Fusing graph transformer with multi-aggregate GCN for enhanced drug-disease associations prediction.

BACKGROUND: Identification of potential drug-disease associations is important for both the discovery of new indications for drugs and for the reduction of unknown adverse drug reactions. Exploring the potential links between drugs and diseases is crucial for advancing biomedical research and improving healthcare. While advanced computational techniques play a vital role in revealing the connections between drugs and diseases, current research still faces challenges in the process of mining potential relationships between drugs and diseases using heterogeneous network data. RESULTS: In this study, we propose a learning framework for fusing Graph Transformer Networks and multi-aggregate graph convolutional network to learn efficient heterogenous information graph representations for drug-disease association prediction, termed WMAGT. This method extensively harnesses the capabilities of a robust graph transformer, effectively modeling the local and global interactions of nodes by integrating a graph convolutional network and a graph transformer with self-attention mechanisms in its encoder. We first integrate drug-drug, drug-disease, and disease-disease networks to construct heterogeneous information graph. Multi-aggregate graph convolutional network and graph transformer are then used in conjunction with neural collaborative filtering module to integrate information from different domains into highly effective feature representation. CONCLUSIONS: Rigorous cross-validation, ablation studies examined the robustness and effectiveness of the proposed method. Experimental results demonstrate that WMAGT outperforms other state-of-the-art methods in accurate drug-disease association prediction, which is beneficial for drug repositioning and drug safety research.

Accurate prediction of drug combination risk levels based on relational graph convolutional network and multi-head attention.

BACKGROUND: Accurately identifying the risk level of drug combinations is of great significance in investigating the mechanisms of combination medication and adverse reactions. Most existing methods can only predict whether there is an interaction between two drugs, but cannot directly determine their accurate risk level. METHODS: In this study, we propose a multi-class drug combination risk prediction model named AERGCN-DDI, utilizing a relational graph convolutional network with a multi-head attention mechanism. Drug-drug interaction events with varying risk levels are modeled as a heterogeneous information graph. Attribute features of drug nodes and links are learned based on compound chemical structure information. Finally, the AERGCN-DDI model is proposed to predict drug combination risk level based on heterogenous graph neural network and multi-head attention modules. RESULTS: To evaluate the effectiveness of the proposed method, five-fold cross-validation and ablation study were conducted. Furthermore, we compared its predictive performance with baseline models and other state-of-the-art methods on two benchmark datasets. Empirical studies demonstrated the superior performances of AERGCN-DDI. CONCLUSIONS: AERGCN-DDI emerges as a valuable tool for predicting the risk levels of drug combinations, thereby aiding in clinical medication decision-making, mitigating severe drug side effects, and enhancing patient clinical prognosis.

MFCF-Gait: Small Silhouette-Sensitive Gait Recognition Algorithm Based on Multi-Scale Feature Cross-Fusion.

Gait recognition based on gait silhouette profiles is currently a major approach in the field of gait recognition. In previous studies, models typically used gait silhouette images sized at 64 × 64 pixels as input data. However, in practical applications, cases may arise where silhouette images are smaller than 64 × 64, leading to a loss in detail information and significantly affecting model accuracy. To address these challenges, we propose a gait recognition system named Multi-scale Feature Cross-Fusion Gait (MFCF-Gait). At the input stage of the model, we employ super-resolution algorithms to preprocess the data. During this process, we observed that different super-resolution algorithms applied to larger silhouette images also affect training outcomes. Improved super-resolution algorithms contribute to enhancing model performance. In terms of model architecture, we introduce a multi-scale feature cross-fusion network model. By integrating low-level feature information from higher-resolution images with high-level feature information from lower-resolution images, the model emphasizes smaller-scale details, thereby improving recognition accuracy for smaller silhouette images. The experimental results on the CASIA-B dataset demonstrate significant improvements. On 64 × 64 silhouette images, the accuracies for NM, BG, and CL states reached 96.49%, 91.42%, and 78.24%, respectively. On 32 × 32 silhouette images, the accuracies were 94.23%, 87.68%, and 71.57%, respectively, showing notable enhancements.

HRYNet: A Highly Robust YOLO Network for Complex Road Traffic Object Detection.

Object detection is a crucial component of the perception system in autonomous driving. However, the road scene presents a highly intricate environment where the visibility and characteristics of traffic targets are susceptible to attenuation and loss due to various complex road scenarios such as lighting conditions, weather conditions, time of day, background elements, and traffic density. Nevertheless, the current object detection network must exhibit more learning capabilities when detecting such targets. This also exacerbates the loss of features during the feature extraction and fusion process, significantly compromising the network's detection performance on traffic targets. This paper presents a novel methodology by which to overcome the concerns above, namely HRYNet. Firstly, a dual fusion gradual pyramid structure (DFGPN) is introduced, which employs a two-stage gradient fusion strategy to enhance the generation of more comprehensive multi-scale high-level semantic information, strengthen the interconnection between non-adjacent feature layers, and reduce the information gap that exists between them. HRYNet introduces an anti-interference feature extraction module, the residual multi-head self-attention mechanism (RMA). RMA enhances the target information by implementing a characteristic channel weighting policy, thereby reducing background interference and improving the attention capability of the network. Finally, the detection performance of HRYNet was evaluated by utilizing three datasets: the horizontally collected dataset BDD1000K, the UAV high-altitude dataset Visdrone, and a custom dataset. Experimental results demonstrate that HRYNet achieves a higher mAP_0.5 compared with YOLOv8s on the three datasets, with increases of 10.8%, 16.7%, and 5.5%, respectively. To optimize HRYNet for mobile devices, this study presents Lightweight HRYNet (LHRYNet), which effectively reduces the number of model parameters by 2 million. The results demonstrate that LHRYNet outperforms YOLOv8s in terms of mAP_0.5, with improvements of 6.7%, 10.9%, and 2.5% observed on the three datasets, respectively.

Mixing states and secondary formation processes of organic nitrogen-containing single particles in Guangzhou, China.

Organic nitrogen (ON) compounds play a significant role in the light absorption of brown carbon and the formation of organic aerosols, however, the mixing state, secondary formation processes, and influencing factors of ON compounds are still unclear. This paper reports on the mixing state of ON-containing particles based on measurements obtained using a high-performance single particle aerosol mass spectrometer in January 2020 in Guangzhou. The ON-containing particles accounted for 21% of the total detected single particles, and the particle count and number fraction of the ON-containing particles were two times higher at night than during the day. The prominent increase in the content of ON-containing particles with the enhancement of NOx mainly occurred at night, and accompanied by high relative humidity and nitrate, which were associated with heterogeneous reactions between organics and gaseous NOx and/or NO3 radical. The synchronous decreases in ON-containing particles and the mass absorption coefficient of water-soluble extracts at 365 nm in the afternoon may be associated with photo-bleaching of the ON species in the particles. In addition, the positive matrix factorization analysis found five factors dominated the formation processes of ON particles, and the nitrate factor (33%) mainly contributed to the production of ON particles at night. The results of this study provide unique insights into the mixing states and secondary formation processes of the ON-containing particles.

Cross-View Gait Recognition Method Based on Multi-Teacher Joint Knowledge Distillation.

Aiming at challenges such as the high complexity of the network model, the large number of parameters, and the slow speed of training and testing in cross-view gait recognition, this paper proposes a solution: Multi-teacher Joint Knowledge Distillation (MJKD). The algorithm employs multiple complex teacher models to train gait images from a single view, extracting inter-class relationships that are then weighted and integrated into the set of inter-class relationships. These relationships guide the training of a lightweight student model, improving its gait feature extraction capability and recognition accuracy. To validate the effectiveness of the proposed Multi-teacher Joint Knowledge Distillation (MJKD), the paper performs experiments on the CASIA_B dataset using the ResNet network as the benchmark. The experimental results show that the student model trained by Multi-teacher Joint Knowledge Distillation (MJKD) achieves 98.24% recognition accuracy while significantly reducing the number of parameters and computational cost.

On-Demand Design of Metasurfaces through Multineural Network Fusion.

In this paper, a multineural network fusion freestyle metasurface on-demand design method is proposed. The on-demand design method involves rapidly generating corresponding metasurface patterns based on the user-defined spectrum. The generated patterns are then input into a simulator to predict their corresponding S-parameter spectrogram, which is subsequently analyzed against the real S-parameter spectrogram to verify whether the generated metasurface patterns meet the desired requirements. The methodology is based on three neural network models: a Wasserstein Generative Adversarial Network model with a U-net architecture (U-WGAN) for inverse structural design, a Variational Autoencoder (VAE) model for compression, and an LSTM + Attention model for forward S-parameter spectrum prediction validation. The U-WGAN is utilized for on-demand reverse structural design, aiming to rapidly discover high-fidelity metasurface patterns that meet specific electromagnetic spectrum responses. The VAE, as a probabilistic generation model, serves as a bridge, mapping input data to latent space and transforming it into latent variable data, providing crucial input for a forward S-parameter spectrum prediction model. The LSTM + Attention network, acting as a forward S-parameter spectrum prediction model, can accurately and efficiently predict the S-parameter spectrum corresponding to the latent variable data and compare it with the real spectrum. In addition, the digits "0" and "1" are used in the design to represent vacuum and metallic materials, respectively, and a 10 × 10 cell array of freestyle metasurface patterns is constructed. The significance of the research method proposed in this paper lies in the following: (1) The freestyle metasurface design significantly expands the possibility of metamaterial design, enabling the creation of diverse metasurface structures that are difficult to achieve with traditional methods. (2) The on-demand design approach can generate high-fidelity metasurface patterns that meet the expected electromagnetic characteristics and responses. (3) The fusion of multiple neural networks demonstrates high flexibility, allowing for the adjustment of network structures and training methods based on specific design requirements and data characteristics, thus better accommodating different design problems and optimization objectives.

A Small Object Detection Algorithm Based on Modulated Deformable Convolution and Large Kernel Convolution.

Object detection is one of the most critical areas in computer vision, and it plays an essential role in a variety of practice scenarios. However, small object detection has always been a key and difficult problem in the field of object detection. Therefore, considering the balance between the effectiveness and efficiency of the small object detection algorithm, this study proposes an improved YOLOX detection algorithm (BGD-YOLOX) to improve the detection effect of small objects. We present the BigGhost module, which combines the Ghost model with a modulated deformable convolution to optimize the YOLOX for greater accuracy. At the same time, it can reduce the inference time by reducing the number of parameters and the amount of computation. The experimental results show that BGD-YOLOX has a higher average accuracy rate in terms of small target detection, with mAP0.5 up to 88.3% and mAP0.95 up to 56.7%, which surpasses the most advanced object detection algorithms such as EfficientDet, CenterNet, and YOLOv4.

Long-Term Observation of Mixing States and Sources of Vanadium-Containing Single Particles from 2020 to 2021 in Guangzhou, China.

The distribution of vanadium (V) in aerosols is commonly used to track ship exhaust emissions, yet the atmospheric abundance of V has been greatly reduced due to the implementation of a clean fuel policy. Recent research mainly discussed the chemical compositions of ship-related particles during specific events, yet few studies focus on the long-term changes of V in the atmosphere. In this study, a single-particle aerosol mass spectrometer was used to measure V-containing particles from 2020 to 2021 in Huangpu Port in Guangzhou, China. The long-term trend of the particle counts of V-containing particles declined annually, but the relative abundance of V-containing particles in the total single particles increased in summer due to the influence of ship emissions. Positive matrix factorization revealed that in June and July 2020, 35.7% of the V-containing particles were from ship emissions, followed by dust and industrial emissions. Furthermore, more than 80% of the V-containing particles were found mixing with sulfate and 60% of the V-containing particles were found mixing with nitrate, suggesting that the majority of the V-containing particles were secondary particles processed during the transport of ship emissions to urban areas. Compared with the small changes in the relative abundance of sulfate in the V-containing particles, the relative abundance of nitrate exhibited clear seasonal variations, with a high abundance in winter. This may have been due to the increased production of nitrate from high concentrations of precursors and a suitable chemical environment. For the first time, the long-term trends of V-containing particles in two years are investigated to demonstrate changes in their mixing states and sources after the clean fuel policy, and to suggest the cautious application of V as an indicator of ship emissions.

Insights into the different mixing states and formation processes of amine-containing single particles in Guangzhou, China.

The formation processes of particulate amines are closely related to their emission sources and secondary reactions, which can be revealed through the investigation of their real-time mixing states in individual particles. The mixing states of methylamine (MA)-, trimethylamine (TMA)-, and diethylamine (DEA)-containing particles were studied using a high-performance single particle aerosol mass spectrometer (HP-SPAMS) in Guangzhou, China, in January 2020. The sharp increase in TMA particles was found to be closely associated with the increase in the ambient relative humidity (RH), while the MA- and DEA-containing particles were not similarly influenced by the changes in the RH. The prominent enrichment of secondary oxygenated organics in DEA particles during the daytime was consistent with the active period of photochemistry, implying that the sharp decrease in DEA particles in the afternoon was likely due to photo-oxidation of the DEA. The number fraction (Nf) of DEA particles, the Nf of the nitrate in the DEA particles, and the abundance of nitrate increased as the NOx content all increased during the nighttime, suggesting that the formation of DEA·HNO3 salt was the dominant pathway of particulate DEA production. These results are consistent with our previous measurements in Nanjing, confirming the general and distinct mixing states of TMA and DEA particles. Positive matrix factorization analysis revealed that the total fraction of the more oxidized organics factor and the less oxidized organics factor were much higher in the DEA particles (26.9 %) than in the TMA particles (9 %), confirming the significant enrichment of oxygenated species in the DEA particles. The different mixing states of the amines revealed the unique response of each type of amine to the same atmospheric environment, and the prominent mixing states of the DEA with secondary oxygenated species suggest the potential role of DEA in tracing the evolution of organic aerosols.