检索结果-内蒙古大学图书馆

Support Vector Machine Methods for the Prediction of Cancer Growth

学校读者我要写书评

暂无评论

Support Vector Machine Methods for the Prediction of Cancer ...

The Third International Joint Conference on Computational Science and Optimization(第三届计算科学与优化国际大会 CSO 2010)

作者： Wai-Ki Ching Xi Chen Kiyoko F. Aoki-Kinoshita Koh Furuta The Advanced Modeling and Applied Computing Laboratory Department of Mathematics The University of H Department of Bioinformatics Faculty of Engineering Soka University Tokyo Japan Division of Clinical Laboratories National Cancer Center Hospital Tokyo Japan

ISBN: (纸本)9781424468126;9780769540306

In this paper, we study the application of Support Vector Machine (SVM) in the prediction of cancer growth. SVM is known to be an efficient method and it has been widely used for classification problems. Here we propose a classifier which can differentiate patients having different levels of cancer growth with a high classification rate. To further improve the accuracy of classification, we propose to determine the optimal size of the training set and perform feature selection using rfe-gist, a special function of SVM.

关键词： Support vector machines Cancer Support vector machine classification Metastasis Training data Neoplasms Degradation Lymph nodes Diseases Optimization methods

A method for inferring polymers based on linear regression and integer programming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ido, Ryota Cao, Shengjuan Zhu, Jianshen Azam, Naveed Ahmed Haraguchi, Kazuya Zhao, Liang Nagamochi, Hiroshi Akutsu, Tatsuya Department of Applied Mathematics and Physics Kyoto University Kyoto606-8501 Japan Kyoto University Kyoto606-8306 Japan Bioinformatics Center Institute for Chemical Research Kyoto University Uji611-0011 Japan

A novel framework has recently been proposed for designing the molecular structure of chemical compounds with a desired chemical property using both artificial neural networks and mixed integer linear programming. In this paper, we design a new method for inferring a polymer based on the framework. For this, we introduce a new way of representing a polymer as a form of monomer and define new descriptors that feature the structure of polymers. We also use linear regression as a building block of constructing a prediction function in the framework. The results of our computational experiments reveal a set of chemical properties on polymers to which a prediction function constructed with linear regression performs well. We also observe that the proposed method can infer polymers with up to 50 non-hydrogen atoms in a monomer form. © 2021, CC BY.

关键词： Linear regression

Molecular Design Based on Integer Programming and Quadratic Descriptors in a Two-layered Model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Jianshen Azam, Naveed Ahmed Cao, Shengjuan Ido, Ryota Haraguchi, Kazuya Zhao, Liang Nagamochi, Hiroshi Akutsu, Tatsuya Department of Applied Mathematics and Physics Kyoto University Kyoto606-8501 Japan Kyoto University Kyoto606-8306 Japan Bioinformatics Center Institute for Chemical Research Kyoto University Uji611-0011 Japan

A novel framework has recently been proposed for designing the molecular structure of chemical compounds with a desired chemical property, where design of novel drugs is an important topic in bioinformatics and chemo-informatics. The framework infers a desired chemical graph by solving a mixed integer linear program (MILP) that simulates the computation process of a feature function defined by a two-layered model on chemical graphs and a prediction function constructed by a machine learning method. A set of graph theoretical descriptors in the feature function plays a key role to derive a compact formulation of such an MILP. To improve the learning performance of prediction functions in the framework maintaining the compactness of the MILP, this paper utilizes the product of two of those descriptors as a new descriptor and then designs a method of reducing the number of descriptors. The results of our computational experiments suggest that the proposed method improved the learning performance for many chemical properties and can infer a chemical structure with up to 50 non-hydrogen atoms. © 2022, CC BY.

关键词： Machine learning

An inverse QSAR method based on linear regression and integer programming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Jianshen Azam, Naveed Ahmed Haraguchi, Kazuya Zhao, Liang Nagamochi, Hiroshi Akutsu, Tatsuya Department of Applied Mathematics and Physics Kyoto University Kyoto606-8501 Japan Kyoto University Kyoto606-8306 Japan Bioinformatics Center Institute for Chemical Research Kyoto University Uji611-0011 Japan

Recently a novel framework has been proposed for designing the molecular structure of chemical compounds using both artificial neural networks (ANNs) and mixed integer linear programming (MILP). In the framework, we first define a feature vector f(ℂ) of a chemical graph ℂ and construct an ANN that maps x = f(ℂ) to a predicted value η(x) of a chemical property π to C. After this, we formulate an MILP that simulates the computation process of f(ℂ) from C and that of η(x) from x. Given a target value y∗ of the chemical property π, we infer a chemical graph C† such that η(f(ℂ†)) = y∗ by solving the MILP. In this paper, we use linear regression to construct a prediction function η instead of ANNs. For this, we derive an MILP formulation that simulates the computation process of a prediction function by linear regression. The results of computational experiments suggest our method can infer chemical graphs with around up to 50 non-hydrogen atoms. © 2021, CC BY.

关键词： Machine learning

Molecular design based on artificial neural networks, integer programming and Grid Neighbor Search

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Azam, Naveed Ahmed Zhu, Jianshen Haraguchi, Kazuya Zhao, Liang Nagamochi, Hiroshi Akutsu, Tatsuya Department of Applied Mathematics and Physics Kyoto University Kyoto606-8501 Japan Kyoto University Kyoto606-8306 Japan Bioinformatics Center Institute for Chemical Research Kyoto University Uji611-0011 Japan

A novel framework has recently been proposed for designing the molecular structure of chemical compounds with a desired chemical property using both artificial neural networks and mixed integer linear programming. In the framework, a chemical graph with a target chemical value is inferred as a feasible solution of a mixed integer linear program that represents a prediction function and other requirements on the structure of graphs. In this paper, we propose a procedure for generating other feasible solutions of the mixed integer linear program by searching the neighbor of output chemical graph in a search space. The procedure is combined in the framework as a new building block. The results of our computational experiments suggest that the proposed method can generate an additional number of new chemical graphs with up to 50 non-hydrogen atoms. © 2021, CC BY.

关键词： Integer programming

Copper(I) complexes inhibit colorectal cancer cells by inducing oxidative stress and cell apoptosis

学校读者我要写书评

暂无评论

Journal of Molecular Structure 2025年 1341卷

作者： Teow, Sin-Yeang Yin, Ying Brianna Neeroa, Bibi Noorheen Haleema Mooneerah Yu Lim, Jing Tan, Yee Seng Yeo, Chien Ing Department of Biology College of Science Mathematics and Technology Wenzhou-Kean University Ouhai Zhejiang Province Wenzhou325060 China Wenzhou Municipal Key Laboratory for Applied Biomedical and Biopharmaceutical Informatics Ouhai Zhejiang Province Wenzhou325060 China Zhejiang Bioinformatics International Science and Technology Cooperation Center Ouhai Zhejiang Province Wenzhou325060 China Dorothy and George Hennings College of Science Mathematics and Technology Kean University 1000 Morris Ave UnionNJ07083 United States Department of Medical Sciences School of Medical and Life Sciences Sunway University Selangor Darul Ehsan Bandar Sunway47500 Malaysia Department of Biological Sciences School of Medical and Life Sciences Sunway University Bandar Sunway Darul Ehsan Selangor47500 Malaysia Sunway Biofunctional Molecules Discovery Centre School of Medical and Life Sciences Sunway University Selangor Darul Ehsan Bandar Sunway47500 Malaysia

Metal-based drugs, including platinum-based compounds such as cisplatin and oxaliplatin, are commonly used in clinical cancer treatments. However, oxaliplatin remains the only clinically effective option for patients with colorectal cancer (CRC), highlighting the critical need for new and more potent therapeutic agents. In this study, we present the anticancer properties of (Ph3P)3Cu2Cl2 (ACu) and its derivatives (Ph₃P)₂CuCl{ROC(=S)N(H)C₆H₅} (ACu1–3), where R = Me (ACu1), Et (ACu2), and iPr (ACu3), and evaluate their underlying mechanisms of action. The synthesized compounds were characterized using spectroscopic methods including multinuclear 1H, 13C{1H}, and 31P{1H} nuclear magnetic resonance (NMR) spectroscopy and Fourier transform infrared (FTIR) spectroscopy. Powder X-ray diffraction (PXRD) studies were also conducted for the confirmation of structural integrity. Single crystal X-ray study showed that the dinuclear copper(I) complex, ACu, features distinct tetrahedral and trigonal planar Cu centers with a Cu···Cu interaction. C–H···π and π···π interactions assemble the molecules into 1D polymeric chains and two-dimensional (2D) supramolecular networks, as revealed by the analysis of its structural data. All copper(I) complexes exhibited potent anticancer activity (IC50 = 1.1–5.32 µM) in CRC monolayer cultures. In the absence of the thiocarbamide ligand, ACu alone disrupted CRC spheroids, with IC50 values of 9.43 µM and 10.4 µM in HCT116 and HT-29 cells, respectively. Mechanistic studies revealed that ACu induces oxidative stress, apoptosis, and necrosis in CRC cells. NanoString analysis further revealed upregulation of apoptotic signaling genes, including BIRC3, GZMB, IL1A, IL1B, and UBB, accompanied by the downregulation of TP53 and MDM2. Transcriptomic analysis revealed the upregulation of genes associated with oxidative stress and cell cycle regulation, such as BAP1 and CDKN2D, alongside the downregulation of CDKN2C, CDK4, HIST1H3B, HIST1H3H, and TFDP1. Nota

关键词： Fourier transform infrared spectroscopy

ON THE QUASI-ERGODICITY OF ABSORBING MARKOV CHAINS WITH UNBOUNDED TRANSITION DENSITIES, INCLUDING RANDOM LOGISTIC MAPS WITH ESCAPE

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Castro, Matheus M. Goverse, Vincent P.H. Lamb, Jeroen S.W. Rasmussen, Martin Department of Mathematics Imperial College London LondonSW7 2AZ United Kingdom International Research Center for Neurointelligence The University of Tokyo Tokyo113-0033 Japan Centre for Applied Mathematics and Bioinformatics Department of Mathematics and Natural Sciences Gulf University for Science and Technology Hawally Kuwait

In this paper, we consider absorbing Markov chains Xn admitting a quasi-stationary measure µ on M where the transition kernel P admits an eigenfunction 0 ≤ η ∈ L1(M, µ). We find conditions on the transition densities of P with respect to µ which ensure that η(x)µ(dx) is a quasi-ergodic measure for Xn and that the Yaglom limit converges to the quasi-stationary measure µ-almost surely. We apply this result to the random logistic map Xn+1 = ωnXn(1 − Xn) absorbed at R \ [0, 1], where ωn is an i.i.d sequence of random variables uniformly distributed in [a, b], for 1 ≤ a *** Codes 37H05, 47B65, 60J05 © 2022, CC BY-NC-ND.

关键词： Eigenvalues and eigenfunctions

Single-cell stochastic gene expression kinetics with coupled positive-plus-negative feedback

学校读者我要写书评

暂无评论

Physical Review E 2019年第5期100卷 052406-052406页

作者： Chen Jia Le Yi Wang George G. Yin Michael Q. Zhang Division of Applied and Computational Mathematics Beijing Computational Science Research Center Beijing 100193 China Department of Mathematics Wayne State University Detroit Michigan 48202 USA Department of Electrical and Computer Engineering Wayne State University Detroit Michigan 48202 USA Department of Biological Sciences Center for Systems Biology University of Texas at Dallas Richardson Texas 75080 USA MOE Key Laboratory of Bioinformatics Center for Synthetic and Systems Biology Tsinghua University Beijing 100084 China

Here we investigate single-cell stochastic gene expression kinetics in a minimal coupled gene circuit with positive-plus-negative feedback. A triphasic stochastic bifurcation is observed upon increasing the ratio of the positive and negative feedback strengths, which reveals a strong synergistic interaction between positive and negative feedback loops. We discover that coupled positive-plus-negative feedback amplifies gene expression mean but reduces gene expression noise over a wide range of feedback strengths when promoter switching is relatively slow, stabilizing gene expression around a relatively high level. In addition, we study two types of macroscopic limits of the discrete chemical master equation model: the Kurtz limit applies to proteins with large burst frequencies and the Lévy limit applies to proteins with large burst sizes. We derive the analytic steady-state distributions of the protein abundance in a coupled gene circuit for both the discrete model and its two macroscopic limits, generalizing the results obtained by Liu et al. [Chaos 26, 043108 (2016)]. We also obtain the analytic time-dependent protein distribution for the classical Friedman-Cai-Xie random bursting model [Friedman, Cai, and Xie, Phys. Rev. Lett. 97, 168302 (2006)]. Our analytic results are further applied to study the structure of gene expression noise in a coupled gene circuit, and a complete decomposition of noise in terms of five different biophysical origins is provided.

关键词： Gene expression Stochastic processes Gene regulatory networks Markovian processes

The mediating role of anxiety between child abuse and pain among a sample of Lebanese adults

学校读者我要写书评

暂无评论

Scientific reports 2025年第1期15卷 16559页

作者： Elie Kesrewani Georgio Chammas Diana Malaeb Fouad Sakr Mariam Dabbous Sami El Khatib Souheil Hallit Feten Fekih-Romdhane Sahar Obeid School of Medicine and Medical Sciences Holy Spirit University of Kaslik P.O. Box 446 Jounieh Lebanon. College of Pharmacy Gulf Medical University Ajman United Arab Emirates. School of Pharmacy Lebanese International University Beirut Lebanon. Department of Biomedical Sciences Lebanese International University Al Khyara Bekaa Lebanon. Center for Applied Mathematics and Bioinformatics (CAMB) Gulf University for Science and Technology Mubarak Al-Abdullah Kuwait. School of Medicine and Medical Sciences Holy Spirit University of Kaslik P.O. Box 446 Jounieh Lebanon. souheilhallit@usek.edu.lb. Psychology Department College of Humanities Effat University Jeddah 21478 Saudi Arabia. souheilhallit@usek.edu.lb. Applied Science Research Center Applied Science Private University Amman Jordan. souheilhallit@usek.edu.lb. The Tunisian Center of Early Intervention in Psychosis Department of Psychiatry "Ibn Omrane" Razi Hospital 2010 Manouba Tunisia. Faculty of Medicine of Tunis Tunis El Manar University Tunis Tunisia. Department of Psychology and Education School of Arts and Sciences Lebanese American University Jbeil Lebanon. saharobeid23@***.

Pain is defined as an unpleasant sensory and emotional experience in response to a noxious stimulus. Nowadays, it is increasingly prevalent among adults and may be influenced by past experiences such as child abuse, trauma or psychiatric conditions like anxiety. Thus, this study aims to evaluate the mediating effect of anxiety between child abuse and pain among a sample of Lebanese adults. This cross-sectional study was conducted between March and April 2024. Participants were selected using a snowball sampling method from various Lebanese governorates, and completed a self-administered online questionnaire via Google Forms. All adults over the age of 18 were eligible to participate. The questionnaire included sociodemographic questions, the short form of McGill pain questionnaire, the generalized anxiety disorder-7 (GAD-7), and the child abuse self report scale (CASRS-12). A total of 507 Lebanese adults completed the questionnaire. The mean age was 26.80 ± 10.29 years and 73.2% were female. The results showed that anxiety partially mediated the association between child abuse and pain. Higher levels of child abuse were significantly associated with greater anxiety, which in turn was significantly associated with increased pain. Child abuse was directly associated with higher pain levels. The study highlights the relationship that child abuse has on pain in adults and its relationship with anxiety. Future research delving into the relationship between child abuse and chronic pain in adulthood is essential to better understand the underlying pathways and support effective prevention and intervention strategies.

关键词： Anxiety Child abuse Pain