检索结果-内蒙古大学图书馆

An Evolutionary Approach for Balancing Effectiveness and Representation Level in Gene Selection

JOURNAL OF INFORMATION TECHNOLOGY RESEARCH 2015年第2期8卷 16-33页

作者： Dessi, Nicoletta Pes, Barbara Cannas, Laura Maria Univ Cagliari Dept Math & Comp Sci Cagliari Italy

As data mining develops and expands to new application areas, feature selection also reveals various aspects to be considered. This paper underlines two aspects that seem to categorize the large body of available feature selection algorithms: the effectiveness and the representation level. The effectiveness deals with selecting the minimum set of variables that maximize the accuracy of a classifier and the representation level concerns discovering how relevant the variables are for the domain of interest. For balancing the above aspects, the paper proposes an evolutionary framework for feature selection that expresses a hybrid method, organized in layers, each of them exploits a specific model of search strategy. Extensive experiments on gene selection from DNA-microarray datasets are presented and discussed. Results indicate that the framework compares well with different hybrid methods proposed in literature as it has the capability of finding well suited subsets of informative features while improving classification accuracy.

关键词： Bioinformatics Feature Selection Genetic Algorithms High-Dimensional data microarray data analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing cancer classification: a hybrid RDO-XGBoost approach for feature selection and predictive insights

引用

CANCER IMMUNOLOGY IMMUNOTHERAPY 2024年第12期73卷 261页

作者： Yaqoob, Abrar Verma, Navneet Kumar Aziz, Rabia Musheer Shah, Mohd Asif VIT Bhopal Univ Sch Adv Sci & Language Bhopal 466114 India State Planning Inst Planning Dept New Div Lucknow 226001 Utter Pradesh India Kardan Univ Dept Econ Kabul 1001 Afghanistan Lovely Profess Univ Div Res & Dev Phagwara 144001 Punjab India Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India

The identification of relevant biomarkers from high-dimensional cancer data remains a significant challenge due to the complexity and heterogeneity inherent in various cancer types. Conventional feature selection methods often struggle to effectively navigate the vast solution space while maintaining high predictive accuracy. In response to these challenges, we introduce a novel feature selection approach that integrates Random Drift Optimization (RDO) with XGBoost, specifically designed to enhance the performance of cancer classification tasks. Our proposed framework not only improves classification accuracy but also offers valuable insights into the underlying biological mechanisms driving cancer progression. Through comprehensive experiments conducted on real-world cancer datasets, including Central Nervous System (CNS), Leukemia, Breast, and Ovarian cancers, we demonstrate the efficacy of our method in identifying a smaller subset of unique and relevant genes. This selection results in significantly improved classification efficiency and accuracy. When compared with popular classifiers such as Support Vector Machine, K-Nearest Neighbor, and Naive Bayes, our approach consistently outperforms these models in terms of both accuracy and F-measure metrics. For instance, our framework achieved an accuracy of 97.24% in the CNS dataset, 99.14% in Leukemia, 95.21% in Ovarian, and 87.62% in Breast cancer, showcasing its robustness and effectiveness across different types of cancer data. These results underline the potential of our RDO-XGBoost framework as a promising solution for feature selection in cancer data analysis, offering enhanced predictive performance and valuable biological insights.

关键词： Random drift optimization XGBoost Feature selection Cancer classification microarray data analysis

来源：评论

学校读者我要写书评

暂无评论

An evaluation of resampling methods for assessment of survival risk prediction in high-dimensional settings

引用

STATISTICS IN MEDICINE 2011年第6期30卷 642-653页

作者： Subramanian, Jyothi Simon, Richard NCI Biometr Res Branch Bethesda MD 20892 USA

Resampling techniques are often used to provide an initial assessment of accuracy for prognostic prediction models developed using high-dimensional genomic data with binary outcomes. Risk prediction is most important, however, in medical applications and frequently the outcome measure is a right-censored time-to-event variable such as survival. Although several methods have been developed for survival risk prediction with high-dimensional genomic data, there has been little evaluation of the use of resampling techniques for the assessment of such models. Using real and simulated datasets, we compared several resampling techniques for their ability to estimate the accuracy of risk prediction models. Our study showed that accuracy estimates for popular resampling methods, such as sample splitting and leave-one-out cross validation (Loo CV), have a higher mean square error than for other methods. Moreover, the large variability of the split-sample and Loo CV may make the point estimates of accuracy obtained using these methods unreliable and hence should be interpreted carefully. A k-fold cross-validation with k = 5 or 10 was seen to provide a good balance between bias and variability for a wide range of data settings and should be more widely adopted in practice. Published in 2010 by John Wiley & Sons, Ltd.

关键词： microarray data analysis prognostic signatures survival analysis resampling methods prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

Identification of common genes in obesity and cancer through network interaction and targeting those genes by virtual screening approach

引用

JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS 2023年第3期41卷 1109-1127页

作者： Modanwal, Shristi Mishra, Nidhi Indian Inst Informat Technol Allahabad Dept Appl Sci Prayagraj 211015 UP India

Obesity may have an effect on cancer outcomes, resulting in global inequalities in cancer survival and death. microarray data analysis was done to identify differentially expressed genes (DEGs) in obese and cancer patients. Total 1977 differentially expressed genes among obesity and gastric cancer, breast cancer, pancreatic cancer, and colorectal cancer were used to build a gene interaction network, which was then analyzed by using Cytoscape software. It has been identified that JUN, CXCL12, and LEP genes show a higher degree and stress, and play an important role in obesity and cancer progression. Further, CXCL12 and LEP were taken for virtual screening study with coumarin and its derivatives to develop a drug against obesity and cancer. The interactions of CXCL12 and LEP with coumarins were studied by molecular docking and it shows good interaction as well as docking score as compared to the standard one. The ADME properties were predicted to check the drug-likeness activity of coumarins and the most of the drug-likeness activities are in admire range. The Binding free energy of the docked complex was calculated by performing MM-GBSA. The molecular docking, ADME properties prediction, and MM-GBSA was performed on Maestro 12.6. The top docked score compounds were further subjected to molecular dynamic simulation to check the stability by using GROMACS. The MM-PBSA study was performed to calculate the binding energy components as well as the energy contributions of specific amino acids. The resultant compounds could be a potent anti-obesity and anti-cancer drug.

关键词： Obesity cancer microarray data analysis protein-protein interaction MD Simulation

来源：评论

学校读者我要写书评

暂无评论

An evolutionary approach for gene selection and classification of microarray data based on SVM error-bound theories

引用

BIOSYSTEMS 2010年第1期100卷 39-46页

作者： Debnath, Rameswar Kurita, Takio AIST Neurosci Res Inst Tsukuba Ibaraki 3058568 Japan

microarrays have thousands to tens-of-thousands of gene features, but only a few hundred patient samples are available. The fundamental problem in microarray data analysis is identifying genes whose disruption causes congenital or acquired disease in humans. In this paper, we propose a new evolutionary method that can efficiently select a subset of potentially informative genes for support vector machine (SVM) classifiers. The proposed evolutionary method uses SVM with a given subset of gene features to evaluate the fitness function, and new subsets of features are selected based on the estimates of generalization error of SVMs and frequency of occurrence of the features in the evolutionary approach. Thus, in theory, selected genes reflect to some extent the generalization performance of SVM classifiers. We compare our proposed method with several existing methods and find that the proposed method can obtain better classification accuracy with a smaller number of selected genes than the existing methods. (C) 2010 Elsevier Ireland Ltd. All rights reserved.

关键词： Support vector machine Generalization error-bound Feature selection Evolutionary algorithm microarray data analysis

来源：评论

学校读者我要写书评

暂无评论

Finding edging genes from microarray data

引用

JOURNAL OF BIOTECHNOLOGY 2008年第3期135卷 233-240页

作者： An, Jiyuan Chen, Yi-Ping Phoebe Deakin Univ Sch Informat Technol Fac Sci & Technol Melbourne Vic 3125 Australia Australian Res Council Ctr Excellence Bioinformat Melbourne Vic Australia

Motivation: A set of genes and their gene expression levels are used to classify disease and normal tissues. Due to the massive number of genes in microarray, there are a large number of edges to divide different classes of genes in microarray space. The edging genes (EGs) can be co-regulated genes, they can also be on the same pathway or deregulated by the same non-coding genes, such as siRNA or miRNA. Every gene in EGs is vital for identifying a tissue's class. The changing in one EG's gene expression may cause a tissue alteration from normal to disease and vice versa. Finding EGs is of biological importance. In this work, we propose an algorithm to effectively find these EGs. Result: We tested our algorithm with five microarray datasets. The results are compared with the border-based algorithm which was used to find gene groups and subsequently divide different classes of tissues. Our algorithm finds a significantly larger amount of EGs than does the border-based algorithm. As our algorithm prunes irrelevant patterns at earlier stages, time and space complexities are much less prevalent than in the border-based algorithm. Availability: The algorithm proposed is implemented in C++ on Linux platform, The EGs in five microarray datasets are calculated. The preprocessed datasets and the discovered EGs are available at http://***/similar to phoebe/***. (C) 2008 Elsevier B.V. All rights reserved.

关键词： microarray data analysis edging genes classifications

来源：评论

学校读者我要写书评

暂无评论

A regularized clustering algorithm based on calculus of variations

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2008年第3期50卷 281-292页

作者： Lam, Benson S. Y. Liew, Alan Wee-Chung Smith, David K. Yan, Hong City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China Griffith Univ Sch Informat & Commun Technol Brisbane Qld 4111 Australia Univ Hong Kong Dept Biochem Hong Kong Hong Kong Peoples R China Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

microarray data clustering has drawn great attention in recent years. However, a major problem in data clustering is convergence to a local optimal solution. In this paper, we introduce a regularized version of the L-2m-FCM algorithm to resolve this problem. The strategy is to constrain the descent direction in the optimization procedure. For this we employ a novel method, calculus of variations, to correct the direction. Experimental results show that the proposed method has a better performance than seven other clustering algorithms for three synthetic and six real world data sets. Also, the proposed method produces reliable results for synthetic data sets with a large number of groups, which is a challenging problem for many clustering algorithms. Our method has been applied to microarray data classification with good results.

关键词： microarray data analysis clustering calculus of variations

来源：评论

学校读者我要写书评

暂无评论

Multimedia signal processing and systems in healthcare and life sciences

引用

IEEE MULTIMEDIA 2007年第4期14卷 20-21页

作者： Dimitrova, Nevenka Philips Research

The guest editor discusses the articles contained in this special issue and explains how this special issue reflects trends, challenges, and opportunities in the field at large.

关键词： Signal Processing IT Healthcare Life Sciences MRI CMT Tactile Navigation Haptics Physiological Monitoring Imaging Diagnostics Genomics microarray data analysis Multimedia Modeling Computer Navigated Surgery Optical Tracking Knowledge Extraction And Digitally Augmented Visuals

来源：评论

学校读者我要写书评

暂无评论

Effective PCA for high-dimension, low-sample-size data with singular value decomposition of cross data matrix

引用

JOURNAL OF MULTIVARIATE analysis 2010年第9期101卷 2060-2077页

作者： Yata, Kazuyoshi Aoshima, Makoto Univ Tsukuba Inst Math Ibaraki 3058571 Japan Univ Tsukuba Grad Sch Pure & Appl Sci Ibaraki 3058571 Japan

In this paper, we propose a new methodology to deal with PCA in high-dimension, low-sample-size (HDLSS) data situations. We give an idea of estimating eigenvalues via singular values of a cross data matrix. We provide consistency properties of the eigenvalue estimation as well as its limiting distribution when the dimension d and the sample size n both grow to infinity in such a way that n is much lower than d. We apply the new methodology to estimating PC directions and PC scores in HDLSS data situations. We give an application of the findings in this paper to a mixture model to classify a dataset into two clusters. We demonstrate how the new methodology performs by using HDLSS data from a microarray study of prostate cancer. (c) 2010 Elsevier Inc. All rights reserved.

关键词： Consistency Eigenvalue distribution HDLSS microarray data analysis Mixture model Principal component analysis Singular value

来源：评论

学校读者我要写书评

暂无评论

Genome-wide identification and characterization of the dof gene family in mango (Mangifera indica L.)

引用

GENETIC RESOURCES AND CROP EVOLUTION 2024年第6期71卷 2749-2765页

作者： Alghanem, Suliman M. S. Alnusairi, Ghalia S. H. Alkhateeb, Mariam Abdulaziz Alwutayd, Khairiah Mubarak Alaklabi, Abdullah Alharbi, Basmah M. Albalawi, Doha Abdullah Alshehri, Dikhnah Al-Harbi, Nadi Awad Al-Qahtani, Salem Mesfir Soliman, Mona H. Qassim Univ Coll Sci Dept Biol Buraydah 52571 Saudi Arabia Jouf Univ Coll Sci Dept Biol Sakaka 2014 Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Sci Dept Biol 84428 Riyadh 11671 Saudi Arabia Univ Bisha Fac Sci Dept Biol 551 Bisha 61922 Saudi Arabia Univ Tabuk Fac Sci Dept Biol Tabuk 71491 Saudi Arabia Univ Tabuk Univ Coll Tayma Biol Dept Tabuk 47512 Saudi Arabia Cairo Univ Fac Sci Bot & Microbiol Dept Giza 12613 Egypt Taibah Univ Fac Sci Biol Dept Al Sharm 46429 Yanbu El Bahr Saudi Arabia

DOF transcription factors are essential plant-specific gene regulators that are crucial in plant growth and stress responses. Mangifera indica, a tropical fruit species with diverse applications, undergoes complex genetic regulation during fruit ripening, influenced by climacteric conditions. This study focuses on DNA-binding one zinc finger genes (MiDofs) in Mangifera indica (mango) and their response to drought stress during fruit development. We found 36 MiDof genes in mango, categorizing them into six distinct clusters based on evolutionary relationships. Despite variations in various characteristics, the fundamental structures of these MiDof transcription factors remained consistent. Notably, two MiDof genes were outside the nucleus. Gene structure analysis and motif identification revealed common features among all MiDofs, with certain genes like MiDof5.3 and MiDof2.2 performing unique functions. Our analysis of conserved domains highlighted crucial functional sites and protein-protein interaction networks, with the zf-Dof domain being the most conserved. Additionally, we explored cis-acting regulatory elements, shedding light on the mechanisms by which MiDofs respond to light and drought stress. Expression analysis demonstrated the involvement of MiDofs in mango fruit ripening and development under light conditions. Quantitative reverse transcription-polymerase chain reaction (qRT-PCR) confirmed the induction of MiDofs under drought stress when compared to a control group. This study contributes valuable insights to the field of fruit biology and provides a deeper understanding of the role of MiDof genes in mango fruit development, offering potential avenues for crop improvement strategies.

关键词： DOF Genome-wide analysis Mangifera indica microarray data analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：