Explore the vast range of titles available.

Multi-view data are generally collected from distinct sources or domains characterized by consistent and specific properties. However, most existing multi-view subspace clustering approaches solely encode the self-representation structure through consistent representation or a set of specific representations, leaving the knowledge of the individual view unexploited and resulting in bad performance in self-representation structure. To address this issue, we propose a novel subspace clustering strategy in which the self-representation structure is contemplated through consistent and specific representations. Specifically, we apply the low-rank sparse representation scenario to uncover the global shared representation structure among all the views and deploy the nearest neighboring method to preserve the geometrical structure according to the consistent and specific representation. The L 1 -norm and frobenius norm are applied to the consistent and specific representation to promote a sparser solution and guarantee a grouping effect. Besides, a novel objective function is figured out, which goes under the optimization process through the alternating direction technique to evaluate the optimal solution. Finally, experiments conducted on several benchmark datasets show the effectiveness of the proposed method over several state-of-the-art algorithms.

Predicting protein–ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein–ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein–ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket’s advancement and practicality for protein–ligand binding site prediction.

Chemoinformatics provides computer methods for learning from chemical data and for modeling tasks a chemist is facing. The field has evolved in the past 50 years and has substantially shaped how chemical research is performed by providing access to chemical information on a scale unattainable by traditional methods. Many physical, chemical and biological data have been predicted from structural data. For the early phases of drug design, methods have been developed that are used in all major pharmaceutical companies. However, all domains of chemistry can benefit from chemoinformatics methods; many areas that are not yet well developed, but could substantially gain from the use of chemoinformatics methods. The quality of data is of crucial importance for successful results. Computer-assisted structure elucidation and computer-assisted synthesis design have been attempted in the early years of chemoinformatics. Because of the importance of these fields to the chemist, new approaches should be made with better hardware and software techniques. Society’s concern about the impact of chemicals on human health and the environment could be met by the development of methods for toxicity prediction and risk assessment. In conjunction with bioinformatics, our understanding of the events in living organisms could be deepened and, thus, novel strategies for curing diseases developed. With so many challenging tasks awaiting solutions, the future is bright for chemoinformatics.

Predictive business process monitoring (PBPM) plays an important role in intelligent workflow management by enabling organizations to anticipate future process behavior and support operational decisions. However, many existing approaches represent execution traces primarily as linear prefixes, thereby limiting their capacity to explicitly capture the control-flow semantics of non-sequential processes. To address this limitation, this paper proposes KG-MTPM, a knowledge-graph-enhanced multi-task framework that integrates process-model-level structural knowledge with prefix-level runtime dynamics in a unified predictive architecture. In particular, control-flow relations are organized as a process knowledge graph so that non-linear execution dependencies can be explicitly represented during prediction. Based on the integrated representation, the model jointly predicts the next-activity, next-activity time, and remaining-time of an ongoing case. Experiments on three real-world event log datasets demonstrate that KG-MTPM achieves the best overall performance among the evaluated baselines, with a marked advantage in time-related prediction tasks. Relative to the best-performing baseline, KG-MTPM improves next-activity prediction accuracy from 0.84 to 0.85, while reducing the mean absolute error (MAE) of next-activity time prediction from 0.81 to 0.25 and that of remaining-time prediction from 0.98 to 0.47. Ablation results confirm the contributions of both the structure-aware representation and the multi-task learning scheme. Overall, the findings suggest that explicit modeling of process structure is beneficial for predictive monitoring in business processes with complex execution behavior.

This study aims to numerically investigate how various common simplifications of grain structure representation in bonded block models affect simulations of rock mechanical behavior. Specimens of Wausau granite were characterized mechanically through Brazilian tensile strength tests for this work. The samples were also characterized petrographically using thin section microscopy, scanning electron microscopy-based automated mineralogy, and visual inspection. Four types of representations of the Wausau granite samples were developed, including 6 detailed manually developed deterministic models, 6 semi-deterministic models, and 120 randomly generated representations (Voronoi models). First, a calibrated set of micro-properties was determined using the deterministic representations to simulate the Brazilian tensile strength measurements. Next, the study examined the ability of different Voronoi tessellations to adequately represent the grain structure for the purposes of accurate tensile strength simulation. This was evaluated by comparing Voronoi model results to the deterministic grain structure model results and laboratory test results. The findings of the study show that the four types of models used in this study can all provide realistic representations of the mechanical behavior of rock. The study confirms that standard Voronoi approximations of grain structures can be reasonably used in lieu of less practical, manually developed representations of the grain structure. Specifically, Voronoi models can properly replicate the geometric heterogeneity within the grain structure, even though they simplify some of its geometric attributes.HighlightsFour types of models of granite specimens were generated, each type representing the specimen grain structure with a different degree of realism.Brazilian tensile strength simulation results obtained using deterministic, semi-deterministic, and two different Voronoi structures were compared.Validity of randomly generated Voronoi models to adequately approximate the geometric heterogeneity within the grain structure was investigated.Voronoi models provided strengths nearly equivalent to those obtained from the more complex deterministic and semi-deterministic models.

Heterogeneous change detection (CD) is widely applied in various fields such as urban planning, environmental monitoring, and disaster management. It enhances the accuracy and comprehensiveness of surface change monitoring by integrating multi-sensor remote sensing data. Scholars have proposed many graph-based methods to address the issue of incomparable heterogeneous images caused by imaging differences. However, these methods often overlook the influence of changes in vertex status on the graph structure, which limits their ability to represent image structural features. To tackle this problem, this paper presents an unsupervised heterogeneous CD method based on enhanced graph structure representation (EGSR). This method enhances the representation capacity of the graph structure for image structural features by measuring the unchanged probabilities of vertices, thereby making it easier to detect changes in heterogeneous images. Firstly, we construct the graph structure using image superpixels and measure the structural graph differences of heterogeneous images in the same image domain. Then, we calculate the unchanged probability of each vertex in the structural graph and reconstruct the graph structure using this probability. To accurately represent the graph structure, we adopt an iterative framework for enhancing the representation of the graph structure. Finally, at the end of the iteration, the final change map (CM) is obtained by binary segmentation of the graph vertices based on their unchanged probabilities. The effectiveness of this method is validated through experiments on four sets of heterogeneous image datasets and two sets of homogeneous image datasets.

Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph representation learning to eliminate the dependence of labels. However, existing studies neglect positional information when learning discrete snapshots, resulting in insufficient network topology learning. At the same time, due to the lack of appropriate data augmentation methods, it is difficult to capture the evolving patterns of the network effectively. To address the above problems, a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs. Firstly, the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph, and the random walk is used to obtain the position representation by learning the positional information of the nodes. Secondly, a new data augmentation method is carried out from the perspectives of short-term changes and long-term stable structures of dynamic graphs. Specifically, subgraph sampling based on snapshots and global snapshots is used to obtain two structural augmentation views, and node structures and evolving patterns are learned by combining graph neural network, gated recurrent unit, and attention mechanism. Finally, the quality of node representation is improved by combining the contrastive learning between different structural augmentation views and between the two representations of structure and position. Experimental results on four real datasets show that the performance of the proposed method is better than the existing unsupervised methods, and it is more competitive than the supervised learning method under a semi-supervised setting.

The objective was to examine differences in the gait-specific cognitive representation structures between individuals after total knee- (TKA) and after total hip-joint arthroplasty (THA). The cognitive representation structure was compared between three groups: 1. three months after TKA ( n  = 12), 2. three months after THA ( n  = 12), and 3. healthy control group (CG) ( n  = 12) using the structural dimensional analysis of mental representation (SDA-M). Additionally, perceived joint function was rated by either the KOOS, JR. or HOOS, JR. Mean distribution of perceived joint function was not significantly different between the TKA (60.35 ± 11.2) and THA group (68.01 ± 13.8) (t = − 1.425; p  = .173). In the cognitive representation structure, the THA group exhibited functional differences from the TKA group and control group, both of which showed a functional structure. Three months after hip joint replacement the gait-specific cognitive representation structure seems to reflect joint function-specific deviations. Therefore, focussing on functional recovery of cognitive gait representation may facilitate gait rehabilitation in individuals after hip replacement.

Due to the complexity of geological structures, the uncertainty of geological phenomena, the massive amount of geological data, and the diversity of geological models, local dynamic updates of 3D geological body models are very difficult. Based on the analysis of the current research status of 3D geological modeling and local dynamic update of 3D geological body model, the local dynamic update methods of geological body models considering geometric, topological, semantic relationships, and geological feature features for different data sources based on the B-Rep (boundary representation) structure model and the CPG (corner-point grid) voxel model are studied in this paper. The local dynamic update methods for the 3D geological bodies based on the B-Rep structure model for new local drilling and profile data are proposed and implemented. There are two local dynamic update methods. The Dynamic update method of B-Rep structure model for local new borehole data is used to update the 3D geological body structure model to comply with the new borehole constraints. The dynamic update method of B-Rep structure model for local new profile data is used to update to the 3D geological body structure model to comply with the new profile constraints. Also the local dynamic update methods for 3D geological bodies based on the CPG voxel model for local new drilling data, new profile data, and new multi-source mixed data are proposed and implemented. There are three local dynamic update methods. The dynamic update method of CPG voxel model for local new borehole data is used to update the 3D geological body CPG voxel model to comply with the new borehole without considering the special topological changes between the strata. The dynamic update method of CPG voxel model for local new profile data is used to update the 3D geological body CPG voxel model to comply with the new profile without considering the fault information. The dynamic update method of CPG voxel model for multi-source mixed data is used to update the 3D geological body CPG voxel model to comply with the new local data through the idea of local voxel replacement with considering the faults information and special topological changes. Finally, dynamic updates for different algorithms and comparative analysis were completed through experiments.

Antibodies are key proteins in the immune system that can reversibly and non-covalently bind specifically to their corresponding antigens, forming antigen–antibody complexes. They play a crucial role in recognizing foreign or self-antigens during the adaptive immune response. Monoclonal antibodies have emerged as a promising class of biological macromolecule therapeutics with broad market prospects. In the process of antibody drug development, a key engineering challenge is to improve the affinity of candidate antibodies, without experimentally resolved structures of the antigen–antibody complexes as input for computer-aided predictive methods. In this work, we present an approach for predicting the effect of residue mutations on antibody affinity without the structures of the antigen–antibody complexes. The method involves the graph representation of proteins and utilizes a pre-trained encoder. The encoder captures the residue-level microenvironment of the target residue on the antibody along with the antigen context pre- and post-mutation. The encoder inherently possesses the potential to identify paratope residues. In addition, we curated a benchmark dataset specifically for mutations of the antibody. Compared to baseline methods based on complex structures and sequences, our approach achieves superior or comparable average accuracy on benchmark datasets. Additionally, we validate its advantage of not requiring antigen–antibody complex structures as input for predicting the effects of mutations in antibodies against SARS-CoV-2, influenza, and human cytomegalovirus. Our method shows its potential for identifying mutations that improve antibody affinity in practical antibody engineering applications.