ICAI 2024 Poster Access

Identification of Membrane Protein Types via Deep Residual Hypergraph Neural Network, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Jiyun Shen, Zhiqiang Hui, and Long Cheng
Abstract: Membrane protein's functions are significantly associated with its type. So it is crucial to identify the types of membrane proteins. Conventional computational methods for identifying the species of membrane proteins tend to ignore two issues: high-order correlation among membrane proteins and the scenarios of multi-modal representations of membrane proteins, which leads to information loss. To tackle those two issues, we propose a deep residual hypergraph neural network DRHGNN which enhances the hypergraph neural network with initial residual and identity mapping in this paper. We carry out extensive experiments on four benchmark datasets of membrane proteins. In the meantime, we compare DRHGNN with recently developed advanced methods. Experimental results show the better performance of DRHGNN on membrane protein classification task on four datasets. Experiments also show that DRHGNN can handle the over-smoothing issue with the increase of the number of model layers compared with hypergraph neural network HGNN .
Keyword: Hypergraph neural network Initial residual Identity mapping Identification Membrane protein
Cite
@inproceedings{ICAI_2024,
    author = {Jiyun Shen, Zhiqiang Hui, and Long Cheng},
    title = {Identification of Membrane Protein Types via Deep Residual Hypergraph Neural Network},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {1-4}
}

Application of DNA-Binding Protein Prediction Based on Graph Convolutional Network and Contact Map, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Zhiqiang Hui and Nan Zhou
Abstract: DNA contains the genetic information for the synthesis of proteins and RNA, and it is an indispensable substance in living organisms. DNA-binding proteins are an enzyme, which can bind with DNA to produce complex proteins, and play an important role in the functions of a variety of biological molecules. With the continuous development of deep learning, the introduction of deep learning into DNA-binding proteins for prediction is conducive to improving the speed and accuracy of DNA-binding protein recognition. In this study, the features and structures of proteins were used to obtain their representations through graph convolutional networks. A protein prediction model based on graph convolutional network and contact map was proposed. The method had some advantages by testing various indexes of PDB14189 and PDB2272 on the benchmark dataset.
Keyword: proteins,graph convolutional network,contact map
Cite
@inproceedings{ICAI_2024,
    author = {Zhiqiang Hui and Nan Zhou},
    title = {Application of DNA-Binding Protein Prediction Based on Graph Convolutional Network and Contact Map},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {41-51}
}

Identification of Membrane Protein Types Based Using Hypergraph Neural Network , ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Zhiqiang Hui and Meiling Qian
Abstract: Membrane proteins are an essential part of the body’s ability to maintain normal life activities. Further research into membrane proteins, which are present in all aspects of life science research, will help to advance the development of cells and drugs. The current methods for predicting proteins are usually based on machine learning, but further improvements in prediction effectiveness and accuracy are needed. In this paper, we propose a dynamic deep network architecture based on lifelong learning in order to use computers to classify membrane proteins more effectively. The model extends the application area of lifelong learning and provides new ideas for multiple classiﬁcation problems in bioinformatics. To demonstrate the performance of our model, we conducted experiments on top of two datasets and compared them with other classiﬁcation methods. The results show that our model achieves high accuracy 95.3 and 93.5 on benchmark datasets and is more effective compared to other methods.
Keyword: lifelong learning, membrane proteins, dynamically scalable networks,position speciﬁc scoring matrix, evolutionary features
Cite
@inproceedings{ICAI_2024,
    author = {Zhiqiang Hui and Meiling Qian},
    title = {Identification of Membrane Protein Types Based Using Hypergraph Neural Network },
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {51-54}
}

Boosting Drug-Target Binding Affinity Predictions with a Novel Three-Branch Convolutional Neural Network Approach, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Yaoyao Lu and Hongjie Wu
Abstract: The process of discovering new drugs is costly and time-consuming, with safety concerns often arising. Deep learning has become a mainstream ap-proach in computer-aided drug design, with convolutional neural networks CNN and graph neural networks GNN playing a significant role in drug-target affinity DTA prediction. This paper introduces a novel method for predicting DTA using a combination of graph convolutional networks and a three-branch multiscale CNN, leading to significant improvements in predic-tion accuracy.
Keyword: Drug-Target Binding Affinity Predictions.
Cite
@inproceedings{ICAI_2024,
    author = {Yaoyao Lu and Hongjie Wu},
    title = {Boosting Drug-Target Binding Affinity Predictions with a Novel Three-Branch Convolutional Neural Network Approach},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {54-63}
}

Predicting DNA-Binding Proteins through Advanced Deep Transfer Learning Techniques, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Jun Yan and Hongjie Wu
Abstract: DNA-binding proteins DBPs are crucial in gene-related life activities. Tra-ditional methods for DBP prediction are labor-intensive and costly. We pre-sent a novel method using deep transfer learning to predict DBPs efficiently. Our approach extracts sequence and PSSM features, employs transfer learn-ing algorithms to construct datasets, and uses an attention mechanism-equipped neural network for prediction.
Keyword: DNA-binding proteins.
Cite
@inproceedings{ICAI_2024,
    author = {Jun Yan and Hongjie Wu},
    title = {Predicting DNA-Binding Proteins through Advanced Deep Transfer Learning Techniques},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {63-72}
}

Leveraging Local Protein Structures for Enhanced Drug-Target Binding Affinity Predictions Using Deep Learning Techniques, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Runhua Zhang and Hongjie Wu
Abstract: The traditional drug discovery process is both time-consuming and costly. Utilizing artificial intelligence to predict drug-target binding affinity DTA has become a crucial approach for accelerating new drug discovery. This study introduces a novel deep learning-based method that incorporates both the primary and secondary structures of proteins to better represent the local and global features of proteins. We employ convolutional neural networks CNNs and graph neural networks GNNs to model proteins and drugs sep-arately, capturing their interactions more effectively. Our method demon-strated improved performance in predicting DTA compared to state-of-the-art methods on two benchmark datasets.
Keyword: Drug-Target Binding Affinity Prediction.
Cite
@inproceedings{ICAI_2024,
    author = {Runhua Zhang and Hongjie Wu},
    title = {Leveraging Local Protein Structures for Enhanced Drug-Target Binding Affinity Predictions Using Deep Learning Techniques},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {72-79}
}

Advancing Identification of DNA-Protein Binding Residues Using Deep Learning Techniques, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Haipeng Zhao and Hongjie Wu
Abstract: Accurate identification of DNA-protein binding sites is vital for understanding biological processes and facilitating drug discovery. This study introduces a novel method that inte-grates a Transformer encoder with Bi-directional Long Short-Term Memory BiLSTM to predict DNA-protein binding residues effectively. The method enriches protein representa-tion by combining evolutionary information from the position-specific scoring matrix PSSM with spatial information from predicted secondary structures. Experimental results demonstrate the method's competitiveness, achieving an MCC of 0.349, SP of 96.50 , SN of 44.03 , and ACC of 94.59 on the PDNA-41 dataset.
Keyword: DNA-Protein Binding.
Cite
@inproceedings{ICAI_2024,
    author = {Haipeng Zhao and Hongjie Wu},
    title = {Advancing Identification of DNA-Protein Binding Residues Using Deep Learning Techniques},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {79-88}
}

Improving Drug-Target Interaction Predictions Through an Explainable Graph Transformer Model, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Baozhong Zhu and Hongjie Wu
Abstract: Drug discovery is a complex and time-consuming process. Identifying drug-target interac-tions DTIs is crucial for early-stage drug development. This study introduces a novel mod-el for DTI prediction that leverages protein binding sites and self-attention mechanisms. The model achieves high performance in DTI prediction and provides interpretability by identifying protein regions interacting with ligands.
Keyword: Drug-target Interaction Prediction.
Cite
@inproceedings{ICAI_2024,
    author = {Baozhong Zhu and Hongjie Wu},
    title = {Improving Drug-Target Interaction Predictions Through an Explainable Graph Transformer Model},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {88-95}
}

SGC-based Anomaly Detection for Multivariate Time Series, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Kewei Hu, Qiang Tian, Biao Wang, Jiakun Wu, and He Li
Abstract: In industrial facilities or IT systems, there are lots of multivariate time series generated from various metrics. Anomaly detection in multivariate time series is of great importance in applications such as fault diagnosis and root cause discovery. Recently, some unsupervised methods have made great progress in this task, especially the reconstruction architecture of autoencoders AEs , learning normal distribution, and producing a significant error for anomalies. Although AEs can reconstruct subtle abnormal patterns well with the powerful generalization ability, it also leads to a high false negative. Moreover, these AE-based models ignore the dependence among variables at different time scales. In this paper, we propose an enhanced anomaly detection framework that builds upon the Multiscale Wavelet Graph Autoencoder MEGA by substituting the Graph Convolutional Network GCN with Simplified Graph Convolution SGC to augment the model's performance. The core idea is to leverage the spectral methods of SGC to process the multivariate time series data obtained by integrating Discrete Wavelet Transform DWT into the AE. Experiments have been conducted on three public multivariate time-series anomaly detection datasets. The results indicate that the improved model utilizing SGC performs comparably to MEGA, yet in certain scenarios, it may provide slightly better outcomes.
Keyword: Anomaly detection · discrete wavelet transform DWT · simple graph convolution SGC · multivariate time series.
Cite
@inproceedings{ICAI_2024,
    author = { Kewei Hu, Qiang Tian, Biao Wang, Jiakun Wu, and He Li},
    title = {SGC-based Anomaly Detection for Multivariate Time Series},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {4-15}
}

An Inferential Graph Convolution Network for Explaining Traffic Congestion, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Qing Zhai, Jiayi Chen, Yifan Yin, Zi’ang Yang, and He Li
Abstract: Due to the growth of vehicles, traffic congestion is becoming increasingly serious. However, existing methods are used for predicting traffic congestion, which cannot been applied for evaluating traffic congestion. In this paper, we propose an Interpretable Graph Convolution Network called ShapGCN for explaining the reason of traffic congestion by considering its physical and semantic neighbors. Specifically, we first design the physical neighbor embedding and semantic neighbor embedding to collectively encode complex extern factors as well as the complex traffic cascade pattern. To interprete traffic congestion in a complex traffic cascade environment, we use the approximation of shapley value to comprehensively quantify the discovered regions and their importance score. We conduct extensive experiments on the real traffic dataset. The experiment results show our ShapGCN can well explain the reason of traffic congestion.
Keyword: Traffic Congestion Prediction · Graph Convolution Net work GCN · Explainable Analysis.
Cite
@inproceedings{ICAI_2024,
    author = { Qing Zhai, Jiayi Chen, Yifan Yin, Zi’ang Yang, and He Li},
    title = {An Inferential Graph Convolution Network for Explaining Traffic Congestion},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {15-27}
}

Dynamic Group Link Prediction in Continuous-Time Interaction Network, ICAI 2024 Posters, Zhengzhou, China, November 22-25, 2024
Authors: Shijie Luo, He Li, Xuejiao Li, and Tian Tian
Abstract: Recently, group link prediction has received increasing attention due to its important role in analyzing relationships between individuals and groups. However, most existing group link prediction methods emphasize static settings or only make cursory exploitation of historical information, so they fail to obtain good performance in dynamic applications. To this end, we attempt to solve the group link prediction problem in continuous-time dynamic scenes with fine-grained temporal information. We propose a novel continuous-time group link prediction method CTGLP to capture the patterns of future link formation between individuals and groups. A new graph neural network CTGNN is presented to learn the latent representations of individuals by biasedly aggregating neighborhood information. Moreover, we design an importance-based group modeling function to model the embedding of a group based on its known members. CTGLPeventually learns a probability distribution and predicts the link target. Experimental results on various datasets with and without unseen nodes show that CTGLP outperforms the state-of-the-art methods by 13.4 and 13.2 on average.
Keyword: Group Link Prediction · Continuous-Time Interaction Net work · Graph Neural Network GNN
Cite
@inproceedings{ICAI_2024,
    author = {Shijie Luo, He Li, Xuejiao Li, and Tian Tian},
    title = {Dynamic Group Link Prediction in Continuous-Time Interaction Network},
    booktitle = {Proceedings of the International Conference on Artificial Intelligence (ICAI 2024)},
    month = November,
    date = 22-25,
    year = 2024,
    address = {Zhengzhou, China},
    pages = {27-41}
}