Article
Biochemistry & Molecular Biology
Liyi Yu, Zhaochun Xu, Meiling Cheng, Weizhong Lin, Wangren Qiu, Xuan Xiao
Summary: In this study, a deep learning framework called MSEDDI is proposed to predict drug-drug interaction events by comprehensively considering multi-scale embedding representations of the drug. The experimental results demonstrate that MSEDDI outperforms other existing methods in terms of prediction performance and exhibits stable performance in a broader sample set.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Biology
Zhiqin Zhu, Zheng Yao, Xin Zheng, Guanqiu Qi, Yuanyuan Li, Neal Mazur, Xinbo Gao, Yifei Gong, Baisen Cong
Summary: Drug-target affinity (DTA) prediction is an emerging and effective method in drug development research to evaluate the efficacy and safety of candidate drugs. However, existing DTA prediction models lack information on interactions between molecular substructures, impacting prediction accuracy and interpretability. Therefore, TDGraphDTA is introduced, using Transformer and Diffusion to predict drug-target interactions by incorporating multi-scale information interaction and graph optimization.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biochemical Research Methods
Yang Li, Guanyu Qiao, Keqi Wang, Guohua Wang
Summary: This paper proposes a new model DTI-MGNN based on multi-channel graph convolutional network and graph attention for predicting drug-target interaction. The model combines topological structure and semantic features to improve the representation learning ability of drug-target interactions, and achieves state-of-the-art results on public datasets.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Yue Hu, Ao Qu, Dan Work
Summary: This study addresses the problem of extreme event detection on large-scale transportation networks using origin-destination mobility data. To overcome the challenges of sparse and high-dimensional data, a Context augmented Graph Autoencoder (Con-GAE) model is proposed, which leverages graph embedding and context embedding techniques to capture spatial and temporal patterns. The results show that the proposed Con-GAE method performs well on multiple city-scale datasets.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Dennis Y. Wu, Tsu-Heng Lin, Xin-Ru Zhang, Chia-Pan Chen, Jia-Hui Chen, Hung-Hsuan Chen
Summary: This article presents an empirical study on detecting faulty sensors in a large-scale sensor network. The study compares different models, including rule-based models, traditional machine learning models, deep learning models without graph neural networks (GNNs), and deep learning models with GNNs. The results show that deep learning models with GNNs outperform other models in identifying problematic sensors, and localized versions of these models achieve comparable predictive power to centralized training.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Shijie Ren, Feng Zhou
Summary: This article proposes a multiscale evolving weighted graph convolutional network for PolSAR image classification, demonstrating superior performance and generalization capacity.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Dongin Jung, Misuk Kim, Yoon-Sik Cho
Summary: The rapid growth of digital information has led to a large volume of documents, but the majority lack quality. To address this issue, the authors propose a novel framework that evaluates document quality based on consistency. They model low-quality document detection as a binary classification task and introduce the concept of supernodes to determine document consistency. The proposed scheme has potential applications in fake news detection and document screening with quality evaluations.
Article
Computer Science, Artificial Intelligence
Min Li, Zhenjiang Miao, Yuanyao Lu
Summary: This paper presents a novel LabanFormer model that achieves more effective Labanotation generation through a Multi-Scale Graph Attention network (MS-GAT) and a transformer model with Gated Recurrent Positional Encoding (GRPE). Experimental results show that the proposed model achieves remarkable performance on the automatic Labanotation generation task.
Article
Computer Science, Artificial Intelligence
Weishuai Che, Zhaowei Liu, Yingjie Wang, Jinglei Liu
Summary: The development of the Internet and big data has led to the importance of graphs as a data representation structure. However, as data size increases, graph embedding faces challenges in computational complexity and memory requirements. To address this, this paper proposes a multilevel embedding refinement framework (MERIT) based on large-scale graphs, using spectral distance-constrained graph coarsening algorithms and an improved graph convolutional neural network model. Experimental results show the effectiveness of MERIT, with an average AUROC score 8% higher than other baseline methods.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Youyong Kong, Jiaxing Li, Ke Zhang, Jiasong Wu
Summary: Data augmentation can enhance the generalization performance of neural networks, but it is challenging for graph data due to its irregular non-Euclidean structure. This paper introduces MSSA-Mixup, a novel graph data augmentation method that extends the training distribution through interpolating multi-scale graph representation with self-attention. MSSA-Mixup effectively improves the generalization ability of GNNs, as demonstrated by extensive experiments on benchmark datasets.
PATTERN RECOGNITION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Ning Xu, An-An Liu, Yongkang Wong, Weizhi Nie, Yuting Su, Mohan Kankanhalli
Summary: This paper proposes a multi-scale context modeling method for scene graph inference, which jointly discovers and integrates object-centric and region-centric context information. Experimental results show that this method can achieve competitive performance on three benchmarks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Zixing Li, Chao Yan, Zhen Lan, Dengqing Tang, Xiaojia Xiang
Summary: In this paper, a novel graph-based multi-scale convolutional recurrent attention model is proposed for subject-independent ERP detection, achieving high precision by learning frequency representations and extracting spatial features.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2022)
Article
Computer Science, Theory & Methods
Zhao Li, Yuying Xing, Jiaming Huang, Haobo Wang, Jianliang Gao, Guoxian Yu
Summary: This paper presents a novel attention-based Heterogeneous Multi-view Graph Neural Network (aHMGNN) to tackle the two challenges faced by traditional GNN frameworks, with efficiency and effectiveness verified through experiments and real-world application in a large e-commerce platform.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Yangmei Shen, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong
Summary: In this paper, a multi-scale graph convolutional network based on the spectral graph wavelet frame is proposed to improve multi-scale representation learning through flexible utilization of multi-scale neighboring information to enhance discrimination and ensure stable feature extraction. The network achieved state-of-the-art performance in extensive experiments on citation networks, bioinformatics graphs, and social networks, showcasing its effectiveness in practical applications.
IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS
(2021)
Article
Computer Science, Artificial Intelligence
Yanxiong Li, Zhongjie Jiang, Wenchang Cao, Qisheng Huang
Summary: This paper proposes a speaker verification method called Attentive Multi-scale Convolutional Recurrent Network (AMCRN), which can obtain both local spatial information and global sequential information from input speech recordings. The method extracts logarithm Mel spectrum from each speech recording and feeds it to AMCRN for learning speaker embedding. The learned speaker embedding is then used for scoring by a back-end classifier such as cosine similarity metric in the testing stage. The proposed method is compared with state-of-the-art methods and shows better performance in terms of equal error rate, minimal detection cost function, computational complexity, memory requirement, and generalization ability.
APPLIED SOFT COMPUTING
(2022)
Article
Biochemical Research Methods
Amin Allahyar, Jeroen de Ridder
Article
Biochemical Research Methods
Erdogan Taskesen, Sepideh Babaei, Marcel M. J. Reinders, Jeroen de Ridder
BMC BIOINFORMATICS
(2015)
Article
Multidisciplinary Sciences
Sepideh Babaei, Waseem Akhtar, Johann de Jong, Marcel Reinders, Jeroen de Ridder
NATURE COMMUNICATIONS
(2015)
Article
Biochemical Research Methods
Sepideh Babaei, Ahmed Mahfouz, Marc Hulsman, Boudewijn P. F. Lelieveldt, Jeroen de Ridder, Marcel Reinders
PLOS COMPUTATIONAL BIOLOGY
(2015)
Article
Biochemical Research Methods
Dick de Ridder, Jeroen de Ridder, Marcel J. T. Reinders
BRIEFINGS IN BIOINFORMATICS
(2013)
Article
Biochemistry & Molecular Biology
Waseem Akhtar, Johann de Jong, Alexey V. Pindyurin, Ludo Pagie, Wouter Meuleman, Jeroen de Ridder, Anton Berns, Lodewyk F. A. Wessels, Maarten van Lohuizen, Bas van Steensel
Article
Multidisciplinary Sciences
Martin A. Rijlaarsdam, David M. J. Tax, Ad J. M. Gillis, Lambert C. J. Dorssers, Devin C. Koestler, Jeroen de Ridder, Leendert H. J. Looijenga
Article
Biochemical Research Methods
Jeroen de Ridder, Yana Bromberg, Magali Michaut, Venkata P. Satagopam, Manuel Corpas, Geoff Macintyre, Theodore Alexandrov
PLOS COMPUTATIONAL BIOLOGY
(2013)
Editorial Material
Biochemical Research Methods
Jeroen de Ridder, Thomas Abeel, Magali Michaut, Venkata P. Satagopam, Nils Gehlenborg
PLOS COMPUTATIONAL BIOLOGY
(2013)
Editorial Material
Biochemical Research Methods
Jeroen de Ridder, Pieter Meysman, Olugbenga Oluwagbemi, Thomas Abeel
PLOS COMPUTATIONAL BIOLOGY
(2014)
Article
Genetics & Heredity
Johann de Jong, Waseem Akhtar, Jitendra Badhai, Alistair G. Rust, Roland Rad, John Hilkens, Anton Berns, Maarten van Lohuizen, Lodewyk F. A. Wessels, Jeroen de Ridder
Article
Genetics & Heredity
Camille A. Huser, Kathryn L. Gilroy, Jeroen de Ridder, Anna Kilbey, Gillian Borland, Nancy Mackay, Alma Jenkins, Margaret Bell, Pawel Herzyk, Louise van der Weyden, David J. Adams, Alistair G. Rust, Ewan Cameron, James C. Neil
Article
Biology
Alexandra Danyi, Myrthe Jager, Jeroen de Ridder
Summary: This study introduces an improved method to address the sparsity in liquid biopsy data, achieving higher accuracy by data augmentation and integration. The results pave the way for the application of machine learning in detecting the cell of origin of cancer from liquid biopsy data.
Proceedings Paper
Computer Science, Information Systems
Sepideh Babaei, Erik van den Akker, Jeroen de Ridder, Marcel Reinders
PATTERN RECOGNITION IN BIOINFORMATICS
(2011)