检索结果-内蒙古大学图书馆

Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large microarray expression data Sets

Parsimonious Computing: A Minority Training Regime for Effec...

引用

International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Sridhar, Shailesh Saha, Snehanshu Shaikh, Azhar Yedida, Rahul Saha, Sriparna PES Univ Dept Comp Sci Bangalore Karnataka India BITS Pilani Dept Comp Sci & Informat Syst KK Birla Goa Campus Sancoale Goa India BITS Pilani APPCAIR KK Birla Goa Campus Sancoale Goa India PES Univ Dept Elect & Commun Bangalore Karnataka India North Carolina State Univ Dept Comp Sci Raleigh NC USA IIT Patna Dept Comp Sci & Engn Patna Bihar India

ISBN: (纸本)9781728169262

Rigorous mathematical investigation of learning rates used in back-propagation in shallow neural networks has become a necessity. This is because experimental evidence needs to be endorsed by a theoretical background. Such theory may be helpful in reducing the volume of experimental effort to accomplish desired results. We leveraged the functional property of Mean Square Error, which is Lipschitz continuous to compute learning rate in shallow neural networks. We claim that our approach reduces tuning efforts, especially when a significant corpus of data has to be handled. We achieve remarkable improvement in saving computational cost while surpassing prediction accuracy reported in literature. The learning rate, proposed here, is the inverse of the Lipschitz constant. The work results in a novel method for carrying out gene expression inference on large microarray data sets with a shallow architecture constrained by limited computing resources. A combination of random sub-sampling of the dataset, an adaptive Lipschitz constant inspired learning rate and a new activation function, A-ReLU helped accomplish the results reported in the paper.

关键词： Lipschitz Constant Adapative Learning microarray expression data A-Relu Mean Square Loss Mean Absolute Error

来源：评论

学校读者我要写书评

暂无评论

Improved swarm-optimization-based filter-wrapper gene selection from microarray data for gene expression tumor classification

引用

PATTERN ANALYSIS AND APPLICATIONS 2023年第2期26卷 455-472页

作者： Ke, Lin Li, Min Wang, Lei Deng, Shaobo Ye, Jun Yu, Xiang Nanchang Inst Technol Sch Informat Engn Nanchang Jiangxi Peoples R China

A typical microarray dataset usually contains thousands of genes, but only a small number of samples. It is in fact that most genes in a DNA microarray dataset are not relevant for classification. Identifying highly discriminating genes, known as biomarkers, is a challenging task for machine learning-based tumor classification. This study focuses on swarm-optimization-based filter-wrapper gene selection. In general, this type of hybrid gene selection consists of two steps: The first step is the filter step, which selects a small top-n percentage of genes and obtains reduced data;then, the second step searches for the optimal gene subset based on a wrapper model from the remaining genes by using a swarm-optimization-based algorithm. However, the second step of the existing swarm-optimization-based filter-wrapper gene selection is to search only from the remaining genes without using the ranking information of the remaining genes. This new study attempts to fill the gap that has been neglected in the area of swarm-optimization-based filter-wrapper gene selection. In this study, population initialization based on ranking criteria (PIRC) is proposed to transform the population initialization of genetic algorithm (GA) and ant colony optimization (ACO), which are called PIRCGA and PIRCACO, respectively. The experiment was carried out on 17 microarray expression datasets, and the two groups of IG-GA vs. IG-PIRCGA and IG-ACO vs. IG-PIRCACO were compared, respectively. The experimental results prove the efficiency of our proposed methods.

关键词： Filter-wrapper gene selection microarray expression data Swarm-based optimization Population initialization Genetic algorithm Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Mg deficiency interacts with the circadian clock and phytochromes pathways in Arabidopsis

引用

ANNALS OF APPLIED BIOLOGY 2021年第2期178卷 387-399页

作者： Riviere, Quentin Xiao, Qiying Gutsch, Annelie Defrance, Matthieu Webb, Alex A. R. Verbruggen, Nathalie Univ Libre Bruxelles Brussels Bioengn Sch Lab Plant Physiol & Mol Genet B-1050 Brussels Belgium Chinese Acad Sci Shanghai Inst Plant Physiol & Ecol CAS JIC Ctr Excellence Plant & Microbial Sci CEPA Ctr Excellence Mol Plant Sci CEMPS Beijing Peoples R China Univ Libre Bruxelles Machine Learning Grp Interuniv Inst Bioinformat Brussels Brussels Belgium Univ Cambridge Dept Plant Sci Cambridge England

Little is known about the relationship between nutrition and the circadian clock in plants. The first global transcriptomic study in plants of the response to magnesium deficiency (-Mg) revealed that the circadian clock was affected in the Arabidopsis thaliana model species. Interactions between the circadian clock and Mg status were here investigated in the light of recent knowledge. We highlight the wide disturbances caused by -Mg within the central oscillator and, reciprocally, the probable pervasive influence of the circadian clock on the response to -Mg. We provide evidence that light signalling pathways are likely to be involved in the input of Mg status to the circadian oscillator and that they interact with the circadian clock to coregulate an important part of the transcriptomic response. We further studied PIF3 LIKE 1 (PIL1) because it strongly and early responded, before the core genes of the circadian oscillator, and was a representative regulator of light signalling that interacts with the circadian oscillator. Furthermore, the far-red light-responsive genes, which are related to PIL1, were more enriched among the -Mg-deregulated genes than those responding to red, blue and intense lights. Finally, pil1 mutants had an altered response to -Mg notably by losing the upregulation of PSEUDO-RESPONSE REGULATOR 9, a core circadian oscillator. In short, we have further characterised the interactions between the Mg status and the circadian clock and identified the involvement of light signalling pathways in the response to Mg status. In particular, we have illustrated the role of a light-signalling component in the regulation of the circadian oscillator and physiological processes during Mg starvation.

关键词： Arabidopsis circadian clock light input Mg deficiency microarray expression data

来源：评论

学校读者我要写书评

暂无评论

New drug candidates for osteosarcoma: Drug repurposing based on gene expression signature

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2021年 134卷 104470-104470页

作者： Andrade, Raissa Coelho Boroni, Mariana Amazonas, Marion Kielmanowicz Vargas, Fernando Regla Oswaldo Cruz Fdn FIOCRUZ Birth Defects Epidemiol Lab Av. Brasil 4365 Pavilhao Leonidas deane Sala 617 Rio De Janeiro Brazil State Rio Janeiro UNIRIO Fed Univ Genet & Mol Biol Dept Rio De Janeiro Brazil Brazilian Natl Canc Inst INCA Div Expt & Translat Res Bioinformat & Computat Biol Lab Rio De Janeiro Brazil Univ Campinas UNICAMP Expt Med Res Cluster EMRC Campinas Brazil

Osteosarcoma (OS) is an aggressive bone malignancy and the third most common cancer in adolescence. Since the late 1970s, OS therapy and prognosis had only modest improvements, making it appealing to explore new tools that could help ameliorate the treatment. We present a meta-analysis of the gene expression signature of primary OS, and propose small molecules that could reverse this signature. The meta-analysis was performed using GEO microarray series. We first compared gene expression from eleven primary OS against osteoblasts to obtain the differentially expressed genes (DEGs). We later filtered those DEGs by verifying which ones had a concordant direction of differential expression in a validation group of 82 OS samples versus 30 bone marrow mesenchymal stem cells (BM-MSC) samples. A final gene expression signature of 266 genes (98 up and 168 down regulated) was obtained. The L1000CDS(2) engine was used for drug repurposing. The top molecules predicted to reverse the signature were afatinib (PubChem CID 10184653), BRD-K95196255 (PubChem CID 3242434), DG-041 (PubChem CID 11296282) and CA-074 Me (PubChem CID 23760717). Afatinib (Gilotrif (TM)) is currently used for metastatic non-small-cell lung cancer with EGFR mutations, and in vitro evidence shows antineoplastic potential in OS cells. The other three molecules have reports of antineoplastic effects, but are not currently FDA-approved. Further studies are necessary to establish the potential of these drugs in OS treatment. We believe our results can be an important contribution for the investigation of new therapeutic genetic targets and for selecting new drugs to be tested for OS.

关键词： Osteosarcoma microarray expression data Gene expression signature Drug repurposing Afatinib

来源：评论

学校读者我要写书评

暂无评论

Informative gene selection and the direct classification of tumors based on relative simplicity

引用

BMC BIOINFORMATICS 2016年第1期17卷 1-16页

作者： Chen, Yuan Wang, Lifeng Li, Lanzhi Zhang, Hongyan Yuan, Zheming Hunan Prov Key Lab Biol & Control Plant Dis & Ins Changsha Hunan Peoples R China Hunan Agr Univ Hunan Prov Key Lab Germplasm Innovat & Utilizat C Changsha Hunan Peoples R China Hunan Acad Agr Sci Biotechnol Res Ctr Changsha Hunan Peoples R China

Background: Selecting a parsimonious set of informative genes to build highly generalized performance classifier is the most important task for the analysis of tumor microarray expression data. Many existing gene pair evaluation methods cannot highlight diverse patterns of gene pairs only used one strategy of vertical comparison and horizontal comparison, while individual-gene-ranking method ignores redundancy and synergy among genes. Results: Here we proposed a novel score measure named relative simplicity (RS). We evaluated gene pairs according to integrating vertical comparison with horizontal comparison, finally built RS-based direct classifier (RS-based DC) based on a set of informative genes capable of binary discrimination with a paired votes strategy. Nine multi-class gene expression datasets involving human cancers were used to validate the performance of new method. Compared with the nine reference models, RS-based DC received the highest average independent test accuracy (91.40 %), the best generalization performance and the smallest informative average gene number (20.56). Compared with the four reference feature selection methods, RS also received the highest average test accuracy in three classifiers (Naive Bayes, k-Nearest Neighbor and Support Vector Machine), and only RS can improve the performance of SVM. Conclusions: Diverse patterns of gene pairs could be highlighted more fully while integrating vertical comparison with horizontal comparison strategy. DC core classifier can effectively control over-fitting. RS-based feature selection method combined with DC classifier can lead to more robust selection of informative genes and classification accuracy.

关键词： microarray expression data Gene selection Direct classify Relative simplicity Binary-discriminative informative genes Paired votes

来源：评论

学校读者我要写书评

暂无评论

Adaptive modelling of gene regulatory network using Bayesian information criterion-guided sparse regression approach

引用

IET SYSTEMS BIOLOGY 2016年第6期10卷 252-259页

作者： Shi, Ming Shen, Weiming Wang, Hong-Qiang Chong, Yanwen Chinese Acad Sci Inst Intelligent Machines Machine Intelligence & Computat Biol Lab POB 1130 Hefei 230031 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R 129 Luoyu Rd Wuhan 430079 Peoples R China

Inferring gene regulatory networks (GRNs) from microarray expression data are an important but challenging issue in systems biology. In this study, the authors propose a Bayesian information criterion (BIC)-guided sparse regression approach for GRN reconstruction. This approach can adaptively model GRNs by optimising the l(1)-norm regularisation of sparse regression based on a modified version of BIC. The use of the regularisation strategy ensures the inferred GRNs to be as sparse as natural, while the modified BIC allows incorporating prior knowledge on expression regulation and thus avoids the overestimation of expression regulators as usual. Especially, the proposed method provides a clear interpretation of combinatorial regulations of gene expression by optimally extracting regulation coordination for a given target gene. Experimental results on both simulation data and real-world microarray data demonstrate the competent performance of discovering regulatory relationships in GRN reconstruction.

关键词： genetics Bayes methods genomics regression analysis inference mechanisms bioinformatics adaptive modelling gene regulatory network Bayesian information criterion-guided sparse regression approach GRN microarray expression data systems biology GRN reconstruction optimisation l(1)-norm regularisation

来源：评论

学校读者我要写书评

暂无评论

COMPUTATIONAL EVIDENCE FROM TWO CORRELATED data SOURCES AT DIFFERENT MOLECULAR LEVELS FOR AF-VHD-SPECIFIC MICRORNA SIGNATURE

引用

JOURNAL OF BIOLOGICAL SYSTEMS 2016年第2-3期24卷 295-309页

作者： Feng, Wei Rao, Nini Wan, Yongli Li, San Zheng, Ji Zeng, Wei Wang, Guangbin Chen, Xu Univ Elect Sci & Technol China Key Lab NeuroInformat Minist Educ Ctr Informat BioMedSch Life Sci & Technol Chengdu 610000 Peoples R China Sichuan Acad Med Sci Cardiovasc Dept Chengdu 610000 Peoples R China Sichuan Prov Peoples Hosp Chengdu 610000 Peoples R China 4 Sect 2North Jianshe Rd Chengdu 610054 Peoples R China

The important roles of microRNAs (miRNAs) in the pathological process of the cardiovascular system have been recognized. However, identification of miRNAs related to valvular heart disease with atrial fibrillation (AF-VHD) has been difficult and very slow because of complex pathological mechanism of AF-VHD. Analysis of microarray expression profiles provides the possibility to rapid prediction of disease-regulating miRNAs and can lay a theoretical foundation for further experimental studies. A computational method is proposed to predict AF-VHD-specific miRNAs by combining miRNA and gene expression data, which are strongly correlated. Using the proposed method, a 45-miRNA AF-VHD-specific signature is predicted. Compared with other related results, 15 of 45 miRNAs are the same and the rest 30 miRNAs are different. Our analysis shows that 11 of 30 new miRNAs are associated with the diseases inducing AF-VHD and the remaining 19 miRNAs have good combinational discrimination power. Therefore, the AF-VHD signature we have predicted is confirmed to be reliable and specific. In a word, this study proposes an effective computational strategy in prediction of disease-regulating miRNAs and finds some AF-VHD-specific miRNAs, which provides new insight into the further experimental study and molecular mechanism leading to the development of AF-VHD.

关键词： Valvular Heart Disease with Atrial Fibrillation (AF-VHD) microarray expression data Correlation miRNA Prediction

来源：评论

学校读者我要写书评

暂无评论

A Signaling Pathway Analysis Model Based on Kullback-Leibler Divergence 4

A Signaling Pathway Analysis Model Based on Kullback-Leibler...

引用

4th International Symposium on Bioelectronics and Bioinformatics (ISBB)

作者： Wei, Hang Zheng, Haoran Xu, Yang Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230026 Peoples R China

ISBN: (纸本)9781467366106

Abnormal regulation of signaling pathways is the key factor to cause disease. Many works focus on identifying the significantly differential pathways between diseases and normal samples via microarray gene expression datasets. However, it is general for exiting methods to concentrate on the difference of pathway components, either the expression or correlation among genes in a given pathway. Thus this will ignore the overall change of pathway. Here we present a powerful analysis model based on the concept of Kullback-Leibler divergence, which mainly measure the difference between two probability distributions of regulation capacity well. We compared our approach with other three classical algorithms on four different human expression datasets, and the results indicate that the capability of our method in detecting disturbed pathways is superior to previous approaches. In conclusion, via introducing the idea of Kullback-Leibler divergence, measure the whole difference of pathway from an overall perspective will provide a complementary analysis framework of pathway analysis.

关键词： Pathway analysis Kullback-Leibler divergence microarray expression data difference analysis

来源：评论

学校读者我要写书评

暂无评论

Integrated Study to Infer Dynamic Protein-gene Interactions in human P53 Regulatory Networks

Integrated Study to Infer Dynamic Protein-gene Interactions ...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Wang, Junbai Wu, Qianqian Tian, Tianhai Norwegian Radium Hosp Oslo Univ Hosp Dept Pathol N-0310 Oslo Norway Monash Univ Sch Math Sci Melbourne Vic 3800 Australia

ISBN: (纸本)9781467367981

Investigating the dynamics of genetic regulatory networks through high throughput experimental data, such as microarray gene expression profiles, is very important but challenging. One of the major hindrances in building detailed mathematical models for genetic regulation is the large number of unknown model parameters. To tackle this problem, a new integrated method is proposed by combining both the top-down and bottom-up approaches. Firstly, a top-down approach, using probability graphical models, is employed to predict the network structure of DNA repair pathway that involves p53 regulation. Then, a bottom-up approach, using differential equation models, is applied to study the detailed genetic regulations based on either a fully-connected regulatory network or gene networks inferred with the top-down approach. Optimal network is selected based on model simulation error and robustness property. Overall, the proposed new integrated method is efficient for studying large dynamical genetic regulations.

关键词： Genetic regulation microarray expression data Network inference DNA repair pathway

来源：评论

学校读者我要写书评

暂无评论

A signaling pathway analysis method based on information divergence

A signaling pathway analysis method based on information div...

引用

12th International Symposium on Operations Research and its Applications in Engineering, Technology and Management (ISORA 2015)

作者： Hang Wei Hao-Ran Zheng University of Science and Technology of China Hefei Anhui CN

ISBN: (纸本)9781510821224

Abnormal regulation of signaling pathways is the key factor causing disease. For better understanding disease mechanisms, many methods have been proposed to identify the significantly differential pathways between diseases and normal individuals via microarray gene expression datasets. Unlike previous common analysis processes, which is focused on merging gene difference into difference of pathway indirectly. In this paper, the idea of information divergence is introduced and a novel signaling pathway analysis method from a holistic view is presented to improve the detection results. We identify significantly differential pathways directly via computing the KL divergence between real and simulated probability distributions of gene-gene regulatory ability. We test our method on four human microarray expression datasets. The results illustrate that the capability of our approach in detecting significantly differential pathways between two sample groups is superior to other three classical pathway analysis methods.

关键词： Pathway analysis difference analysis information divergence microarray expression data

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：