Article
Mathematics
Mahmoud Elmezain, Ebtesam A. Othman, Hani M. Ibrahim
Summary: In the area of network analysis, centrality metrics are important in defining the most important actors in a social network. This study introduces new centrality measures for weighted dynamic networks, showing the impact of each node throughout social networks through extensive experiments and discussions.
Article
Computer Science, Interdisciplinary Applications
Michael De Coste, Zhong Li, Ridha Khedri
Summary: This study develops a hybrid modeling framework combining ontological and machine learning models to predict national-scale river ice breakups. The framework sorts and analyzes data through an Ice Season Ontology, enabling better decision-making support and modeling applications in various fields.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Engineering, Chemical
Yachen Lu, Yufan Teng, Qi Zhang, Jiaquan Dai
Summary: In this paper, a new prediction model is proposed to accurately recognize and evaluate the trends of domestic chemical products and improve the forecasting accuracy of their prices. The model uses the minimum forecasting error as the evaluation objective for forecasting the settlement price. The proposed model utilizes an improved genetic algorithm to optimize the parameters of a long short-term memory (LSTM) network. Experimental results show that the proposed IGA-LSTM model has excellent forecasting performance with minimal forecasting errors for two types of chemical products.
Article
Engineering, Marine
Xin-Jiang Wei, Xiao Wang, Gang Wei, Cheng-Wei Zhu, Yu Shi
Summary: The study aims to predict the jacking forces during vertical tunneling construction process using artificial neural networks (ANNs) and hybrid genetic algorithm optimized ANNs (GA-ANNs). The GA-ANN models perform better than the ANN model, especially on RMSE values. The height of overlaying water, average jacking speed, and geological condition are identified as the most effective input parameters on the jacking force in this study.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Acoustics
Pushuang Chen, Liangyuan Xu, Qiansheng Tang, Lili Shang, Wei Liu
Summary: The research focuses on the noise comfort of tractors and it utilizes a rating scale method and objective acoustic parameters to evaluate tractor noise. By optimizing model parameters through genetic algorithm, the prediction accuracy and stability of the models are improved, providing higher accuracy and stability in predicting the sound quality value of tractor noise compared to other prediction models.
Article
Computer Science, Artificial Intelligence
Luning Bi, Guiping Hu
Summary: This paper proposes a genetic algorithm-assisted deep learning method for crop yield prediction, with two phases of global search and local search to improve prediction accuracy and convergence speed. Experimental results show that the proposed method outperforms traditional gradient-based methods.
Article
Energy & Fuels
Cheng Zhang, Maomao Zhang
Summary: A method using wavelet neural network and genetic algorithm for photovoltaic power generation forecast is proposed in this study, which shows improved accuracy and better performance compared to traditional methods in experimental simulations.
Article
Mathematics, Applied
Hewu Kuang
Summary: With the development of urbanization, the urban population is becoming denser and the demand for land is becoming more tense. This paper proposes a prediction model based on a genetic algorithm optimized neural network, which shows advantages in reducing algorithm running time and improving prediction accuracy.
JOURNAL OF FUNCTION SPACES
(2022)
Article
Multidisciplinary Sciences
Yanqing Liu, Cuiqing Jiang, Cuiping Lu, Zhao Wang, Wanliu Che
Summary: This study proposed an optimized BP neural network model using an improved genetic algorithm (IGA) to predict soil nutrient time series with high accuracy. Empirical evaluation using annual soil nutrient data from China showed that the IGA-BP method accurately predicted soil nutrient content for future time series.
Article
Green & Sustainable Science & Technology
Szu-Hsien Lin, Tzu-Pu Chang, Huei-Hwa Lai, Zi-Ying Lu
Summary: This study examines the impact of top management's social networks on their companies' recovery during a financial crisis. Logit and Cox regression models are used to investigate whether social networks can help overcome financial distress and shorten the duration of the crisis. The results show that specific network characteristics, such as low degree centrality of the chairman's bank networks and high closeness centrality of the general manager's networks, are associated with a higher likelihood of overcoming financial distress and returning to normal status. Additionally, certain network characteristics, including low degree centrality of the chairman's personal networks and high degree centrality of the financial executive's personal bank networks, make it easier to shorten the crisis duration. The practical implication is that companies should prioritize quality over quantity when configuring their social networks in order to survive or mitigate the impact of a crisis.
Article
Computer Science, Interdisciplinary Applications
Tran Thi Ngan, Ha Gia Son, Michael Omar, Nguyen Truong Thang, Nguyen Long Giang, Tran Manh Tuan, Nguyen Anh Tho
Summary: This article presents the method and models for rainfall prediction using machine learning and deep learning models. The combination of genetic algorithm and models is used to improve the prediction performance, and activation functions are utilized for enhancing the results.
EARTH SCIENCE INFORMATICS
(2023)
Article
Computer Science, Information Systems
Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
Summary: Graphs naturally occur in various contexts, and determining influential nodes is crucial for understanding the overall structure. Betweenness and closeness centrality are commonly used measures for identifying important nodes. Our proposed graph neural network (GNN) model improves upon current techniques for approximating betweenness and closeness centrality, showing superior performance in experiments.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2021)
Article
Engineering, Environmental
Elif Tugce Kabak, Ozge Cagcag Yolcu, Fulya Aydm Temel, Nurdan Gamze Turan
Summary: This study investigated the effects of co-composting of food waste and poultry waste on nitrogen losses and maturity. Different mixture ratios were used and the effectiveness of co-composting was compared with mono-composting of each waste. A linear and nonlinear hybrid tool based on a cascaded forward neural network was used to estimate nitrogen losses. The results showed that co-composting had higher prediction accuracy and could update the composting process without creating a new experimental setup.
CHEMICAL ENGINEERING JOURNAL
(2022)
Article
Geography
Tian Lan, Hong Zhang, Zhilin Li
Summary: This study explores the evolutionary centrality characteristics of Hong Kong urban road networks from 1976 to 2018. The findings show that the cumulative degree distributions are long-tail distributions and exhibit the Matthew Effect. The closeness centrality distributions evolve to become normal distributions, while the number of roads with very high betweenness centrality decreases. These findings reveal a self-organized optimization process in the structural evolution of road networks and enhance our understanding of urban evolution.
Article
Computer Science, Interdisciplinary Applications
Edore G. Arhore, Mehdi Yasaee, Iman Dayyani
Summary: This study aims to optimize the architecture of an artificial neural network (ANN) to predict the strength of adhesively bonded joints, replacing the computationally expensive non-linear finite element analysis (FEA). Through manual multi-objective optimization and genetic algorithm optimization, the optimal ANN architecture is found. The generated optimal ANN architecture accurately predicts the strength of adhesively bonded joints and saves 93% of computational cost compared to the traditional FEA method.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Virology
Ze-yu Wei, Fang Liu, Yu Li, Hong-lei Wang, Zi-ding Zhang, Zhong-zhou Chen, Wen-hai Feng
Article
Biotechnology & Applied Microbiology
Yongsheng Jia, Krithika N. Kodumudi, Ganesan Ramamoorthi, Amrita Basu, Colin Snyder, Doris Wiener, Shari Pilon-Thomas, Payal Grover, Hongtao Zhang, Mark Greene, Qianxing Mo, Zhongsheng Tong, Yong-Zi Chen, Ricardo L. B. Costa, Hyo Han, Catherine Lee, Hatem Soliman, Jose R. Conejo-Garcia, Gary Koski, Brian J. Czerniecki
Summary: The study reveals the impact of Th1 immune response on HER2 breast cancer, showing that IFN-gamma can regulate HER2 through the PDP pathway. Treatment with IFN-gamma or Th1-polarizing anti-HER2 vaccine can lead to decreased surface HER2 expression and induction of tumor senescence in HER2-resistant mammary carcinoma, demonstrating therapeutic potential through anti-tumor immunity.
Article
Biochemical Research Methods
Xiaodi Yang, Xianyi Lian, Chen Fu, Stefan Wuchty, Shiping Yang, Ziding Zhang
Summary: The study introduces a database called HVIDB that provides comprehensive annotated data on human-virus protein-protein interactions and integrates online PPI prediction tools. Users can easily access reliable information on various human virus PPIs and conduct in-depth analysis through this database.
BRIEFINGS IN BIOINFORMATICS
(2021)
Review
Biochemical Research Methods
Xianyi Lian, Xiaodi Yang, Shiping Yang, Ziding Zhang
Summary: The interactions between human and viruses play a crucial role in viral infection and the host immune system. Studying these interactions is essential for understanding human-virus relationships and developing effective drugs to combat viral infectious diseases. Recent years have seen a rapid accumulation of experimentally identified human-virus protein-protein interaction data, providing an opportunity for bioinformatics research in this area.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Oncology
Su Zhang, Manqing Cao, Zhenyu Hou, Xiaoying Gu, Yongzi Chen, Lu Chen, Yi Luo, Liwei Chen, Dongming Liu, Hongyuan Zhou, Keyun Zhu, Zhiwei Wang, Xihao Zhang, Xiaolin Zhu, Yunlong Cui, Huikai Li, Hua Guo, Ti Zhang
Summary: ACE inhibitors are not effective in reducing proteinuria caused by anti-angiogenic drugs (AADs), and may even exacerbate AADs' anticancer effects. This finding highlights the importance of careful management of side effects in cancer patients undergoing anti-angiogenic therapy.
Article
Biochemistry & Molecular Biology
Zhen Chen, Pei Zhao, Chen Li, Fuyi Li, Dongxu Xiang, Yong-Zi Chen, Tatsuya Akutsu, Roger J. Daly, Geoffrey Webb, Quanzhi Zhao, Lukasz Kurgan, Jiangning Song
Summary: iLearnPlus is the first machine-learning platform with graphical- and web-based interfaces for analysis and predictions using nucleic acid and protein sequences, providing a comprehensive set of algorithms and automating sequence-based feature extraction and analysis. It caters to experienced bioinformaticians and biologists with no programming background, showcasing its capabilities through case studies on lncRNA prediction and crotonylation site prediction.
NUCLEIC ACIDS RESEARCH
(2021)
Article
Biochemistry & Molecular Biology
Xiaofeng Wang, Renxiang Yan, Yong-Zi Chen, Yongji Wang
Summary: Two convolutional neural network models were proposed for predicting ubiquitination sites in Arabidopsis thaliana, which outperformed other models. The study also analyzed the physicochemical properties of amino acids and the influence of CNN structure on prediction performance. Additionally, potential ubiquitination sites in the global Arabidopsis proteome were predicted.
PLANT MOLECULAR BIOLOGY
(2021)
Article
Microbiology
Wen-Jing Cui, Biliang Zhang, Ran Zhao, Li-Xue Liu, Jian Jiao, Ziding Zhang, Chang-Fu Tian
Summary: This study utilized gene editing to improve compatibility between rhizobium and soybean. Transcriptomics revealed consistent lineage-dependent transcriptional profiles of core pathways, predating the divergence of legumes and rhizobia. Additionally, low-efficiency nodules exhibited impaired antioxidant activity and energy status, restricting nitrogen fixation activity.
Article
Biochemical Research Methods
Xiaodi Yang, Shiping Yang, Xianyi Lian, Stefan Wuchty, Ziding Zhang
Summary: This study uses machine learning and transfer learning methods to predict human-virus protein interactions, utilizing a combination of Siamese CNN architecture and multi-layer perceptron for improved predictions. The introduced transfer learning methods reliably predict interactions in different domains by retraining CNN layers.
Article
Biochemistry & Molecular Biology
Tianpeng Wang, Yaqiong Guo, Dawn M. Roellig, Na Li, Monica Santin, Jason Lombard, Martin Kvac, Doaa Naguib, Ziding Zhang, Yaoyu Feng, Lihua Xiao
Summary: Genetic recombination between sympatric ancestral populations leads to the emergence of divergent subpopulations of the zoonotic parasite Cryptosporidium parvum with modified host ranges. This study reveals the ancestral origins of C. parvum and suggests that pathogen import through modern animal farming promotes the emergence of subpopulations with modified host preference.
MOLECULAR BIOLOGY AND EVOLUTION
(2022)
Article
Biochemical Research Methods
Yan Huang, Stefan Wuchty, Yuan Zhou, Ziding Zhang
Summary: This study proposes a structure-based deep learning framework, SGPPI, for predicting protein-protein interactions (PPIs) by extracting structural, geometric, and evolutionary features. The model outperforms traditional methods and state-of-the-art deep learning methods on unbiased benchmark datasets and demonstrates the ability to predict PPIs across different species.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Ecology
Yuan-Yuan Ji, Biliang Zhang, Pan Zhang, Liu-Chi Chen, You-Wei Si, Xi-Yao Wan, Can Li, Ren-He Wang, Yu Tian, Ziding Zhang, Chang-Fu Tian
Summary: Migration from rhizosphere to rhizoplane is a crucial process in root microbiome assembly. The presence of Rhizobiales members is significant in the core root microbiome of terrestrial plants. This study investigates the genome-wide transposon-sequencing of rhizoplane fitness genes of beneficial Sinorhizobium fredii on various crops and reveals the role of FadL and ExoFQP in modulating bacterial migration towards rhizoplane through the regulation of AHLs.
Article
Plant Sciences
Jingyan Zheng, Xiaodi Yang, Yan Huang, Shiping Yang, Stefan Wuchty, Ziding Zhang
Summary: The authors introduce a deep learning framework called DeepAraPPI, using sequence, domain, and Gene Ontology information to predict protein-protein interactions in Arabidopsis. DeepAraPPI combines the prediction results of three individual predictors and shows superior performance compared to existing methods. It also exhibits better cross-species predictive ability in rice. DeepAraPPI is freely accessible online.
Article
Biochemistry & Molecular Biology
Panyu Ren, Xiaodi Yang, Tianpeng Wang, Yunpeng Hou, Ziding Zhang
Summary: This study predicted the protein-protein interaction (PPI) network of Cryptosporidium parvum (C. parvum) using three bioinformatics methods and explored the biological significance of the network. The constructed PPI network can serve as a valuable data resource for functional genomics studies and target discovery in drug/vaccine development for C. parvum.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2022)
Article
Biochemistry & Molecular Biology
Yu Li, Lei Han, Ziding Zhang
Summary: In this study, molecular dynamics simulations were performed to investigate the conformational change of the KRAS(G12C)-AMG 510 complex. The results showed that AMG 510 restricts KRAS(G12C) to the inactive conformation and identified potential resistance mutations.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2022)