检索结果-内蒙古大学图书馆

Deep learning-based microarray cancer classification and ensemble gene selection approach

IET SYSTEMS BIOLOGY 2022年第3-4期16卷 120-131页

作者： Rezaee, Khosro Jeon, Gwanggil Khosravi, Mohammad R. Attar, Hani H. Sabzevari, Alireza Meybod Univ Dept Biomed Engn Meybod Iran Incheon Natl Univ Coll Informat Technol Dept Embedded Syst Engn Incheon South Korea Persian Gulf Univ Dept Comp Engn Bushehr Iran Zarqa Univ Dept Energy Engn Zarqa Jordan

Malignancies and diseases of various genetic origins can be diagnosed and classified with microarray data. There are many obstacles to overcome due to the large size of the gene and the small number of samples in the microarray. A combination strategy for gene expression in a variety of diseases is described in this paper, consisting of two steps: identifying the most effective genes via soft ensembling and classifying them with a novel deep neural network. The feature selection approach combines three strategies to select wrapper genes and rank them according to the k-nearest neighbour algorithm, resulting in a very generalisable model with low error levels. Using soft ensembling, the most effective subsets of genes were identified from three microarray datasets of diffuse large cell lymphoma, leukaemia, and prostate cancer. A stacked deep neural network was used to classify all three datasets, achieving an average accuracy of 97.51%, 99.6%, and 96.34%, respectively. In addition, two previously unreported datasets from small, round blue cell tumors (SRBCTs)and multiple sclerosis-related brain tissue lesions were examined to show the generalisability of the model method.

关键词： soft ensembling lab-on-a-chip ensemble gene selection approach feature selection medical computing deep learning (artificial intelligence) k-nearest neighbour algorithm diseases genetic origins microarray data diffuse large cell lymphoma deep learning-based microarray cancer classification gene expression stacked deep neural network wrapper genes data analysis feature selection approach microarray datasets cancer pattern classification genetics effective genes prostate cancer brain tumours low error levels combination strategy

来源：评论

学校读者我要写书评

暂无评论

Supervised feature selection by constituting a basis for the original space of features and matrix factorization

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2020年第7期11卷 1405-1421页

作者： Saberi-Movahed, Farid Eftekhari, Mahdi Mohtashami, Mohammad Grad Univ Adv Technol Fac Sci & Modern Technol Dept Appl Math Kerman Iran Shahid Bahonar Univ Kerman Dept Comp Engn Kerman Iran

Most of existing research works in the field of feature selection via matrix factorization techniques have been employed for unsupervised learning problems. This paper introduces a new framework for the supervised feature selection, called supervised feature selection by constituting a basis for the original space of features and matrix factorization (SFS-BMF). To this end, SFS-BMF is a guided search to find a basis for the original space of features that inherently contains linearly independent features and can be replaced with the original space. For finding the best subset of features regarding the class attribute, information gain is utilized for the process of constructing a basis. In fact, a basis for the original features is constructed according to the most informative features in terms of the information gain. Then, this basis is decomposed through a matrix factorization form in order to select a subset of features. Our proposed method guarantees the maximum relevancy of selected features to the output by using the information gain while simultaneously secures the minimum redundancy among them based on the linear independence property. Several experiments on high-dimensional microarray datasets are conducted for illustrating the efficiency of SFS-BMF. The experimental results show that the proposed SFS-BMF method outperforms some state-of-the-art feature selection methods with respect to classification performance and also according to the computational complexity.

关键词： Feature selection Subspace learning Linear independence Basis of features microarray datasets

来源：评论

学校读者我要写书评

暂无评论

An efficient method to identify differentially expressed genes in microarray experiments

引用

BIOINFORMATICS 2008年第14期24卷 1583-1589页

作者： Qin, Huaizhen Feng, Tao Harding, Scott A. Tsai, Chung-Jui Zhang, Shuanglin Michigan Technol Univ Dept Math Sci Sch Forest Resources & Environm Sci Houghton MI 49931 USA Michigan Technol Univ Biotechnol Res Ctr Sch Forest Resources & Environm Sci Houghton MI 49931 USA Heilongjiang Univ Dept Math Harbin 150080 Peoples R China

Motivation: microarray experiments typically analyze thousands to tens of thousands of genes from small numbers of biological replicates. The fact that genes are normally expressed in functionally relevant patterns suggests that gene-expression data can be stratified and clustered into relatively homogenous groups. Cluster-wise dimensionality reduction should make it feasible to improve screening power while minimizing information loss. Results: We propose a powerful and computationally simple method for finding differentially expressed genes in small microarray experiments. The method incorporates a novel stratification-based tight clustering algorithm, principal component analysis and information pooling. Comprehensive simulations show that our method is substantially more powerful than the popular SAM and eBayes approaches. We applied the method to three real microarray datasets: one from a Populus nitrogen stress experiment with 3 biological replicates;and two from public microarray datasets of human cancers with 10 to 40 biological replicates. In all three analyses, our method proved more robust than the popular alternatives for identification of differentially expressed genes.

关键词： .tight principal component powerful propose expressed genes gene-expression microarray experiments Populus Computationally microarray datasets biological replicates method to identify eBayes

来源：评论

学校读者我要写书评

暂无评论

Biostatistical approaches for the reconstruction of gene co-expression networks based on transcriptomic data

引用

BRIEFINGS IN FUNCTIONAL GENOMICS 2013年第5期12卷 457-467页

作者： Lopez-Kleine, Liliana Leal, Luis Lopez, Camilo Univ Nacl Colombia Stat Program Bogota Colombia Univ Nacl Colombia Dept Biol Manihot Biotec Grp Bogota Colombia

Techniques in molecular biology have permitted the gathering of an extremely large amount of information relating organisms and their genes. The current challenge is assigning a putative function to thousands of genes that have been detected in different organisms. One of the most informative types of genomic data to achieve a better knowledge of protein function is gene expression data. Based on gene expression data and assuming that genes involved in the same function should have a similar or correlated expression pattern, a function can be attributed to those genes with unknown functions when they appear to be linked in a gene co-expression network (GCN). Several tools for the construction of GCNs have been proposed and applied to plant gene expression data. Here, we review recent methodologies used for plant gene expression data and compare the results, advantages and disadvantages in order to help researchers in their choice of a method for the construction of GCNs.

关键词： gene co-expression networks microarray datasets transcriptomics plants gene functional prediction

来源：评论

学校读者我要写书评

暂无评论

Screening and identification of key biomarkers in alimentary tract cancers: A bioinformatic analysis

引用

CANCER BIOMARKERS 2020年第2期29卷 221-233页

作者： Cai, Zeling Wei, Yi Chen, Shuai Gong, Yu Fu, Yue Dai, Xianghua Zhou, Yan Yang, Haojun Tang, Liming Liu, Hanyang Nantong Univ Affiliated Haimen Peoples Hosp Genter Gen Surg Nantong Jiangsu Peoples R China Nanjing Med Univ Ctr Gastrointestinal Dis Affiliated Changzhou Peoples Hosp 2 68 Gehu Rd Changzhou Jiangsu Peoples R China

BACKGROUND: Alimentary tract cancers (ATCs) are the most malignant cancers in the world. Numerous studies have revealed the tumorigenesis, diagnosis and treatment of ATCs, but many mechanisms remain to be explored. METHODS: To identify the key genes of ATCs, microarray datasets of oesophageal cancer, gastric cancer and colorectal cancer were obtained from the Gene Expression Omnibus (GEO) database. In total, 207 differentially expressed genes (DEGs) were screened. KEGG and GO function enrichment analyses were conducted, and a protein-protein interaction (PPI) network was generated and gene modules analysis was performed using STRING and Cytoscape. RESULTS: Five hub genes were screened, and the associated biological processes indicated that these genes were mainly enriched in cellular processes, protein binding and metabolic processes. Clinical survival analysis showed that COL10A1 and KIF14 may be significantly associated with the tumorigenesis or pathology grade of ATCs. In addition, relative human ATC cell lines along with blood samples and tumour tissues of ATC patients were obtained. The data proved that high expression of COL10A1 and KIF14 was associated with tumorigenesis and could be detected in blood. CONCLUSION: In conclusion, the identification of hub genes in the present study helped us to elucidate the molecular mechanisms of tumorigenesis and identify potential diagnostic indicators and targeted treatment for ATCs.

关键词： Alimentary tract cancers differentially expressed genes microarray datasets enrichment analysis survival analysis

来源：评论

学校读者我要写书评

暂无评论

P3H4 and PLOD1 expression associates with poor prognosis in bladder cancer

引用

CLINICAL & TRANSLATIONAL ONCOLOGY 2022年第8期24卷 1524-1532页

作者： Zhang, Junjie Dong, Yang Shi, Zhenduo He, Houguang Chen, Jiangang Zhang, Shaoqi Wu, Wei Zhang, Qianjin Han, Conghui Hao, Lin Soochow Univ Med Coll Suzhou 215123 Jiangsu Peoples R China Xuzhou Cent Hosp Dept Urol 199 Jiefang South Rd Xuzhou 221009 Jiangsu Peoples R China

Purpose The prolyl 3-hydroxylase family member 4 gene (P3H4) is involved in the development of human cancers. The association of P3H4 with bladder cancer (BC) prognosis is unclear. This study aimed to analyze the association of P3H4 with BC prognosis. Methods RNA-Seq data were downloaded from The Cancer Genome Atlas project and BC microarray datasets (GSE13507, GSE31684, and GSE32548) were downloaded from the Gene Expression Omnibus database. We analyzed the differences in P3H4 expression levels between BC tumors and non-tumor tissues and between samples with different clinical information. The association of P3H4 and P3H4-related genes with BC prognosis and the possibility of using P3H4 expression as a prognostic biomarker in BC patients were also analyzed. RevMan was used to perform the meta-analysis. Results P3H4 was upregulated in BC tissues compared with the adjacent non-tumor tissues (p = 4.06e-08). Univariate Cox regression analysis and meta-analysis showed that high P3H4 expression level contributed to a poor BC prognosis (Hazard ratio, HR = 1.348, 95% CI 1.140-1.594, p = 4.89e-04;meta-analysis: HR = 1.45, 95% CI 1.10-1.91;p = 9.00e-03). Among the genes related to P3H4, the PLOD1 gene was closely associated with P3H4 expression (r = 0.620, p = 2.49e-44). Also, a meta-analysis showed that PLOD1 expression was associated with a poor prognosis in BC patients (HR = 1.77, 95% CI 1.31-2.38;p = 2.00e-04). Conclusions The P3H4 and PLOD1 genes might be used as reliable prognostic biomarkers for BC.

关键词： Bladder cancer Prognostic biomarker Meta-analysis Overall survival microarray datasets

来源：评论

学校读者我要写书评

暂无评论

Compendium of TCDD-mediated transcriptomic response datasets in mammalian model systems

引用

BMC GENOMICS 2017年第1期18卷 1-8页

作者： Prokopec, Stephenie D. Houlahan, Kathleen E. Sun, Ren X. Watson, John D. Yao, Cindy Q. Lee, Jamie P'ng, Christine Pang, Renee Wu, Alexander H. Chong, Lauren C. Smith, Ashley B. Harding, Nicholas J. Moffat, Ivy D. Linden, Jere Lensu, Sanna Okey, Allan B. Pohjanvirta, Raimo Boutros, Paul C. Ontario Inst Canc Res Informat & Biocomp Program 661 Univ AveSuite 510 Toronto ON M5G 0A3 Canada Univ Toronto Dept Pharmacol & Toxicol Toronto ON Canada Univ Helsinki Dept Vet Biosci Helsinki Finland Univ Jyvaskyla Dept Biol Phys Act Jyvaskyla Finland Natl Inst Hlth & Welf Dept Environm Hlth Kuopio Finland Natl Inst Hlth & Welf Toxicol Lab Kuopio Finland Univ Helsinki Dept Food Hyg & Environm Hlth Helsinki Finland Univ Toronto Dept Med Biophys Toronto ON Canada

Background: 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD) is the most potent congener of the dioxin class of environmental contaminants. Exposure to TCDD causes a wide range of toxic outcomes, ranging from chloracne to acute lethality. The severity of toxicity is highly dependent on the aryl hydrocarbon receptor (AHR). Binding of TCDD to the AHR leads to changes in transcription of numerous genes. Studies evaluating the transcriptional changes brought on by TCDD may provide valuable insight into the role of the AHR in human health and disease. We therefore compiled a collection of transcriptomic datasets that can be used to aid the scientific community in better understanding the transcriptional effects of ligand-activated AHR. Results: Specifically, we have created a datasets package - TCDD. Transcriptomics - for the R statistical environment, consisting of 63 unique experiments comprising 377 samples, including various combinations of 3 species ( human derived cell lines, mouse and rat), 4 tissue types (liver, kidney, white adipose tissue and hypothalamus) and a wide range of TCDD exposure times and doses. These datasets have been fully standardized using consistent preprocessing and annotation packages (available as of September 14, 2015). To demonstrate the utility of this R package, a subset of "AHR-core" genes were evaluated across the included datasets. Ahrr, Nqo1 and members of the Cyp family were significantly induced following exposure to TCDD across the studies as expected while Aldh3a1 was induced specifically in rat liver. Inmt was altered only in liver tissue and primarily by rat-AHR. Conclusions: Analysis of the "AHR-core" genes demonstrates a continued need for studies surrounding the impact of AHR-activity on the transcriptome;genes believed to be consistently regulated by ligand-activated AHR show surprisingly little overlap across species and tissues. Until now, a comprehensive assessment of the transcriptome across these studies was challenging due

关键词： TCDD AHR microarray datasets R

来源：评论

学校读者我要写书评

暂无评论

Genome-scale meta-analysis of breast cancer datasets identifies promising targets for drug development

引用

JOURNAL OF BIOLOGICAL RESEARCH-THESSALONIKI 2021年第1期28卷 1-15页

作者： Altaf, Reem Nadeem, Humaira Babar, Mustafeez Mujtaba Ilyas, Umair Muhammad, Syed Aun Riphah Int Univ Dept Pharmaceut Chem Fac Pharmaceut Sci Islamabad 44000 Pakistan Shifa Tameer E Millat Univ Shifa Coll Pharmaceut Sci Islamabad 44000 Pakistan Riphah Int Univ Dept Pharmaceut Fac Pharmaceut Sci Islamabad 44000 Pakistan Bahauddin Zakariya Univ Inst Mol Biol & Biotechnol Multan 66000 Pakistan

Background Because of the highly heterogeneous nature of breast cancer, each subtype differs in response to several treatment regimens. This has limited the therapeutic options for metastatic breast cancer disease requiring exploration of diverse therapeutic models to target tumor specific biomarkers. Methods Differentially expressed breast cancer genes identified through extensive data mapping were studied for their interaction with other target proteins involved in breast cancer progression. The molecular mechanisms by which these signature genes are involved in breast cancer metastasis were also studied through pathway analysis. The potential drug targets for these genes were also identified. Results From 50 DEGs, 20 genes were identified based on fold change and p-value and the data curation of these genes helped in shortlisting 8 potential gene signatures that can be used as potential candidates for breast cancer. Their network and pathway analysis clarified the role of these genes in breast cancer and their interaction with other signaling pathways involved in the progression of disease metastasis. The miRNA targets identified through miRDB predictor provided potential miRNA targets for these genes that can be involved in breast cancer progression. Several FDA approved drug targets were identified for the signature genes easing the therapeutic options for breast cancer treatment. Conclusion The study provides a more clarified role of signature genes, their interaction with other genes as well as signaling pathways. The miRNA prediction and the potential drugs identified will aid in assessing the role of these targets in breast cancer.

关键词： Breast cancer microarray datasets Pathway enrichment analysis Gene ontology miRNA Drug-gene network

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for microarray Data Classification Using Hybrid Information Gain and a Modified Binary Krill Herd Algorithm

引用

INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES 2020年第3期12卷 288-301页

作者： Zhang, Ge Hou, Jincui Wang, Jianlin Yan, Chaokun Luo, Junwei Henan Univ Sch Comp & Informat Engn Kaifeng Peoples R China Henan Univ Henan Engn Res Ctr Intelligent Technol & Applicat Kaifeng 475004 Peoples R China Henan Polytech Univ Coll Comp Sci & Technol Jiaozuo Henan Peoples R China

Due to the presence of irrelevant or redundant data in microarray datasets, capturing potential patterns accurately and directly via existing models is difficult. Feature selection (FS) has become a necessary strategy to identify and screen out the most relevant attributes. However, the high dimensionality of microarray datasets poses a serious challenge to most existing FS algorithms. For this purpose, we propose a novel feature selection strategy in this paper, called IG-MBKH. A pre-screening method of feature ranking which is based on information gain (IG) and an improved binary krill herd (MBKH) algorithm are integrated in this strategy. When searching for feature subsets using MBKH, a hyperbolic tangent function, an adaptive transfer factor, and a chaos memory weight factor are introduced to facilitate a better searching the possible feature subsets. The results indicates that the IG-MBKH algorithm can achieve improvement in convergence, the number of features and classification accuracy when compared to the BKH, MBKH, and several newest algorithms. Furthermore, we evaluate the impact of different classifiers on the performance of the strategy we propose.

关键词： Feature selection Modified binary krill herd algorithm Information gain microarray datasets

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Recursive Firefly Algorithm for Informative Gene Selection

引用

INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH 2019年第2期10卷 21-33页

作者： Dif, Nassima Elberrichi, Zakaria Univ Djillali Liabes Sidi Bel Abbes EEDIS Lab Sidi Bel Abbes Algeria

Feature selection is the process of identifying good performing combinations of significant features among many possibilities. This preprocess improves the classification accuracy and facilitates the learning task. For this optimization problem, the authors have used a metaheuristics approach. Their main objective is to propose an enhanced version of the firefly algorithm as a wrapper approach by adding a recursive behavior to improve the search of the optimal solution. They applied SVM classifier to investigate the proposed method. For the authors experimentations, they have used the benchmark microarray datasets. The results show that the new enhanced recursive FA (RFA) outperforms the standard version with a reduction of dimensionality for all the datasets. As an example, for the leukemia microarray dataset, they have a perfect performance score of 100% with only 18 informative selected genes among the 7,129 of the original dataset. The RFA was competitive compared to other state-of-art approaches and achieved the best results for CNS, Ovarian cancer, MLL, prostate, Leukemia_4c, and lymphoma datasets.

关键词： Classification Data Mining Data Preprocessing Data Reduction Feature Selection Firefly Algorithm Metaheuristic microarray datasets Recursion SVM Algorithm

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：