Article
Computer Science, Artificial Intelligence
Thanh Toan Nguyen, Minh Tam Pham, Thanh Tam Nguyen, Thanh Trung Huynh, Van Vinh Tong, Quoc Viet Hung Nguyen, Thanh Tho Quan
Summary: The study introduces a novel network alignment framework NAWAL, emphasizing on unsupervised embedding of structural information. By capturing the structural relationships between nodes, alignment of networks is achieved without relying on pre-defined anchor links.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Patrick Keller, Abdoul Kader Kabore, Laura Plein, Jacques Klein, Yves Le Traon, Tegawende F. Bissyande
Summary: This research proposes a novel embedding approach called WySiWiM, which leverages the visual patterns in source code and utilizes pre-trained image classification neural networks for transfer learning. The evaluation on various tasks demonstrates that the WySiWiM approach performs as effectively as state-of-the-art methods.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2022)
Article
Biochemical Research Methods
Lingling Zhao, Huiting Sun, Xinyi Cao, Naifeng Wen, Junjie Wang, Chunyu Wang
Summary: This paper proposes a novel representation model for GO terms, named GT2Vec, which considers both the GO graph structure obtained by graph contrastive learning and the semantic description of GO terms based on BERT encoders. Experimental results demonstrate the effectiveness of the model in learning vector representations for GO terms.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Ning An, Meng Chen, Li Lian, Peng Li, Kai Zhang, Xiaohui Yu, Yilong Yin
Summary: This study focuses on the interpretability of venue representations and proposes two novel models, CEM and XEM, which can generate easy-to-understand venue representations. Experimental results demonstrate that the interpretability introduced to the venue representations improves the performance of various downstream tasks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Qi Luo, Dongxiao Yu, Akshita Maradapu Vera Venkata Sai, Zhipeng Cai, Xiuzhen Cheng
Summary: Social networks have a wide range of applications, and the analysis of these applications has attracted a lot of attention from the research community. However, the high dimensionality of social network data presents a challenge in its analysis, known as the curse of dimensionality. Representation learning offers a solution by learning low-dimensional vector representations of high-dimensional network data while preserving network structural information. These representations can be utilized in various network-based applications.
Article
Computer Science, Information Systems
Hongchan Li, Zhuang Zhu, Haodong Zhu, Baohua Jin
Summary: The purpose of entity alignment for knowledge graphs is to find pairs of entities that represent the same real-world object from different knowledge graphs. In recent years, techniques for knowledge fusion using entity alignment have gained attention. This article proposes a method for entity alignment using truncated negative sampling with attribute character embedding. The method utilizes relationship and attribute data in heterogeneous knowledge graphs to perform entity alignment.
Article
Computer Science, Artificial Intelligence
Wenqiang Liu, Hongyun Cai, Xu Cheng, Sifa Xie, Yipeng Yu, Dukehyzhang
Summary: The goal of representation learning of knowledge graph is to encode entities and relations into a low-dimensional embedding space. Existing methods have limitations in expressing high-order structural relationships between entities and utilizing attribute triples. To overcome these limitations, this paper proposes a novel method named KANE, which captures high-order structural and attribute information of knowledge graphs using graph convolutional networks. Experimental results show that KANE outperforms other methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Review
Biochemical Research Methods
Maxat Kulmanov, Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf
Summary: Ontologies have been widely used in the life sciences to formalize domain knowledge. Recently, there has been an increasing trend in using ontologies to provide background knowledge in similarity-based analysis and machine learning models. The methods of combining ontologies with machine learning are still novel and actively being developed.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Computer Science, Information Systems
Xiaofeng Ding, Tieyong Zeng, Jian Tang, Zhengping Che, Yaxin Peng
Summary: This paper proposes a novel semantic representation (SR) module for extracting semantic information in semantic segmentation tasks. The module enhances the representation ability of semantic context by utilizing global semantic information and improves the consistency of intraclass features by aggregating global features. Additionally, the SR module can be extended to build a semantic representation refinement network for enhancing the structural reasoning of the model through multiple-scale iterations.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Plant Sciences
Xingsi Xue, Pei-Wei Tsai
Summary: This study proposes an Adaptive Compact Evolutionary Algorithm (ACEA) to address the problem of aligning ecology and biodiversity ontologies. By utilizing semantic reasoning and optimization techniques, the algorithm improves performance and achieves better results compared to other aligning techniques in experiments.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Computer Science, Theory & Methods
Ruiqi Li, Xiang Zhao, Marie-Francine Moens
Summary: This survey summarizes the current universal sentence-embedding methods, categorizes them into four groups, and analyzes their performance. Different training schemes for sentence embeddings lead to different performance patterns, and incentive strategies and future research directions are proposed.
ACM COMPUTING SURVEYS
(2023)
Article
Chemistry, Multidisciplinary
Roua Jabla, Maha Khemaja, Felix Buendia, Sami Faiz
Summary: Knowledge engineering relies on ontologies for formal descriptions of real-world knowledge, and ontology learning is seen as a helpful approach to generating ontologies semi-automatically or automatically. This approach not only improves efficiency in ontology development, but also extends preexisting ontologies with new knowledge from diverse input data forms. The presented automatic ontology-based model evolution approach aims to cope with dynamic environments by analyzing semi-structured input data for learning and extending ontologies at runtime.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Shuangyin Li, Rong Pan, Haoyu Luo, Xiao Liu, Gansen Zhao
Summary: The study proposes an adaptive cross-contextual word embedding (ACWE) method to capture word polysemy in different contexts. Experimental results show that ACWE excels in tasks such as word similarity, polysemy induction, semantic interpretability, and text classification, outperforming other word embedding methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Piotr Bielak, Kamil Tagowski, Maciej Falkiewicz, Tomasz Kajdanowicz, Nitesh V. Chawla
Summary: This paper discusses the challenges of representation learning on dynamic graphs and proposes a framework called FILDNE for incorporating advances in static representation learning into dynamic graphs. FILDNE reduces computational costs while improving quality measure gains by applying static representation learning methods to dynamic graphs.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Theory & Methods
Gianfranco Lombardo, Agostino Poggi, Michele Tomaiuolo
Summary: The recent advances in node embedding techniques have enabled more efficient application of machine learning on graphs, but traditional static approaches have limitations. Continual feature learning, which builds on previously learned knowledge and known properties, offers a solution to address these limitations efficiently, especially for power-law distribution graphs in real scenarios.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Biochemistry & Molecular Biology
Qiangwei Zhou, Sheng Cheng, Shanshan Zheng, Zhenji Wang, Pengpeng Guan, Zhixian Zhu, Xingyu Huang, Cong Zhou, Guoliang Li
Summary: The study developed a comprehensive database called ChromLoops, which integrated 1030 ChIA-PET, HiChIP, and PLAC-Seq datasets from 13 species, and documented 1,491,416,813 high-quality chromatin loops. The database provided annotations for genes and regions overlapping with chromatin loop anchors, and included rich functional annotations. Additionally, it identified genes with high-frequency chromatin interactions in different species and cancer samples.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Chemistry, Multidisciplinary
Yigeng Shang, Zhigang Hao, Chao Yao, Guoliang Li
Summary: Graph neural network (GNN) is a widely used deep learning model for processing graph-structured data and has been applied to link prediction task. However, randomly sampling unobserved edges as negative samples has limitations. We propose a policy-based training method (PbTRM) to improve the quality of negative samples.
APPLIED SCIENCES-BASEL
(2023)
Review
Computer Science, Artificial Intelligence
Zohaib Jan, Farhad Ahamed, Wolfgang Mayer, Niki Patel, Georg Grossmann, Markus Stumptner, Ana Kuusk
Summary: Many industry sectors are adopting Industry 4.0 with the use of technologies like AI and machine learning, sensor networks, and cloud computing. However, the adoption of AI technologies varies greatly among industry sectors. This article examines specific applications of AI in different sectors, highlighting issues and concerns, and discussing potential solutions and challenges for adoption.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Virology
Xi Zeng, Yuyouye Wang, Binghan Liu, Xinjie Rao, Canhui Cao, Fang Peng, Wenhua Zhi, Ping Wu, Ting Peng, Ye Wei, Tian Chu, Miaochun Xu, Yashi Xu, Wencheng Ding, Guoliang Li, Shitong Lin, Peng Wu
Summary: Integration of human papilloma virus (HPV) DNA into the human genome may progressively contribute to cervical carcinogenesis. We analyzed multiomics data from 50 patients with cervical cancer to explore how HPV integration affects gene expression by altering DNA methylation. High-frequency HPV-integrated genes, including five novel recurrent genes, were identified. HPV integrations occurring in exons were associated with altered gene expression in tumor tissues. Our study provides novel insights into HPV-induced cervical cancer at the biological and clinical level.
JOURNAL OF MEDICAL VIROLOGY
(2023)
Article
Biochemical Research Methods
Ying Wang, Qin Jiang, Yilin Geng, Yuren Hu, Yue Tang, Jixiang Li, Junmei Zhang, Wolfgang Mayer, Shanmei Liu, Hong-Yu Zhang, Xianghua Yan, Zaiwen Feng
Summary: Gut microbiota plays a crucial role in pig development and health, and is associated with differences in feed efficiency. A Swine Gut Microbiota Federated Query Platform (SGMFQP) is presented, which provides convenient and efficient query service about swine feeding and gut microbiota. The system is based on a Swine Gut Microbiota Ontology (SGMO) and utilizes a template-based query interface, a federated query engine, and a workflow orchestration mechanism to retrieve information from multiple data sources.
Article
Cell Biology
Weizhi Ouyang, Xiwen Zhang, Minrong Guo, Jing Wang, Xiaoting Wang, Runxin Gao, Xu Xiang, Shiping Luan, Feng Xing, Zhilin Cao, Meng Ma, Jiapei Yan, Guoliang Li, Xingwang Li
Summary: In this study, high-resolution 3D genome maps were constructed using long-read chromatin interaction analysis, and the H3K27me3-associated chromatin interactions in an elite rice hybrid, Shanyou 63, were characterized. It was found that many H3K27me3-marked regions may function as silencer-like regulatory elements and can come into proximity with distal target genes via forming chromatin loops in the nuclei's 3D space. Additionally, genetic variations were identified to alter allelic chromatin topology and modulate allelic gene imprinting in rice hybrids.
Article
Computer Science, Artificial Intelligence
Rebecca Morgan, Simon Pulawski, Matt Selway, Aditya Ghose, Georg Grossmann, Wolfgang Mayer, Markus Stumptner, Ross Kyprianou
Summary: This article introduces a goal-oriented approach to managing the complexity of changing requirements in IT infrastructure. It presents the concepts of differential goals and integral goals, and formalizes them in both linear-time and branching-time settings. Additionally, the article illustrates the application of this approach in a Kubernetes setting, specifically in dealing with a Distributed Denial-of-Service (DDoS) attack.
DATA & KNOWLEDGE ENGINEERING
(2023)
Editorial Material
Biochemistry & Molecular Biology
Zhenji Wang, Minghao Liu, Fuming Lai, Qiangqiang Fu, Liang Xie, Yaping Fang, Qiangwei Zhou, Guoliang Li
Article
Biochemistry & Molecular Biology
Zhixian Zhu, Qiangwei Zhou, Yuanhui Sun, Fuming Lai, Zhenji Wang, Zhigang Hao, Guoliang Li
Summary: DNA methylation plays a crucial role in tumorigenesis and tumor progression. The MethMarkerDB database integrates WGBS data and DNA methylation biomarker genes, providing valuable resources for identifying novel biomarkers.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Biotechnology & Applied Microbiology
Li Deng, Qiangwei Zhou, Jie Zhou, Qing Zhang, Zhibo Jia, Guangfeng Zhu, Sheng Cheng, Lulu Cheng, Caijun Yin, Chao Yang, Jinxiong Shen, Junwei Nie, Jian-Kang Zhu, Guoliang Li, Lun Zhao
Summary: The fine scale genome organization of Arabidopsis was revealed through high-resolution chromatin interaction analysis, showing that distant active cis-regulatory elements are linked to target genes through long-range chromatin interactions with increased expression, while poised cis-regulatory elements are linked to target genes through long-range chromatin interactions with depressed expression. Transcription factor MYC2 plays a critical role in chromatin spatial organization, and MYC2 occupancy and MYC2-mediated chromatin interactions facilitate transcription within 3D chromatin architecture. Functionally related gene-defined chromatin connectivity networks indicated that genes involved in flowering-time control are compartmentalized into separate subdomains based on their spatial activity, linking chromatin conformation with coordinated gene expression.
