT-rescuing effects.

Understanding the function of proteins is of great significance for revealing disease pathogenesis and discovering new targets. Benefiting from the explosive growth of the protein universal, deep learning has been applied to accelerate the protein annotation cycle from different biological modalities. However, most existing deep learning-based methods not only fail to effectively fuse different biological modalities, resulting in low-quality protein representations, but also suffer from the convergence of suboptimal solution caused by sparse label representations. Aiming at the above issue, we propose a multiprocedural approach for fusing heterogeneous biological modalities and annotating protein functions, i.e., MIF2GO (Multimodal Information Fusion to infer Gene Ontology terms), which sequentially fuses up to six biological modalities ranging from different biological levels in three steps, thus leading to powerful protein representations. Evaluation results on seven benchmark datasets show that the proposed method not only considerably outperforms state-of-the-art performance, but also demonstrates great robustness and generalizability across species. Besides, we also present biological insights into the associations between those modalities and protein functions. This research provides a robust framework for integrating multimodal biological data, offering a scalable solution for protein function annotation, ultimately facilitating advancements in precision medicine and the discovery of novel therapeutic strategies. MIF2GO leverages up to six biological modalities to enhance protein function annotation. It outperforms state-of-the-art methods, showing robustness and generalizability across species, while offering insights into modality-function associations.

Visible Infrared Imaging Radiometer Suite (VIIRS) data were systematically evaluated and used to detect harmful algal bloom (HAB) and classify algal bloom types in coasts of the East China Sea covered by optically complex and sediment-rich waters. First, the accuracy and spectral characteristics of VIIRS retrieved normalized water-leaving radiance or the equivalent remote sensing reflectance from September 2019 to October 2020 that were validated by the long-term observation data acquired from an offshore platform and underway measurements from a cruise in the Changjiang Estuary and adjacent East China Sea. These data were evaluated by comparing them with data from the Moderate-Resolution Imaging Spectroradiometer. The bands of 486, 551, and 671 nm provided much higher quality than those of 410 and 443 nm and were more suitable for HAB detection. Secondly, the performance of four HAB detection algorithms were compared. The Ratio of Algal Bloom (RAB) algorithm is probably more suitable for HAB detection in the study area. Importantly, although RAB was also verified to be applicable for the detection of different kinds of HAB (Prorocentrum donghaiense, diatoms, Ceratium furca, and Akashiwo sanguinea), the capability of VIIRS in the classification of those algal species was limited by the lack of the critical band near 531 nm.

The Arctic sea-ice extent has shown a declining trend over the past 30 years. Ice coverage reached historic minima in2007 and again in 2012. This trend has recently been assessed to be unique over at least the last 1450 years. In the summerof 2010, a very low sea-ice concentration （SIC） appeared at high Arctic latitudes--even lower than that of surrounding packice at lower latitudes. This striking low ice concentration--referred to here as a record low ice concentration in the centralArctic （CARLIC）--is unique in our analysis period of 2003-15, and has not been previously reported in the literature. TheCARLIC was not the result of ice melt, because sea ice was still quite thick based on in-situ ice thickness measurements.Instead, divergent ice drift appears to have been responsible for the CARLIC. A high correlation between SIC and windstress curl suggests that the sea ice drift during the summer of 2010 responded strongly to the regional wind forcing. Thedrift trajectories of ice buoys exhibited a transpolar drift in the Atlantic sector and an eastward drift in the Pacific sector,which appeared to benefit the CARLIC in 2010. Under these conditions, more solar energy can penetrate into the open water,increasing melt through increased heat flux to the ocean. We speculate that this divergence of sea ice could occur more oftenin the coming decades, and impact on hemispheric SIC and feed back to the climate.

Human activity recognition is important for healthcare and lifestyle evaluation. In this paper, a novel method for activity recognition by jointly considering motion sensor data recorded by wearable smart watches and image data captured by RGB-Depth (RGB-D) cameras is presented. A normalized cross correlation based mapping method is implemented to establish association between motion sensor data with corresponding image data from the same person in multi-person situations. Further, to improve the performance and accuracy of recognition, a hierarchical structure embedded with an automatic group selection method is proposed. Through this method, if the number of activities to be classified is changed, the structure will be changed correspondingly without interaction. Our comparative experiments against the single data source and single layer methods have shown that our method is more accurate and robust.