A Single-Cell Interrogation System from Scratch: Microfluidics and Deep Learning

Live-cell imaging using fluorescence microscopy enables researchers to study cellular processes in unprecedented detail. These techniques are becoming increasingly popular among microbiologists. The emergence of microfluidics and deep learning has significantly increased the amount of quantitative data that can be extracted from such experiments. However, these techniques require highly specialized expertise and equipment, making them inaccessible to many biologists. Here we present a guide for microbiologists, with a basic understanding of microfluidics, to construct a custom-made live-cell interrogation system that is capable of recording and analyzing thousands of bacterial cell-cycles per experiment. The requirements for different microbiological applications are varied, and experiments often demand a high level of versatility and custom-designed capabilities. This work is intended as a guide for the design and engineering of microfluidic master molds and how to build polydimethylsiloxane chips. Furthermore, we show how state-of-the-art deep-learning techniques can be used to design image processing algorithms that allow for the rapid extraction of highly quantitative information from large populations of individual bacterial cells.

Fast moving table tennis ball tracking algorithm based on graph neural network

The key object tracking in sports video scenarios poses a pivotal challenge in the analysis of sports techniques and tactics. In table tennis, due to the small size and rapid motion of the ball, identifying and tracking the table tennis ball through video is a particularly arduous task, where the majority of existing detection and tracking algorithms struggle to meet the practical application requirements in real-world scenarios. To address this issue, this paper proposes a combined technical approach integrating detection and discrimination, tailored to the unique motion characteristics of table tennis. For the detector, we utilize and refine a common video differential detector. As for the discriminator, we introduce GMP (a Graph Max-message Pass Neural Network), which is designed specifically for tracking table tennis balls or similar objects. Furthermore, we enhance an existing dataset for table tennis tracking problems by enriching its scenarios. The results demonstrate that our proposed technical solution performs impressively on both the dataset and the intended real-world environments, showcasing the good scalability of our algorithms and models as well as their potential for application in other scenarios.

Fusing multiplex heterogeneous networks using graph attention-aware fusion networks

Graph Neural Networks (GNN) emerged as a deep learning framework to generate node and graph embeddings for downstream machine learning tasks. Popular GNN-based architectures operate on networks of single node and edge type. However, a large number of real-world networks include multiple types of nodes and edges. Enabling these architectures to work on networks with multiple node and edge types brings additional challenges due to the heterogeneity of the networks and the multiplicity of the existing associations. In this study, we present a framework, named GRAF (Graph Attention-aware Fusion Networks), to convert multiplex heterogeneous networks to homogeneous networks to make them more suitable for graph representation learning. Using attention-based neighborhood aggregation, GRAF learns the importance of each neighbor per node (called node-level attention) followed by the importance of each network layer (called network layer-level attention). Then, GRAF processes a network fusion step weighing each edge according to the learned attentions. After an edge elimination step based on edge weights, GRAF utilizes Graph Convolutional Networks (GCN) on the fused network and incorporates node features on graph-structured data for a node classification or a similar downstream task. To demonstrate GRAF's generalizability, we applied it to four datasets from different domains and observed that GRAF outperformed or was on par with the baselines and state-of-the-art (SOTA) methods. We were able to interpret GRAF's findings utilizing the attention weights. Source code for GRAF is publicly available at https://github.com/bozdaglab/GRAF .

Learning and fine-tuning a generic value-selection heuristic inside a constraint programming solver

Constraint programming is known for being an efficient approach to solving combinatorial problems. Important design choices in a solver are the branching heuristics, designed to lead the search to the best solutions in a minimum amount of time. However, developing these heuristics is a time-consuming process that requires problem-specific expertise. This observation has motivated many efforts to use machine learning to automatically learn efficient heuristics without expert intervention. Although several generic variable-selection heuristics are available in the literature, the options for value-selection heuristics are more scarce. We propose to tackle this issue by introducing a generic learning procedure that can be used to obtain a value-selection heuristic inside a constraint programming solver. This has been achieved thanks to the combination of a deep Q-learning algorithm, a tailored reward signal, and a heterogeneous graph neural network. Experiments on graph coloring, maximum independent set, maximum cut, and minimum vertex cover problems show that this framework competes with the well-known impact-based and activity-based search heuristics and can find solutions close to optimality without requiring a large number of backtracks. Additionally, we observe that fine-tuning a model with a different problem class can accelerate the learning process.

CellMsg: graph convolutional networks for ligand-receptor-mediated cell-cell communication analysis

The role of cell-cell communications (CCCs) is increasingly recognized as being important to differentiation, invasion, metastasis, and drug resistance in tumoral tissues. Developing CCC inference methods using traditional experimental methods are time-consuming, labor-intensive, cannot handle large amounts of data. To facilitate inference of CCCs, we proposed a computational framework, called CellMsg, which involves two primary steps: identifying ligand-receptor interactions (LRIs) and measuring the strength of LRIs-mediated CCCs. Specifically, CellMsg first identifies high-confident LRIs based on multimodal features of ligands and receptors and graph convolutional networks. Then, CellMsg measures the strength of intercellular communication by combining the identified LRIs and single-cell RNA-seq data using a three-point estimation method. Performance evaluation on four benchmark LRI datasets by five-fold cross validation demonstrated that CellMsg accurately captured the relationships between ligands and receptors, resulting in the identification of high-confident LRIs. Compared with other methods of identifying LRIs, CellMsg has better prediction performance and robustness. Furthermore, the LRIs identified by CellMsg were successfully validated through molecular docking. Finally, we examined the overlap of LRIs between CellMsg and five other classical CCC databases, as well as the intercellular crosstalk among seven cell types within a human melanoma tissue. In summary, CellMsg establishes a complete, reliable, and well-organized LRI database and an effective CCC strength evaluation method for each single-cell RNA-seq data. It provides a computational tool allowing researchers to decipher intercellular communications. CellMsg is freely available at https://github.com/pengsl-lab/CellMsg.

A Spatial-Temporal Multi-Feature Network (STMF-Net) for Skeleton-Based Construction Worker Action Recognition

Globally, monitoring productivity, occupational health, and safety of construction workers has long been a significant concern. To address this issue, there is an urgent need for efficient methods to continuously monitor construction sites and recognize workers' actions in a timely manner. Recently, advances in electronic technology and pose estimation algorithms have made it easier to obtain skeleton and joint trajectories of human bodies. Deep learning algorithms have emerged as robust and automated tools for extracting and processing 3D skeleton information on construction sites, proving effective for workforce action assessment. However, most previous studies on action recognition have primarily focused on single-stream data, which limited the network's ability to capture more comprehensive worker action features. Therefore, this research proposes a Spatial-Temporal Multi-Feature Network (STMF-Net) designed to utilize six 3D skeleton-based features to monitor and capture the movements of construction workers, thereby recognizing their actions. The experimental results demonstrate an accuracy of 79.36%. The significance of this work lies in its potential to enhance management models within the construction industry, ultimately improving workers' health and work efficiency.

HHH whitepaper

We here report on the progress of the HHH Workshop, that took place in Dubrovnik in July 2023. After the discovery of a particle that complies with the properties of the Higgs boson of the Standard Model, all Standard Model (SM) parameters are in principle determined. However, in order to verify or falsify the model, the full form of the potential has to be determined. This includes the measurement of the triple and quartic scalar couplings. We here report on ongoing progress of measurements for multi-scalar final states, with an emphasis on three SM-like scalar bosons at 125Ge V , but also mentioning other options. We discuss both experimental progress and challenges as well as theoretical studies and models that can enhance such rates with respect to the SM predictions.

An adaptive multi-graph neural network with multimodal feature fusion learning for MDD detection

Major Depressive Disorder (MDD) is an affective disorder that can lead to persistent sadness and a decline in the quality of life, increasing the risk of suicide. Utilizing multimodal data such as electroencephalograms and patient interview audios can facilitate the timely detection of MDD. However, existing depression detection methods either consider only a single modality or do not fully account for the differences and similarities between modalities in multimodal approaches, potentially overlooking the latent information inherent in various modal data. To address these challenges, we propose EMO-GCN, a multimodal depression detection method based on an adaptive multi-graph neural network. By employing graph-based methods to model data from various modalities and extracting features from them, the potential correlations between modalities are uncovered. The model's performance on the MODMA dataset is outstanding, achieving an accuracy (ACC) of 96.30%. Ablation studies further confirm the effectiveness of the model's individual components.The experimental results of EMO-GCN demonstrate the application prospects of graph-based multimodal analysis in the field of mental health, offering new perspectives for future research.

Stock movement prediction in a hotel with multimodality and spatio-temporal features during the Covid-19 pandemic

The COVID-19 pandemic has underscored the importance of accurate stock prediction in the tourism industry, particularly for hotels. Despite the growing interest in leveraging consumer reviews for stock performance forecasting, existing methods often need to integrate the rich, multimodal data from these reviews fully. This study addresses this gap by developing a novel deep learning model, the Multimodal Spatio-Temporal Graph Convolutional Neural Network (MSGCN), specifically designed to predict hotel stock performance. Unlike traditional models, MSGCN captures the spatial relationships between hotels using a graph convolutional network and integrates multimodal information-including text, images, and ratings from consumer reviews-into the prediction process. Our research builds on existing literature by validating the efficacy of multimodal data in improving stock prediction and introducing a spatio-temporal component that enhances prediction accuracy. Through rigorous testing on two diverse datasets, our model demonstrates superior performance compared to existing approaches, showing robustness during and after the COVID-19 pandemic. The findings provide valuable insights for hotel managers and consumers, offering a powerful tool for making informed business decisions in a rapidly evolving market.

DGNMDA: Dual Heterogeneous Graph Neural Network Encoder for miRNA-Disease Association Prediction

In recent years, numerous studies have highlighted the pivotal importance of miRNAs in personalized healthcare, showcasing broad application prospects. miRNAs hold significant potential in disease diagnosis, prognosis assessment, and therapeutic target discovery, making them an integral part of precision medicine. They are expected to enable precise disease subtyping and risk prediction, thereby advancing the development of precision medicine. GNNs, a class of deep learning architectures tailored for graph data analysis, have greatly facilitated the advancement of miRNA-disease association prediction algorithms. However, current methods often fall short in leveraging network node information, particularly in utilizing global information while neglecting the importance of local information. Effectively harnessing both local and global information remains a pressing challenge. To tackle this challenge, we propose an innovative model named DGNMDA. Initially, we constructed various miRNA and disease similarity networks based on authoritative databases. Subsequently, we creatively design a dual heterogeneous graph neural network encoder capable of efficiently learning feature information between adjacent nodes and similarity information across the entire graph. Additionally, we develop a specialized fine-grained multi-layer feature interaction gating mechanism to integrate outputs from the neural network encoders to identify novel associations connecting miRNAs with diseases. We evaluate our model using 5-fold cross-validation and real-world disease case studies, based on the HMDD V3.2 dataset. Our method demonstrates superior performance compared to existing approaches in various tasks, confirming the effectiveness and potential of DGNMDA as a robust method for predicting miRNA-disease associations.

scGraphformer: unveiling cellular heterogeneity and interactions in scRNA-seq data using a scalable graph transformer network

The precise classification of cell types from single-cell RNA sequencing (scRNA-seq) data is pivotal for dissecting cellular heterogeneity in biological research. Traditional graph neural network (GNN) models are constrained by reliance on predefined graphs, limiting the exploration of complex cell-to-cell relationships. We introduce scGraphformer, a transformer-based GNN that transcends these limitations by learning an all-encompassing cell-cell relational network directly from scRNA-seq data. Through an iterative refinement process, scGraphformer constructs a dense graph structure that captures the full spectrum of cellular interactions. This comprehensive approach enables the identification of subtle and previously obscured cellular patterns and relationships. Evaluated on multiple datasets, scGraphformer demonstrates superior performance in cell type identification compared to existing methods and showcases its scalability with large-scale datasets. Our method not only provides enhanced cell type classification ability but also reveals the underlying cell interactions, offering deeper insights into functional cellular relationships. The scGraphformer thus holds the potential to significantly advance the field of single-cell analysis and contribute to a more nuanced understanding of cellular behavior.

Development of a deep learning-based feature stream network for forecasting riverine harmful algal blooms from a network perspective

Global increases in the occurrence of harmful algal blooms (HABs) are of major concern in water quality and resource management. A predictive model capable of quantifying the spatiotemporal associations between HABs and their influencing factors is required for effective preventive management. In this study, a feature stream network (FSN) model is proposed to provide daily forecasts of cyanobacteria abundance at multiple monitoring sites simultaneously in a river network. The spatial connectivity between monitoring sites was expressed as a directed acyclic graph comprising edges and nodes representing flows and monitoring sites, respectively. Furthermore, a segment-wise node connection structure was developed to extract the latent features of a river segment comprising individual nodes and sequentially transfer them to the downstream segment(s). In addition, a feature engineering-attention hybrid mechanism was employed to address temporal mismatches among different monitoring schemes while adding explainability to the model. Consequently, the FSN showed improved predictive performance, temporal resolution, and explainability for multi-site forecasts of HAB in a single model framework. The developed model was applied to a bloom-prone middle course of the Nakdong River, South Korea. Various hydrological, environmental, and biological factors were utilized for forecasting the cyanobacteria abundance. The FSN exhibited a high degree of accuracy across the sites for the test data with a coefficient of determination in the range of 0.64-0.71 and root mean square error in the range of 2.06-2.26 cells/mL on natural log scales. Although the relative importance of input features varied across the sites, the features extracted from nearby nodes consistently exhibited high importance in forecasting the cyanobacteria abundance. These explanations indicate that the proposed model can successfully characterize the spatial hierarchy of a river network. A scenario analysis suggested that reduced total nitrogen loads in the effluents from the wastewater treatment plant and the combined operations of upstream and downstream weirs were effective in managing HABs.

An Accurate and Efficient Approach to Knowledge Extraction from Scientific Publications Using Structured Ontology Models, Graph Neural Networks, and Large Language Models

The rapid growth of biomedical literature makes it challenging for researchers to stay current. Integrating knowledge from various sources is crucial for studying complex biological systems. Traditional text-mining methods often have limited accuracy because they don't capture semantic and contextual nuances. Deep-learning models can be computationally expensive and typically have low interpretability, though efforts in explainable AI aim to mitigate this. Furthermore, transformer-based models have a tendency to produce false or made-up information-a problem known as hallucination-which is especially prevalent in large language models (LLMs). This study proposes a hybrid approach combining text-mining techniques with graph neural networks (GNNs) and fine-tuned large language models (LLMs) to extend biomedical knowledge graphs and interpret predicted edges based on published literature. An LLM is used to validate predictions and provide explanations. Evaluated on a corpus of experimentally confirmed protein interactions, the approach achieved a Matthews correlation coefficient (MCC) of 0.772. Applied to insomnia, the approach identified 25 interactions between 32 human proteins absent in known knowledge bases, including regulatory interactions between MAOA and 5-HT2C, binding between ADAM22 and 14-3-3 proteins, which is implicated in neurological diseases, and a circadian regulatory loop involving RORB and NR1D1. The hybrid GNN-LLM method analyzes biomedical literature efficiency to uncover potential molecular interactions for complex disorders. It can accelerate therapeutic target discovery by focusing expert verification on the most relevant automatically extracted information.

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

Graph neural networks (GNN) suffer from severe inefficiency due to the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT) and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity. To avoid the only unidirectional information delivery of FT and sufficiently train shallow modules with the deeper ones, we develop a backward training mechanism that makes the former modules perceive the latter modules, inspired by the classical backward propagation algorithm. The backward training introduces the reversed information delivery into the decoupled modules as well as the forward information delivery. To investigate how the decoupling and greedy training affect the representational capacity, we theoretically prove that the error produced by linear modules will not accumulate on unsupervised tasks in most cases. The theoretical and experimental results show that the proposed framework is highly efficient with reasonable performance, which may deserve more investigation.

Universal Ensemble-Embedding Graph Neural Network for Direct Prediction of Optical Spectra from Crystal Structures

Optical properties in solids, such as refractive index and absorption, hold vast applications ranging from solar panels to sensors, photodetectors, and transparent displays. However, first-principles computation of optical properties from crystal structures is a complex task due to the high convergence criteria and computational cost. Recent progress in machine learning shows promise in predicting material properties, yet predicting optical properties from crystal structures remains challenging due to the lack of efficient atomic embeddings. Here, Graph Neural Network for Optical spectra prediction (GNNOpt) is introduced, an equivariant graph-neural-network architecture featuring universal embedding with automatic optimization. This enables high-quality optical predictions with a dataset of only 944 materials. GNNOpt predicts all optical properties based on the Kramers-Krönig relations, including absorption coefficient, complex dielectric function, complex refractive index, and reflectance. The trained model is applied to screen photovoltaic materials based on spectroscopic limited maximum efficiency and search for quantum materials based on quantum weight. First-principles calculations validate the efficacy of the GNNOpt model, demonstrating excellent agreement in predicting the optical spectra of unseen materials. The discovery of new quantum materials with high predicted quantum weight, such as SiOs, which host exotic quasiparticles with multifold nontrivial topology, demonstrates the potential of GNNOpt in predicting optical properties across a broad range of materials and applications.

Hierarchical Hypergraph Learning in Association- Weighted Heterogeneous Network for miRNA- Disease Association Identification

MicroRNAs (miRNAs) play a significant role in cell differentiation, biological development as well as the occurrence and growth of diseases. Although many computational methods contribute to predicting the association between miRNAs and diseases, they do not fully explore the attribute information contained in associated edges between miRNAs and diseases. In this study, we propose a new method, Hierarchical Hypergraph learning in Association-Weighted heterogeneous network for MiRNA-Disease association identification (HHAWMD). HHAWMD first adaptively fuses multi-view similarities based on channel attention and distinguishes the relevance of different associated relationships according to changes in expression levels of disease-related miRNAs, miRNA similarity information, and disease similarity information. Then, HHAWMD assigns edge weights and attribute features according to the association level to construct an association-weighted heterogeneous graph. Next, HHAWMD extracts the subgraph of the miRNA-disease node pair from the heterogeneous graph and builds the hyperedge (a kind of virtual edge) between the node pair to generate the hypergraph. Finally, HHAWMD proposes a hierarchical hypergraph learning approach, including node-aware attention and hyperedge-aware attention, which aggregates the abundant semantic information contained in deep and shallow neighborhoods to the hyperedge in the hypergraph. Our experiment results suggest that HHAWMD has better performance and can be used as a powerful tool for miRNA-disease association identification.

An attribution graph-based interpretable method for CNNs

Convolutional Neural Networks (CNNs) have demonstrated outstanding performance in various domains, such as face recognition, object detection, and image segmentation. However, the lack of transparency and limited interpretability inherent in CNNs pose challenges in fields such as medical diagnosis, autonomous driving, finance, and military applications. Several studies have explored the interpretability of CNNs and proposed various post-hoc interpretable methods. The majority of these methods are feature-based, focusing on the influence of input variables on outputs. Few methods undertake the analysis of parameters in CNNs and their overall structure. To explore the structure of CNNs and intuitively comprehend the role of their internal parameters, we propose an Attribution Graph-based Interpretable method for CNNs (AGIC) which models the overall structure of CNNs as graphs and provides interpretability from global and local perspectives. The runtime parameters of CNNs and feature maps of each image sample are applied to construct attribution graphs (At-GCs), where the convolutional kernels are represented as nodes and the SHAP values between kernel outputs are assigned as edges. These At-GCs are then employed to pretrain a newly designed heterogeneous graph encoder based on Deep Graph Infomax (DGI). To comprehensively delve into the overall structure of CNNs, the pretrained encoder is used for two types of interpretable tasks: (1) a classifier is attached to the pretrained encoder for the classification of At-GCs, revealing the dependency of At-GC's topological characteristics on the image sample categories, and (2) a scoring aggregation (SA) network is constructed to assess the importance of each node in At-GCs, thus reflecting the relative importance of kernels in CNNs. The experimental results indicate that the topological characteristics of At-GC exhibit a dependency on the sample category used in its construction, which reveals that kernels in CNNs show distinct combined activation patterns for processing different image categories, meanwhile, the kernels that receive high scores from SA network are crucial for feature extraction, whereas low-scoring kernels can be pruned without affecting model performance, thereby enhancing the interpretability of CNNs.

Physics-informed line graph neural network for power flow calculation

Power flow calculation plays a significant role in the operation and planning of modern power systems. Traditional numerical calculation methods have good interpretability but high time complexity. They are unable to cope with increasing amounts of data in power systems; therefore, many machine learning based methods have been proposed for more efficient power flow calculation. Despite the good performance of these methods in terms of computation speed, they often overlook the importance of transmission lines and do not fully consider the physical mechanisms in the power systems, thereby weakening the prediction accuracy of power flow. Given the importance of the transmission lines as well as to comprehensively consider their mutual influence, we shift our focus from bus adjacency relationships to transmission line adjacency relationships and propose a physics-informed line graph neural network framework. This framework propagates information between buses and transmission lines by introducing the concepts of the incidence matrix and the line graph matrix. Based on the mechanics of the power flow equations, we further design a loss function by integrating physical information to ensure that the output results of the model satisfy the laws of physics and have better interpretability. Experimental results on different power grid datasets and different scenarios demonstrate the accuracy of our proposed model.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST's capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

Knowledge graph based reasoning in medical image analysis: A scoping review

Automated computer-aided diagnosis (CAD) is becoming more significant in the field of medicine due to advancements in computer hardware performance and the progress of artificial intelligence. The knowledge graph is a structure for visually representing knowledge facts. In the last decade, a large body of work based on knowledge graphs has effectively improved the organization and interpretability of large-scale complex knowledge. Introducing knowledge graph inference into CAD is a research direction with significant potential. In this review, we briefly review the basic principles and application methods of knowledge graphs firstly. Then, we systematically organize and analyze the research and application of knowledge graphs in medical imaging-assisted diagnosis. We also summarize the shortcomings of the current research, such as medical data barriers and deficiencies, low utilization of multimodal information, and weak interpretability. Finally, we propose future research directions with possibilities and potentials to address the shortcomings of current approaches.

Grounded situation recognition under data scarcity

Grounded Situation Recognition (GSR) aims to generate structured image descriptions. For a given image, GSR needs to identify the key verb, the nouns corresponding to roles, and their bounding-box groundings. However, current GSR research demands numerous meticulously labeled images, which are labor-intensive and time-consuming, making it costly to expand detection categories. Our study enhances model accuracy in detecting and localizing under data scarcity, reducing dependency on large datasets and paving the way for broader detection capabilities. In this paper, we propose the Grounded Situation Recognition under Data Scarcity (GSRDS) model, which uses the CoFormer model as the baseline and optimizes three subtasks: image feature extraction, verb classification, and bounding-box localization, to better adapt to data-scarce scenarios. Specifically, we replace ResNet50 with EfficientNetV2-M for advanced image feature extraction. Additionally, we introduce the Transformer Combined with CLIP for Verb Classification (TCCV) module, utilizing features extracted by CLIP's image encoder to enhance verb classification accuracy. Furthermore, we design the Multi-source Verb-Role Queries (Multi-VR Queries) and the Dual Parallel Decoders (DPD) modules to improve the accuracy of bounding-box localization. Through extensive comparative experiments and ablation studies, we demonstrate that our method achieves higher accuracy than mainstream approaches in data-scarce scenarios. Our code will be available at https://github.com/Zhou-maker-oss/GSRDS .

Click, Compute, Create: A Review of Web-based Tools for Enzyme Engineering

Enzyme engineering, though pivotal across various biotechnological domains, is often plagued by its time-consuming and labor-intensive nature. This review aims to offer an overview of supportive in silico methodologies for this demanding endeavor. Starting from methods to predict protein structures, to classification of their activity and even the discovery of new enzymes we continue with describing tools used to increase thermostability and production yields of selected targets. Subsequently, we discuss computational methods to modulate both, the activity as well as selectivity of enzymes. Last, we present recent approaches based on cutting-edge machine learning methods to redesign enzymes. With exception of the last chapter, there is a strong focus on methods easily accessible via web-interfaces or simple Python-scripts, therefore readily useable for a diverse and broad community.

To Boost Zero-Shot Generalization for Embodied Reasoning With Vision-Language Pre-Training

Recently, there exists an increased research interest in embodied artificial intelligence (EAI), which involves an agent learning to perform a specific task when dynamically interacting with the surrounding 3D environment. There into, a new challenge is that many unseen objects may appear due to the increased number of object categories in 3D scenes. It makes developing models with strong zero-shot generalization ability to new objects necessary. Existing work tries to achieve this goal by providing embodied agents with massive high-quality human annotations closely related to the task to be learned, while it is too costly in practice. Inspired by recent advances in pre-trained models in 2D visual tasks, we attempt to boost zero-shot generalization for embodied reasoning with vision-language pre-training that can encode common sense as general prior knowledge. To further improve its performance on a specific task, we rectify the pre-trained representation through masked scene graph modeling (MSGM) in a self-supervised manner, where the task-specific knowledge is learned from iterative message passing. Our method can improve a variety of representative embodied reasoning tasks by a large margin (e.g., over 5.0% w.r.t. answer accuracy on MP3D-EQA dataset that consists of many real-world scenes with a large number of new objects during testing), and achieve the new state-of-the-art performance.

Computer-Aided Synthesis Planning (CASP) and Machine Learning: Optimizing Chemical Reaction Conditions

Computer-aided synthesis planning (CASP) has garnered increasing attention in light of recent advancements in machine learning models. While the focus is on reverse synthesis or forward outcome prediction, optimizing reaction conditions remains a significant challenge. For datasets with multiple variables, the choice of descriptors and models is pivotal. This selection dictates the effective extraction of conditional features and the achievement of higher prediction accuracy. This review delineates the origins of data in conditional optimization, the criteria for descriptor selection, the response models, and the metrics for outcome evaluation, aiming to acquaint readers with the latest research trends and facilitate more informed research in this domain.

Hypergraph-Based Multi-View Action Recognition Using Event Cameras

Action recognition from video data forms a cornerstone with wide-ranging applications. Single-view action recognition faces limitations due to its reliance on a single viewpoint. In contrast, multi-view approaches capture complementary information from various viewpoints for improved accuracy. Recently, event cameras have emerged as innovative bio-inspired sensors, leading to advancements in event-based action recognition. However, existing works predominantly focus on single-view scenarios, leaving a gap in multi-view event data exploitation, particularly in challenges like information deficit and semantic misalignment. To bridge this gap, we introduce HyperMV, a multi-view event-based action recognition framework. HyperMV converts discrete event data into frame-like representations and extracts view-related features using a shared convolutional network. By treating segments as vertices and constructing hyperedges using rule-based and KNN-based strategies, a multi-view hypergraph neural network that captures relationships across viewpoint and temporal features is established. The vertex attention hypergraph propagation is also introduced for enhanced feature fusion. To prompt research in this area, we present the largest multi-view event-based action dataset THUMV-EACT-50, comprising 50 actions from 6 viewpoints, which surpasses existing datasets by over tenfold. Experimental results show that HyperMV significantly outperforms baselines in both cross-subject and cross-view scenarios, and also exceeds the state-of-the-arts in frame-based multi-view action recognition.

Relation semantic fusion in subgraph for inductive link prediction in knowledge graphs

Inductive link prediction (ILP) in knowledge graphs (KGs) aims to predict missing links between entities that were not seen during the training phase. Recent some subgraph-based methods have shown some advancements, but they all overlook the relational semantics between entities during subgraph extraction. To overcome this limitation, we introduce a novel inductive link prediction model named SASILP (Structure and Semantic Inductive Link Prediction), which comprehensively incorporates relational semantics in both subgraph extraction and node initialization processes. The model employs a random walk strategy to calculate the structural scores of neighboring nodes and utilizes an enhanced graph attention network to determine their semantic scores. By integrating both structural and semantic scores, SASILP strategically selects key nodes to form a subgraph. Furthermore, the subgraph is initialized with a node initialization technique that integrates information about neighboring relations. The experiments conducted on benchmark datasets demonstrate that SASILP outperforms state-of-the-art methods on inductive link prediction tasks, and verify the effectiveness of our approach.

Medical-Knowledge-Based Graph Neural Network for Medication Combination Prediction

Medication combination prediction (MCP) can provide assistance for experts in the more thorough comprehension of complex mechanisms behind health and disease. Many recent studies focus on the patient representation from the historical medical records, but neglect the value of the medical knowledge, such as the prior knowledge and the medication knowledge. This article develops a medical-knowledge-based graph neural network (MK-GNN) model which incorporates the representation of patients and the medical knowledge into the neural network. More specifically, the features of patients are extracted from their medical records in different feature subspaces. Then these features are concatenated to obtain the feature representation of patients. The prior knowledge, which is calculated according to the mapping relationship between medications and diagnoses, provides heuristic medication features according to the diagnosis results. Such medication features can help the MK-GNN model learn optimal parameters. Moreover, the medication relationship in prescriptions is formulated as a drug network to integrate the medication knowledge into medication representation vectors. The results reveal the superior performance of the MK-GNN model compared with the state-of-the-art baselines on different evaluation metrics. The case study manifests the application potential of the MK-GNN model.

FuseLinker: Leveraging LLM's pre-trained text embeddings and domain knowledge to enhance GNN-based link prediction on biomedical knowledge graphs

OBJECTIVE

To develop the FuseLinker, a novel link prediction framework for biomedical knowledge graphs (BKGs), which fully exploits the graph's structural, textual and domain knowledge information. We evaluated the utility of FuseLinker in the graph-based drug repurposing task through detailed case studies.

METHODS

FuseLinker leverages fused pre-trained text embedding and domain knowledge embedding to enhance the graph neural network (GNN)-based link prediction model tailored for BKGs. This framework includes three parts: a) obtain text embeddings for BKGs using embedding-visible large language models (LLMs), b) learn the representations of medical ontology as domain knowledge information by employing the Poincaré graph embedding method, and c) fuse these embeddings and further learn the graph structure representations of BKGs by applying a GNN-based link prediction model. We evaluated FuseLinker against traditional knowledge graph embedding models and a conventional GNN-based link prediction model across four public BKG datasets. Additionally, we examined the impact of using different embedding-visible LLMs on FuseLinker's performance. Finally, we investigated FuseLinker's ability to generate medical hypotheses through two drug repurposing case studies for Sorafenib and Parkinson's disease.

RESULTS

By comparing FuseLinker with baseline models on four BKGs, our method demonstrates superior performance. The Mean Reciprocal Rank (MRR) and Area Under receiver operating characteristic Curve (AUROC) for KEGG50k, Hetionet, SuppKG and ADInt are 0.969 and 0.987, 0.548 and 0.903, 0.739 and 0.928, and 0.831 and 0.890, respectively.

CONCLUSION

Our study demonstrates that FuseLinker is an effective novel link prediction framework that integrates multiple graph information and shows significant potential for practical applications in biomedical and clinical tasks. Source code and data are available at https://github.com/YKXia0/FuseLinker.

Message-Passing Monte Carlo: Generating low-discrepancy point sets via graph neural networks

Discrepancy is a well-known measure for the irregularity of the distribution of a point set. Point sets with small discrepancy are called low discrepancy and are known to efficiently fill the space in a uniform manner. Low-discrepancy points play a central role in many problems in science and engineering, including numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation. In this work, we present a machine learning approach to generate a new class of low-discrepancy point sets named Message-Passing Monte Carlo (MPMC) points. Motivated by the geometric nature of generating low-discrepancy point sets, we leverage tools from Geometric Deep Learning and base our model on graph neural networks. We further provide an extension of our framework to higher dimensions, which flexibly allows the generation of custom-made points that emphasize the uniformity in specific dimensions that are primarily important for the particular problem at hand. Finally, we demonstrate that our proposed model achieves state-of-the-art performance superior to previous methods by a significant margin. In fact, MPMC points are empirically shown to be either optimal or near-optimal with respect to the discrepancy for low dimension and small number of points, i.e., for which the optimal discrepancy can be determined.

Few-Shot Relation Extraction With Dual Graph Neural Network Interaction

Recent advances in relation extraction with deep neural architectures have achieved excellent performance. However, current models still suffer from two main drawbacks: 1) they require enormous volumes of training data to avoid model overfitting and 2) there is a sharp decrease in performance when the data distribution during training and testing shift from one domain to the other. It is thus vital to reduce the data requirement in training and explicitly model the distribution difference when transferring knowledge from one domain to another. In this work, we concentrate on few-shot relation extraction under domain adaptation settings. Specifically, we propose DUAL GRAPH, a novel graph neural network (GNN) based approach for few-shot relation extraction. DUAL GRAPH leverages an edge-labeling dual graph (i.e., an instance graph and a distribution graph) to explicitly model the intraclass similarity and interclass dissimilarity in each individual graph, as well as the instance-level and distribution-level relations across graphs. A dual graph interaction mechanism is proposed to adequately fuse the information between the two graphs in a cyclic flow manner. We extensively evaluate DUAL GRAPH on FewRel1.0 and FewRel2.0 benchmarks under four few-shot configurations. The experimental results demonstrate that DUAL GRAPH can match or outperform previously published approaches. We also perform experiments to further investigate the parameter settings and architectural choices, and we offer a qualitative analysis.

Alzheimer's disease diagnosis from multi-modal data via feature inductive learning and dual multilevel graph neural network

Multi-modal data can provide complementary information of Alzheimer's disease (AD) and its development from different perspectives. Such information is closely related to the diagnosis, prevention, and treatment of AD, and hence it is necessary and critical to study AD through multi-modal data. Existing learning methods, however, usually ignore the influence of feature heterogeneity and directly fuse features in the last stages. Furthermore, most of these methods only focus on local fusion features or global fusion features, neglecting the complementariness of features at different levels and thus not sufficiently leveraging information embedded in multi-modal data. To overcome these shortcomings, we propose a novel framework for AD diagnosis that fuses gene, imaging, protein, and clinical data. Our framework learns feature representations under the same feature space for different modalities through a feature induction learning (FIL) module, thereby alleviating the impact of feature heterogeneity. Furthermore, in our framework, local and global salient multi-modal feature interaction information at different levels is extracted through a novel dual multilevel graph neural network (DMGNN). We extensively validate the proposed method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and experimental results demonstrate our method consistently outperforms other state-of-the-art multi-modal fusion methods. The code is publicly available on the GitHub website. (https://github.com/xiankantingqianxue/MIA-code.git).

Pair-EGRET: enhancing the prediction of protein-protein interaction sites through graph attention networks and protein language models

MOTIVATION

Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, accurately predicting protein-protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs.

RESULTS

We present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pretrained transformer-like models to accurately predict PPI sites. Pair-EGRET works on a k-nearest neighbor graph, representing the 3D structure of a protein, and utilizes the cross-attention mechanism for accurate identification of interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we demonstrate that Pair-EGRET can achieve remarkable performance in predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix.

AVAILABILITY AND IMPLEMENTATION

Pair-EGRET is freely available in open source form at the GitHub Repository https://github.com/1705004/Pair-EGRET.

A Weighted GraphSAGE-Based Context-Aware Approach for Big Data Access Control

Context information is the key element to realizing dynamic access control of big data. However, existing context-aware access control (CAAC) methods do not support automatic context awareness and cannot automatically model and reason about context relationships. To solve these problems, this article proposes a weighted GraphSAGE-based context-aware approach for big data access control. First, graph modeling is performed on the access record data set and transforms the access control context-awareness problem into a graph neural network (GNN) node learning problem. Then, a GNN model WGraphSAGE is proposed to achieve automatic context awareness and automatic generation of CAAC rules. Finally, weighted neighbor sampling and weighted aggregation algorithms are designed for the model to realize automatic modeling and reasoning of node relationships and relationship strengths simultaneously in the graph node learning process. The experiment results show that the proposed method has obvious advantages in context awareness and context relationship reasoning compared with similar GNN models. Meanwhile, it obtains better results in dynamic access control decisions than the existing CAAC models.

Rational Design of Earth-Abundant Catalysts toward Sustainability

Catalysis is crucial for clean energy, green chemistry, and environmental remediation, but traditional methods rely on expensive and scarce precious metals. This review addresses this challenge by highlighting the promise of earth-abundant catalysts and the recent advancements in their rational design. Innovative strategies such as physics-inspired descriptors, high-throughput computational techniques, and artificial intelligence (AI)-assisted design with machine learning (ML) are explored, moving beyond time-consuming trial-and-error approaches. Additionally, biomimicry, inspired by efficient enzymes in nature, offers valuable insights. This review systematically analyses these design strategies, providing a roadmap for developing high-performance catalysts from abundant elements. Clean energy applications (water splitting, fuel cells, batteries) and green chemistry (ammonia synthesis, CO2 reduction) are targeted while delving into the fundamental principles, biomimetic approaches, and current challenges in this field. The way to a more sustainable future is paved by overcoming catalyst scarcity through rational design.

Genome analysis through image processing with deep learning models

Genomic sequences are traditionally represented as strings of characters: A (adenine), C (cytosine), G (guanine), and T (thymine). However, an alternative approach involves depicting sequence-related information through image representations, such as Chaos Game Representation (CGR) and read pileup images. With rapid advancements in deep learning (DL) methods within computer vision and natural language processing, there is growing interest in applying image-based DL methods to genomic sequence analysis. These methods involve encoding genomic information as images or integrating spatial information from images into the analytical process. In this review, we summarize three typical applications that use image processing with DL models for genome analysis. We examine the utilization and advantages of these image-based approaches.

Simultaneous Optimization of Discrete and Continuous Parameters Defining a Robot Morphology and Controller

The morphology and controller design of robots is often a labor-intensive task performed by experienced and intuitive engineers. Automatic robot design using machine learning is attracting increasing attention in the hope that it will reduce the design workload and result in better-performing robots. Most robots are created by joining several rigid parts and then mounting actuators and their controllers. Many studies limit the possible types of rigid parts to a finite set to reduce the computational burden. However, this not only limits the search space, but also prohibits the use of powerful optimization techniques. To find a robot closer to the global optimal design, a method that explores a richer set of robots is desirable. In this article, we propose a novel method to efficiently search for various robot designs. The method combines three different optimization methods with different characteristics. We apply proximal policy optimization (PPO) or soft actor-critic (SAC) as the controller, the REINFORCE algorithm to determine the lengths and other numerical parameters of the rigid parts, and a newly proposed method to determine the number and layout of the rigid parts and joints. Experiments with physical simulations confirm that when this method is used to handle two types of tasks-walking and manipulation-it performs better than simple combinations of existing methods. The source code and videos of our experiments are available online (https://github.com/r-koike/eagent).

A topological description of loss surfaces based on Betti Numbers

In the context of deep learning models, attention has recently been paid to studying the surface of the loss function in order to better understand training with methods based on gradient descent. This search for an appropriate description, both analytical and topological, has led to numerous efforts in identifying spurious minima and characterize gradient dynamics. Our work aims to contribute to this field by providing a topological measure for evaluating loss complexity in the case of multilayer neural networks. We compare deep and shallow architectures with common sigmoidal activation functions by deriving upper and lower bounds for the complexity of their respective loss functions and revealing how that complexity is influenced by the number of hidden units, training models, and the activation function used. Additionally, we found that certain variations in the loss function or model architecture, such as adding an ℓ2 regularization term or implementing skip connections in a feedforward network, do not affect loss topology in specific cases.

Advanced 3D Face Reconstruction from Single 2D Images Using Enhanced Adversarial Neural Networks and Graph Neural Networks

This paper presents a novel framework for 3D face reconstruction from single 2D images and addresses critical limitations in existing methods. Our approach integrates modified adversarial neural networks with graph neural networks to achieve state-of-the-art performance. Key innovations include (1) a generator architecture based on Graph Convolutional Networks (GCNs) with a novel loss function and identity blocks, mitigating mode collapse and instability; (2) the integration of facial landmarks and a non-parametric efficient-net decoder for enhanced feature capture; and (3) a lightweight GCN-based discriminator for improved accuracy and stability. Evaluated on the 300W-LP and AFLW2000-3D datasets, our method outperforms existing approaches, reducing Chamfer Distance by 62.7% and Earth Mover's Distance by 57.1% on 300W-LP. Moreover, our framework demonstrates superior robustness to variations in head positioning, occlusion, noise, and lighting conditions while achieving significantly faster processing times.

Unsupervised Machine Learning in the Analysis of Nonadiabatic Molecular Dynamics Simulation

The all-atomic full-dimensional-level simulations of nonadiabatic molecular dynamics (NAMD) in large realistic systems has received high research interest in recent years. However, such NAMD simulations normally generate an enormous amount of time-dependent high-dimensional data, leading to a significant challenge in result analyses. Based on unsupervised machine learning (ML) methods, considerable efforts were devoted to developing novel and easy-to-use analysis tools for the identification of photoinduced reaction channels and the comprehensive understanding of complicated molecular motions in NAMD simulations. Here, we tried to survey recent advances in this field, particularly to focus on how to use unsupervised ML methods to analyze the trajectory-based NAMD simulation results. Our purpose is to offer a comprehensive discussion on several essential components of this analysis protocol, including the selection of ML methods, the construction of molecular descriptors, the establishment of analytical frameworks, their advantages and limitations, and persistent challenges.

Artificial intelligence and machine learning applications for cultured meat

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. In addition, we have included a survey of datasets relevant to CM research. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.

ToxGIN: an In silico prediction model for peptide toxicity via graph isomorphism networks integrating peptide sequence and structure information

Peptide drugs have demonstrated enormous potential in treating a variety of diseases, yet toxicity prediction remains a significant challenge in drug development. Existing models for prediction of peptide toxicity largely rely on sequence information and often neglect the three-dimensional (3D) structures of peptides. This study introduced a novel model for short peptide toxicity prediction, named ToxGIN. The model utilizes Graph Isomorphism Network (GIN), integrating the underlying amino acid sequence composition and the 3D structures of peptides. ToxGIN comprises three primary modules: (i) Sequence processing module, converting peptide 3D structures and sequences into information of nodes and edges; (ii) Feature extraction module, utilizing GIN to learn discriminative features from nodes and edges; (iii) Classification module, employing a fully connected classifier for toxicity prediction. ToxGIN performed well on the independent test set with F1 score = 0.83, AUROC = 0.91, and Matthews correlation coefficient = 0.68, better than existing models for prediction of peptide toxicity. These results validated the effectiveness of integrating 3D structural information with sequence data using GIN for peptide toxicity prediction. The proposed ToxGIN and data can be freely accessible at https://github.com/cihebiyql/ToxGIN.

MLGCN: an ultra efficient graph convolutional neural model for 3D point cloud analysis

With the rapid advancement of 3D acquisition technologies, 3D sensors such as LiDARs, 3D scanners, and RGB-D cameras have become increasingly accessible and cost-effective. These sensors generate 3D point cloud data that require efficient algorithms for tasks such as 3D model classification and segmentation. While deep learning techniques have proven effective in these areas, existing models often rely on complex architectures, leading to high computational costs that are impractical for real-time applications like augmented reality and robotics. In this work, we propose the Multi-level Graph Convolutional Neural Network (MLGCN), an ultra-efficient model for 3D point cloud analysis. The MLGCN model utilizes shallow Graph Neural Network (GNN) blocks to extract features at various spatial locality levels, leveraging precomputed KNN graphs shared across GCN blocks. This approach significantly reduces computational overhead and memory usage, making the model well-suited for deployment on low-memory and low-CPU devices. Despite its efficiency, MLGCN achieves competitive performance in object classification and part segmentation tasks, demonstrating results comparable to state-of-the-art models while requiring up to a thousand times fewer floating-point operations and significantly less storage. The contributions of this paper include the introduction of a lightweight, multi-branch graph-based network for 3D shape analysis, the demonstration of the model's efficiency in both computation and storage, and a thorough theoretical and experimental evaluation of the model's performance. We also conduct ablation studies to assess the impact of different branches within the model, providing valuable insights into the role of specific components.

A photovoltaic cell defect detection model capable of topological knowledge extraction

As the global transition towards clean energy accelerates, the demand for the widespread adoption of solar energy continues to rise. However, traditional object detection models prove inadequate for handling photovoltaic cell electroluminescence (EL) images, which are characterized by high levels of noise. To address this challenge, we developed an advanced defect detection model specifically designed for photovoltaic cells, which integrates topological knowledge extraction. Our approach begins with the introduction of a multi-scale dynamic context-based feature extraction method, capable of generating static context by thoroughly capturing the local texture and structural information of multi-scale defects. This static context is then combined with dynamic context to produce fine-grained local features. Subsequently, we developed a centralized feature pyramid structure, enhanced by spatial semantics, which models the explicit visual center. This structure effectively elucidates the relationship between local and global features in defect images, thereby improving the representation of defect characteristics. Finally, we implemented a feature enhancement strategy grounded in spatial semantic knowledge extraction. This strategy uncovers potential correlations among defect targets by constructing a spatial semantic topology of features, mapping these features to a higher-order representation, and ultimately delivering precise defect detection results.

Contrastive Learning-Based Personalized Tag Recommendation

Personalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately learn the embeddings of users, items, and tags. To address this issue, we propose a contrastive learning-based personalized tag recommendation algorithm, namely CLPTR. Specifically, CLPTR generates augmented views of user-tag and item-tag interaction graphs by injecting noises into implicit feature representations rather than dropping nodes and edges. Hence, CLPTR is able to greatly preserve the underlying semantics of the original user-tag or the item-tag interaction graphs and avoid destroying their structural information. In addition, we integrate the contrastive learning module into a graph neural network-based personalized tag recommendation model, which enables the model to extract self-supervised signals from user-tag and item-tag interaction graphs. We conduct extensive experiments on real-world datasets, and the experimental results demonstrate the state-of-the-art performance of our proposed CLPTR compared with traditional personalized tag recommendation models.

Efficient Multi-View Graph Convolutional Network with Self-Attention for Multi-Class Motor Imagery Decoding

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain-computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding.

Inferring gene regulatory networks with graph convolutional network based on causal feature reconstruction

Inferring gene regulatory networks through deep learning and causal inference methods is a crucial task in the field of computational biology and bioinformatics. This study presents a novel approach that uses a Graph Convolutional Network (GCN) guided by causal information to infer Gene Regulatory Networks (GRN). The transfer entropy and reconstruction layer are utilized to achieve causal feature reconstruction, mitigating the information loss problem caused by multiple rounds of neighbor aggregation in GCN, resulting in a causal and integrated representation of node features. Separable features are extracted from gene expression data by the Gaussian-kernel Autoencoder to improve computational efficiency. Experimental results on the DREAM5 and the mDC dataset demonstrate that our method exhibits superior performance compared to existing algorithms, as indicated by the higher values of the AUPRC metrics. Furthermore, the incorporation of causal feature reconstruction enhances the inferred GRN, rendering them more reasonable, accurate, and reliable.

Foundations of automatic feature extraction at LHC-point clouds and graphs

Deep learning algorithms will play a key role in the upcoming runs of the Large Hadron Collider (LHC), helping bolster various fronts ranging from fast and accurate detector simulations to physics analysis probing possible deviations from the Standard Model. The game-changing feature of these new algorithms is the ability to extract relevant information from high-dimensional input spaces, often regarded as "replacing the expert" in designing physics-intuitive variables. While this may seem true at first glance, it is far from reality. Existing research shows that physics-inspired feature extractors have many advantages beyond improving the qualitative understanding of the extracted features. In this review, we systematically explore automatic feature extraction from a phenomenological viewpoint and the motivation for physics-inspired architectures. We also discuss how prior knowledge from physics results in the naturalness of the point cloud representation and discuss graph-based applications to LHC phenomenology.

Calculating the similarity between prescriptions to find their new indications based on graph neural network

BACKGROUND

Drug repositioning has the potential to reduce costs and accelerate the rate of drug development, with highly promising applications. Currently, the development of artificial intelligence has provided the field with fast and efficient computing power. Nevertheless, the repositioning of traditional Chinese medicine (TCM) is still in its infancy, and the establishment of a reasonable and effective research method is a pressing issue that requires urgent attention. The use of graph neural network (GNN) to compute the similarity between TCM prescriptions to develop a method for finding their new indications is an innovative attempt.

METHODS

This paper focused on traditional Chinese medicine prescriptions containing ephedra, with 20 prescriptions for treating external cough and asthma taken as target prescriptions. The remaining 67 prescriptions containing ephedra were taken as to-be-matched prescriptions. Furthermore, a multitude of data pertaining to the prescriptions, including diseases, disease targets, symptoms, and various types of information on herbs, was gathered from a diverse array of literature sources, such as Chinese medicine databases. Then, cosine similarity and Jaccard coefficient were calculated to characterize the similarity between prescriptions using graph convolutional network (GCN) with a self-supervised learning method, such as deep graph infomax (DGI).

RESULTS

A total of 1340 values were obtained for each of the two calculation indicators. A total of 68 prescription pairs were identified after screening with 0.77 as the threshold for cosine similarity. Following the removal of false positive results, 12 prescription pairs were deemed to have further research value. A total of 5 prescription pairs were screened using a threshold of 0.50 for the Jaccard coefficient. However, the specific results did not exhibit significant value for further use, which may be attributed to the excessive variety of information in the dataset.

CONCLUSIONS

The proposed method can provide reference for finding new indications of target prescriptions by quantifying the similarity between prescriptions. It is expected to offer new insights for developing a scientific and systematic research methodology for traditional Chinese medicine repositioning.

A Predictive Model for Benchmarking the Performance of Algorithms for Fake and Counterfeit News Classification in Global Networks

The pervasive spread of fake news in online social media has emerged as a critical threat to societal integrity and democratic processes. To address this pressing issue, this research harnesses the power of supervised AI algorithms aimed at classifying fake news with selected algorithms. Algorithms such as Passive Aggressive Classifier, perceptron, and decision stump undergo meticulous refinement for text classification tasks, leveraging 29 models trained on diverse social media datasets. Sensors can be utilized for data collection. Data preprocessing involves rigorous cleansing and feature vector generation using TF-IDF and Count Vectorizers. The models' efficacy in classifying genuine news from falsified or exaggerated content is evaluated using metrics like accuracy, precision, recall, and more. In order to obtain the best-performing algorithm from each of the datasets, a predictive model was developed, through which SG with 0.681190 performs best in Dataset 1, BernoulliRBM has 0.933789 in Dataset 2, LinearSVC has 0.689180 in Dataset 3, and BernoulliRBM has 0.026346 in Dataset 4. This research illuminates strategies for classifying fake news, offering potential solutions to ensure information integrity and democratic discourse, thus carrying profound implications for academia and real-world applications. This work also suggests the strength of sensors for data collection in IoT environments, big data analytics for smart cities, and sensor applications which contribute to maintaining the integrity of information within urban environments.