Article
Computer Science, Information Systems
Zichen Zhang, Shifei Ding, Yuting Sun
Summary: This paper introduces a new method called multiple birth support vector regression (MBSVR), which constructs the regressor from multiple hyperplanes obtained by solving small quadratic programming problems, aiming for faster computation and better fitting precision.
INFORMATION SCIENCES
(2021)
Review
Computer Science, Information Systems
Jian Sun, Pu-Feng Du
Summary: Chloroplast is a crucial subcellular organelle in plant and algal cells, essential for photosynthesis. Proteins within different compartments of the chloroplast play roles in various steps of photosynthesis, and precise cellular localization is important for understanding their functions in the process. Computational methods have been developed to predict protein subchloroplast locations, offering a cost-effective alternative to experimental approaches.
FRONTIERS OF COMPUTER SCIENCE
(2021)
Article
Computer Science, Information Systems
Guoquan Li, Linxi Yang, Zhiyou Wu, Changzhi Wu
Summary: Proximal support vector machine (PSVM) is a variant of support vector machine (SVM) which aims to generate a pair of non-parallel hyperplanes for classification. Introducing l(0)-norm regularization in PSVM enables simultaneous selection of important features and removal of redundant features for classification. The proposed method utilizes a continuous nonconvex function and difference of convex functions algorithms (DCA) to solve the optimization problem efficiently.
INFORMATION SCIENCES
(2021)
Article
Environmental Sciences
Guangxin Liu, Liguo Wang, Danfeng Liu, Lei Fei, Jinghui Yang
Summary: This article proposes a non-parallel SVM model, which improves the classification effect and generalization performance for hyperspectral images by adding an additional empirical risk minimization term and bias constraint.
Article
Computer Science, Artificial Intelligence
Liming Liu, Maoxiang Chu, Rongfen Gong, Li Zhang
Summary: The improved nonparallel support vector machine (INPSVM) proposed in this article inherits the advantages of nonparallel support vector machine (NPSVM) while also offering incomparable benefits over twin support vector machine (TSVM). INPSVM effectively eliminates noise effects and achieves higher classification accuracy for both linear and nonlinear datasets compared to other algorithms. Experimental results demonstrate the superior efficiency, accuracy, and robustness of INPSVM.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Bagesh Kumar, Ayush Sinha, Sourin Chakrabarti, O. P. Vyas
Summary: In this paper, a fast training method for OCSSVM is proposed, which enhances its scalability without compromising precision significantly. Experimental results show that the proposed method achieves the best tradeoff between training time and accuracy, providing similar accuracies to regular OCSSVM and better scalability compared to existing state-of-the-art one-class classifiers.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jingyue Zhou, Ye Tian, Jian Luo, Qianru Zhai
Summary: This paper proposes a support vector machine approach based on optimizing the margin distribution, which optimizes the margin distribution of training points by maximizing the margin mean and minimizing the margin variance, and classifies data points by constructing a quadratic surface.
Article
Computer Science, Artificial Intelligence
Chen Ding, Tian-Yi Bao, He-Liang Huang
Summary: The study proposes a quantum-inspired classical algorithm for LS-SVM, utilizing an improved sampling technique for classification. The theoretical analysis indicates that the algorithm can achieve classification with logarithmic runtime for low-rank, low-condition number, and high-dimensional data matrices.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Bikram Kumar, Deepak Gupta
Summary: The paper introduces a novel method ULTBSVM which utilizes Universum data to enhance the classification of healthy and seizure EEG signals, showing promising results in experiments.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Computer Science, Theory & Methods
Umesh Gupta, Deepak Gupta
Summary: This paper presents two efficient variant models to handle noise and outliers, obtaining solutions by solving a system of linear equations and minimizing the impact of noise. The proposed models demonstrate exceptional generalization performance.
FUZZY SETS AND SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xiaohan Zheng, Li Zhang, Leilei Yan
Summary: This paper proposes a novel sparse discriminant twin support vector machine (SD-TSVM) to improve the discriminant ability and sparsity compared to traditional TSVM. The introduction of twin Fisher regularization terms and the utilization of 1-norm of coefficients and hinge loss contribute to its satisfactory performance.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hossein Moosaei, M. A. Ganaie, Milan Hladik, M. Tanveer
Summary: Imbalanced datasets are common in real-world problems. Traditional classification algorithms have limitations in handling imbalanced data. To improve classification performance on imbalanced datasets, an improved reduced universum twin support vector machine (IRUTSVM) algorithm is proposed, which introduces new constraints and reduces computational time.
Article
Computer Science, Artificial Intelligence
Matteo Avolio, Antonio Fuduli
Summary: This paper introduces a novel approach for binary multiple instance learning classification, combining the strengths of SVM and PSVM, aiming to discriminate between positive and negative instances by generating a hyperplane placed in the middle between two parallel hyperplanes.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Environmental Sciences
Zhihao Wang, Alexander Brenning
Summary: Using active learning with uncertainty sampling can reduce the time and cost needed by experts under limited data conditions, improve model performance, and is particularly suitable for emergency response settings and landslide susceptibility modeling.
Article
Computer Science, Information Systems
Lili Zhu, Petros Spachos
Summary: Food quality and safety are crucial for human health and social stability. This study proposed a mobile visual system to grade bananas, achieving high accuracy rates in the grading process. The complex process of ensuring food quality involves all stages from cultivation to consumption.
INTERNET OF THINGS
(2021)
Article
Biochemistry & Molecular Biology
Jing Lin, Li Wen, Yuwei Zhou, Shaozhou Wang, Haiyang Ye, Jun Su, Juelin Li, Jianping Shu, Jian Huang, Peng Zhou
Summary: In this study, a comprehensive platform called PepQSAR database was developed, which systematically collects and decomposes various data sources and abundant information related to pQSARs. The database also includes a comparison function for previously built pQSAR models reported by different groups. This structured and searchable database is expected to be a useful resource and powerful tool for the computational peptidology community.
Article
Chemistry, Medicinal
Liping Ren, Xianrun Pan, Lin Ning, Di Gong, Jian Huang, Kejun Deng, Lei Xie, Yang Zhang
Summary: In this study, a liver cancer prognosis model was constructed using four hypoxia-related genes (NDRG1, ENO1, SERPINE1, ANXA2) identified from two independent datasets. The model showed significant differences in survival and immune characteristics between high- and low-risk groups, indicating its potential as a predictor and drug target for liver cancer prognosis. This study provides insights into the association between hypoxia, tumor microenvironment, and liver cancer prognosis.
CURRENT COMPUTER-AIDED DRUG DESIGN
(2023)
Review
Biochemical Research Methods
Li Liu, Kaiyuan Han, Huimin Sun, Lu Han, Dong Gao, Qilemuge Xi, Lirong Zhang, Hao Lin
Summary: This review provides an overview of loop-calling tools for various 3C-based techniques. It categorizes and summarizes these tools, discusses background biases and denoising algorithms, and helps researchers select the most appropriate method for loop calling and downstream analysis. It is also useful for bioinformatics scientists aiming to develop new loop-calling algorithms.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Xiang Feng, Hongqi Zhang, Hao Lin, Haixia Long
Summary: In this study, a directed graph neural network called scDGAE was developed for scRNA-seq analysis, using graph autoencoders and graph attention network. The experiment results showed that the scDGAE model achieved promising performance in gene imputation and cell clustering prediction, and it can be applied to general scRNA-Seq analyses.
Article
Biochemical Research Methods
Sen-Bin Zhu, Qian-Hu Jiang, Zhi-Guo Chen, Xiang Zhou, Yan-ting Jin, Zixin Deng, Feng-Biao Guo
Summary: Synthetic lethality refers to the phenomenon where mutations in two genes together lead to cell or organism death, while a single mutation in either gene has minimal impact. Currently, there is a lack of a specialized platform to collect microbial synthetic lethality gene pairs. To address this, we have developed the Microbial Synthetic Lethal and Rescue Database (Mslar) which collects a large number of gene pairs for reference.
PLOS COMPUTATIONAL BIOLOGY
(2023)
Review
Medicine, Research & Experimental
Wei Chen, Xuesong Liu, Sanyin Zhang, Shilin Chen
Summary: Traditional wet laboratory testing and validations are costly and time-consuming for drug discovery. However, advancements in artificial intelligence (AI) techniques are changing the landscape of drug discovery. Combined with accessible data resources, AI techniques have accelerated the drug discovery process and have been widely applied in pharmaceutical analysis and drug design. Nonetheless, there are challenges in applying AI to drug discovery.
MOLECULAR THERAPY-NUCLEIC ACIDS
(2023)
Article
Biochemistry & Molecular Biology
Mingyou Liu, Hongmei Liu, Tao Wu, Yingxue Zhu, Yuwei Zhou, Ziru Huang, Changcheng Xiang, Jian Huang
Summary: The ongoing COVID-19 pandemic necessitates the development of safe and efficient anti-coronavirus infection drugs. This study presents the ACP-Dnnel model, which employs machine learning techniques to predict anti-coronavirus peptides. The model achieves high accuracy and can expedite the discovery of anti-coronavirus peptide drugs.
Article
Chemistry, Medicinal
Xiao-Wei Liu, Tian-Yu Shi, Dong Gao, Cai-Yi Ma, Hao Lin, Dan Yan, Ke-Jun Deng
Summary: Diabetes mellitus is a chronic metabolic disease that disrupts blood glucose homeostasis and leads to severe complications. The development of artificial intelligence has provided a powerful tool, iPADD, for accelerating the discovery of potential antidiabetic drugs. iPADD achieved high accuracy in drug prediction by using molecular fingerprints and machine learning algorithms.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemical Research Methods
Yuwei Zhou, Ziru Huang, Wenzhen Li, Jinyi Wei, Qianhu Jiang, Wei Yang, Jian Huang
Summary: Antibody drugs have become essential in biotherapeutics and have benefited patients with various diseases. However, their development process is time-consuming, costly, and risky. To accelerate development, reduce costs, and increase success rates, artificial intelligence, particularly deep learning methods, are extensively used in all stages of preclinical antibody drug development. This review systematically summarizes the use of deep learning in antibody drug discovery and development, including antibody encodings, deep learning architectures, and models. We also critically discuss the challenges, opportunities, current applications, and future directions of deep learning in antibody drug development.
Article
Multidisciplinary Sciences
Zhaohui Zhong, Guanqing Liu, Zhongjie Tang, Shuyue Xiang, Liang Yang, Lan Huang, Yao He, Tingting Fan, Shishi Liu, Xuelian Zheng, Tao Zhang, Yiping Qi, Jian Huang, Yong Zhang
Summary: In this study, a probiotic sourced CRISPR-LrCas9 system with a similar PAM requirement to Cas12a was reported, and its high efficiency in various genome editing applications was demonstrated.
NATURE COMMUNICATIONS
(2023)
Article
Mathematical & Computational Biology
Bowen Li, Heng Chen, Jian Huang, Bifang He
Summary: The CD47/SIRPa pathway is a new breakthrough in tumor immunity, and we developed a predictive model using NGPD and traditional machine learning methods to distinguish CD47 binding peptides. We screened CD47 binding peptides using NGPD biopanning technology and built computational models using multiple peptide descriptors and deep learning methods. The integrated model based on support vector machine showed good specificity, accuracy, and sensitivity during the cross-validation.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2023)
Article
Medicine, General & Internal
Wen Zhu, Shi-Shi Yuan, Jian Li, Cheng-Bing Huang, Hao Lin, Bo Liao
Summary: This study provides the first recognition framework for accurately identifying HBP based on machine learning. By using four sequence descriptors, HBP and non-HBP samples were represented by discrete numbers and input into SVM and RF algorithms for comparison. The SVM-based classifier was found to have the greatest potential for identifying HBP.
Article
Medicine, Research & Experimental
Kexing Xi, Mengqing Zhang, Mingrui Li, Qiang Tang, Qi Zhao, Wei Chen
Summary: In this study, a network-based methodology was used to explore the mechanisms of nephrotoxicity induced by specific compounds. The results showed that the advanced glycosylation end products-receptor for advanced glycosylation end products signaling pathway, human cytomegalovirus infection, lipid and atheroapoptosis, and the phosphatidylinositol 3-kinase-Akt pathways play important roles in nephrotoxicity.
MOLECULAR THERAPY NUCLEIC ACIDS
(2023)
Article
Biodiversity Conservation
Wenfei Liao, Hao Lin
Summary: Urbanisation has complex effects on the morphological traits of aquatic insect species, with different species exhibiting different strategies and abilities to cope with movement barriers caused by urbanisation.
INSECT CONSERVATION AND DIVERSITY
(2023)
Article
Biology
Jie Gao, Yongxian Feng, Yan Yang, Yuetong Shi, Junjie Liu, Hao Lin, Lirong Zhang
Summary: This study systematically identified and analyzed key CpG sites closely related to differential expression of genes in LUSC through a two-step correlation analysis method, and found that these sites and genes can serve as effective biomarkers for LUSC.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Mathematical & Computational Biology
Yuxuan Tang, Shuling Shen, Linhe Zhu
Summary: In this paper, a SI reaction-diffusion rumor propagation model with nonlinear saturation incidence is studied. The conditions for the existence and local stability of the positive equilibrium point are obtained through stability analysis. The critical value and existence theorem of Turing bifurcation are obtained by selecting suitable variable as the control parameter. Different types of Turing pattern are divided and verified through numerical simulation.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Soumitra Pal, Pijush Panday, Nikhil Pal, A. K. Misra, Joydev Chattopadhyay
Summary: This paper investigates a nonlinear ratio-dependent prey-predator model with constant prey refuge, incorporating Allee and fear phenomena in the prey population. The qualitative behaviors of the model are studied around equilibrium points, including Hopf bifurcation and its direction and stability. The study shows that fear of predation risk can have both stabilizing and destabilizing effects, and an increase in prey refuge drives the system towards stability. Numerical simulations using MATLAB software explore the dynamical behaviors of the system.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Fengsheng Chien, Hassan Saberi Nik, Mohammad Shirazian, J. F. Gomez-Aguilar
Summary: This paper investigates the stability analysis of an SEIRV model with nonlinear incidence rates and discusses the significance of control factors in disease transmission. The use of Volterra-Lyapunov matrices enables the study of global stability at the endemic equilibrium point. Additionally, an optimal control strategy is proposed to prevent the spread of coronavirus, aiming to minimize the number of infected and exposed individuals as well as treatment costs. Numerical simulations are conducted to further examine the analytical findings.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Honglan Zhu, Xuebing Zhang, Hao Zhang
Summary: In this paper, we investigate a delayed diffusive predator-prey model affected by toxic substances. The boundedness and persistence property of the model are studied first. Conditions for the existence of steady state bifurcation, Hopf bifurcation, and Turing bifurcation are obtained by analyzing the characteristic equation. Moreover, the Hopf bifurcation induced by the delay is also studied. Theoretical results are verified by numerical simulation, showing the significant impact of toxic substances on the system dynamics.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Liliana Puchuri, Orestes Bueno
Summary: In this study, a predator-prey model of Gause type is investigated. The prey growth rate is influenced by an Allee effect and the predator's impact on the prey is determined by a generalized hyperbolic-type functional response. The behavior of the solutions in the first quadrant and the existence of limit cycles are studied. The existence of equilibrium points and their stability are also analyzed, with a focus on the conditions for a center-type equilibrium. Additionally, the existence of a unique limit cycle for small perturbations of the system is guaranteed.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
M. M. Abdeslami, L. Basri, M. El Fatini, I. Sekkak, R. Taki
Summary: In this work, a stochastic epidemic model with vaccination, healing and relapse is studied. The existence and uniqueness of the positive solution are proven. Sufficient conditions for extinction and persistence in mean of the stochastic system are established. Additionally, sufficient conditions for the existence of an ergodic stationary distribution to the model are also established, indicating the persistence of the infectious disease. Graphical illustrations of the approximate solutions of the stochastic epidemic model are presented.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Yan Zhang, Yuanhua Qiao, Lijuan Duan
Summary: This paper investigates the memristive multidirectional associative memory neural networks (MAMNNs) with mixed time-varying delays in modeling the abrupt synaptic connections in human brain's associative memory. It proves the existence, boundedness, and asymptotical almost periodicity of the solution using Lyapunov function. It also examines the uniqueness and global exponential stability of the almost periodic solution using a new Lyapunov function. The research extends the study on the periodic and almost periodic solutions of bidirectional associative memory neural networks. Numerical examples and simulations are provided to demonstrate the validity of the main results.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Xiangjun Dai, Jianjun Jiao, Qi Quan, Airen Zhou
Summary: In this study, a comprehensive pest management model for agricultural production is proposed, involving periodic spraying of pesticides and releasing predatory natural enemies. Using Floquet theory and the comparison theorem of impulsive differential equations, a sufficient condition for the global asymptotic stability of the pest-eradication periodic solution is obtained. The persistence of the system is further studied, and a sufficient condition for the persistence of the system is obtained. Numerical simulations are conducted to verify the theoretical works. The results indicate that the sublethal effects of insecticides and the release of predatory natural enemies play significant roles in pest control in agricultural production.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Yan Li, Zhiyi Lv, Fengrong Zhang, Hui Hao
Summary: In this paper, a diffusive predator-prey model with hyperbolic mortality and prey-taxis under homogeneous Neumann boundary condition is studied. The influence of prey-taxis on the local stability of constant equilibria is analyzed. Prey-taxis is found to affect the stability of the unique positive constant equilibrium, but has no influence on the stability of the trivial equilibrium and the semi-trivial equilibrium. Hopf bifurcation and steady state bifurcation related to prey-taxis are then derived, indicating the important role of prey-taxis in the dynamics.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Surath Ghosh
Summary: The main goal of this work is to implement the Homotopy perturbation transform method (HPTM) involving the Katugampola fractional operator. A fractional order Hepatitis model is used as an example to analyze the solutions. The integer order model is first converted to a fractional order model in the Caputo sense and then the new operator Katugampola fractional derivative is used to present the model. The HPTM is described to obtain the solution of the proposed model using this new operator, and some analyses are conducted on the operator to prove its efficiency.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Zhihui Ma, Shenghua Li, Shuyan Han
Summary: In this paper, a nonlinear infectious disease model is proposed to consider the impact of information on vaccination behavior and contact patterns. The existence of equilibria and stability properties of the model are analyzed using a geometric approach. The double Hopf bifurcation around the endemic equilibrium is shown through mathematical derivation and numerical simulation. The optimal control problem is established and solved using Pontryagin's maximum principle, and the effectiveness of the proposed control strategies is demonstrated through numerical experiments.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)
Article
Mathematical & Computational Biology
Yajing Li, Zhihua Liu
Summary: In this paper, a size-stage-structured cooperation model is proposed, which takes into account both size structure and stage structure, as well as obligate and facultative symbiosis in a cooperation system. The model is reduced to a threshold delay equations (TDEs) model using the method of characteristic, which is further transformed into a functional differential equations (FDEs) model. The results of the qualitative analysis of solutions of the FDEs model, including global existence and uniqueness, positivity and boundedness, stability and Hopf bifurcation of positive equilibrium, are established based on the classical theory of FDEs. Numerical simulations are conducted to support the analytical results, showing the importance of size structure and stage structure in the dynamic behavior of the model.
INTERNATIONAL JOURNAL OF BIOMATHEMATICS
(2024)