检索结果-内蒙古大学图书馆

Exploring combinations of dimensionality reduction, transfer learning, and regularization methods for predicting binary phenotypes with transcriptomic data

引用

BMC BIOINFORMATICS 2024年第1期25卷 1页

作者： Oshternian, S. R. Loipfinger, S. Bhattacharya, A. Fehrmann, R. S. N. Univ Groningen Univ Med Ctr Groningen Dept Med Oncol POB 30-001 NL-9700 RB Groningen Netherlands

Background Numerous transcriptomic-based models have been developed to predict or understand the fundamental mechanisms driving biological phenotypes. However, few models have successfully transitioned into clinical practice due to challenges associated with generalizability and interpretability. To address these issues, researchers have turned to dimensionality reduction methods and have begun implementing transfer learning approaches. Methods In this study, we aimed to determine the optimal combination of dimensionality reduction and regularization methods for predictive modeling. We applied seven dimensionality reduction methods to various datasets, including two supervised methods (linear optimal low-rank projection and low-rank canonical correlation analysis), two unsupervised methods [principal component analysis and consensus independent component analysis (c-ICA)], and three methods [autoencoder (AE), adversarial variational autoencoder, and c-ICA] within a transfer learning framework, trained on > 140,000 transcriptomic profiles. To assess the performance of the different combinations, we used a cross-validation setup encapsulated within a permutation testing framework, analyzing 30 different transcriptomic datasets with binary phenotypes. Furthermore, we included datasets with small sample sizes and phenotypes of varying degrees of predictability, and we employed independent datasets for validation. Results Our findings revealed that regularized models without dimensionality reduction achieved the highest predictive performance, challenging the necessity of dimensionality reduction when the primary goal is to achieve optimal predictive performance. However, models using AE and c-ICA with transfer learning for dimensionality reduction showed comparable performance, with enhanced interpretability and robustness of predictors, compared to models using non-dimensionality-reduced data. Conclusion These findings offer valuable insights into the optimal combinati

关键词： Dimensionality reduction Transfer learning Predictive modeling transcriptomic data Independent component analysis Autoencoder

来源：评论

学校读者我要写书评

暂无评论

A bioinformatics workflow to decipher transcriptomic data from vitamin D studies

引用

JOURNAL OF STEROID BIOCHEMISTRY AND MOLECULAR BIOLOGY 2019年 189卷 28-35页

作者： Garcia, Amadeo Munoz Eijssen, Lars M. Kutmon, Martina Sarathy, Chaitra Cengo, Ardi Hewison, Martin Evelo, Chris T. Lenz, Michael Coort, Susan L. Maastricht Univ NUTRIM Sch Nutr & Translat Res Metab Dept Bioinformat BiGCaT POB 616 Maastricht Netherlands Univ Birmingham Inst Metab & Syst Res Birmingham B15 2TT W Midlands England Maastricht Univ Maastricht Ctr Syst Biol MaCSBio Maastricht Netherlands

The link between the experimental laboratory studies and bioinformatic approaches aims to find procedures to connect tools from both branches producing workflows that bring together different techniques that are capable of exploiting data at many levels. Thanks to the open access sources and the numerous tools available, it is possible to create various pipelines capable of solving specific problems. Nevertheless the lack of connectivity between them that interconnect different approaches complicates the exploitation of these workflows. Here, we present a detailed description of a workflow composed of different bioinformatics tools that exploits data from large-scale gene expression experiments, contextualizing them at many biological levels. To illustrate the relevance of our workflow for the vitamin D community we applied it to data from myeloid cell models treated with the hormonally active form of vitamin. From raw files of functional genomic studies it is possible to utilize the whole information to obtain a biological insight. Different software and algorithms are included to analyse at pathway, metabolic, ontology and molecular biology level the effects on gene expression. The usage of different databases to analyse gene expression data allows to perform a complete interpretation of functional genomic studies and the implementation of analysis and visualization software tools gives a better understanding of the biological meaning of the results. This review is an example of how to select and bring together several software modules to create one pipeline that processes and analyses genomic data at many biological levels making it open, reproducible and user friendly. Finally, the application of our bioinformatic pipeline revealed that vitamin D modulates crucial metabolic pathways in different myeloid cells that may play an important role in their immune function.

关键词： transcriptomic data Vitamin D Bioinfonnatics Biological pathways Network analysis

来源：评论

学校读者我要写书评

暂无评论

Density of points clustering, application to transcriptomic data analysis

引用

NUCLEIC ACIDS RESEARCH 2002年第18期30卷 3992-4000页

作者： Wicker, N Dembele, D Raffelsberger, W Poch, O ULP INSERM CNRS Inst Genet & Biol Mol & Cellulaire F-67404 Illkirch Graffenstaden France Univ Strasbourg 1 CNRS UPRESA 70005 LSIITICPS AXE E F-67400 Illkirch Graffenstaden France

With the increasing amount of data produced by high-throughput technologies in many fields of science, clustering has become an integral step in exploratory data analysis in order to group similar elements into classes. However, many clustering algorithms can only work properly if aided by human expertise. For example, one parameter which is crucial and often manually set is the number of clusters present in the analyzed set. We present a novel stopping rule to find the optimal number of clusters based on the comparison of the density of points inside the clusters and between them. The method is evaluated on synthetic as well as on real transcriptomic data and compared with two current methods. Finally, we illustrate its usefulness in the analysis of the expression profiles of promyelocytic cells before and after treatment with all-trans retinoic acid. Simultaneous clustering for gene regulation and absolute initial expression levels allowed the identification of numerous genes associated with signal transduction revealing the complexity of retinoic acid signaling.

关键词： .Density gene regulation points expression levels retinoic clustering algorithms transcriptomic data number of clusters

来源：评论

学校读者我要写书评

暂无评论

Outcome-guided sparse K-means for disease subtype discovery via integrating phenotypic data with high-dimensional transcriptomic data

引用

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS 2022年第2期71卷 352-375页

作者： Meng, Lingsong Avram, Dorina Tseng, George Huo, Zhiguang Univ Florida Dept Biostat 2004 Mowry Rd Gainesville FL 32611 USA H Lee Moffitt Canc Ctr & Res Inst Dept Immunol Tampa FL 33612 USA Univ Pittsburgh Dept Biostat Pittsburgh PA 15260 USA

The discovery of disease subtypes is an essential step for developing precision medicine, and disease subtyping via omics data has become a popular approach. While promising, subtypes obtained from existing approaches are not necessarily associated with clinical outcomes. With the rich clinical data along with the omics data in modern epidemiology cohorts, it is urgent to develop an outcome-guided clustering algorithm to fully integrate the phenotypic data with the high-dimensional omics data. Hence, we extended a sparse K-means method to an outcome-guided sparse K-means (GuidedSparseKmeans) method. An unified objective function was proposed, which was comprised of (i) weighted K-means to perform sample clusterings;(ii) lasso regularizations to perform gene selection from the high-dimensional omics data;and (iii) incorporation of a phenotypic variable from the clinical dataset to facilitate biologically meaningful clustering results. By iteratively optimizing the objective function, we will simultaneously obtain a phenotype-related sample clustering results and gene selection results. We demonstrated the superior performance of the GuidedSparseKmeans by comparing with existing clustering methods in simulations and applications of high-dimensional transcriptomic data of breast cancer and Alzheimer's disease. Our algorithm has been implemented into an R package, which is publicly available on GitHub ( ).

关键词： disease subtype outcome-guided clustering phenotypic data sparse K-means transcriptomic data

来源：评论

学校读者我要写书评

暂无评论

Integrating semantic transcriptomic data analysis and knowledge extraction from biological literature

Integrating semantic transcriptomic data analysis and knowle...

引用

IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)

作者： Podpecan, Vid Miljkovic, Dragana Petek, Marko Stare, Tsaja Gruden, Kristina Mozetic, Igor Lavrac, Nada Jozef Stefan Inst Ljubljana Slovenia Jozef Stefan Int Postgrad Sch Ljubljana Slovenia Natl Inst Biol Ljubljana Slovenia Univ Nova Gorica Nova Gorica Slovenia Univ Ljubljana Fac Math & Phys Ljubljana Slovenia

ISBN: (纸本)9781479913091;9781479913107

The paper presents an approach to the holistic analysis of transcriptomic data which integrates two state-ofthe-art methodologies into a coherent framework. The aim of the proposed approach is to give insight into the discovered patterns, help explaining the observed phenomena, enable the creation of new research hypotheses and assist in design of new experiments. We have integrated a methodology for semantic analysis of transcriptomic data, a system for automated extraction of biological relations from the literature, and a number of supporting components. The approach is demonstrated and evaluated on a publicly available dataset from a clinical trial in acute lymphoblastic leukaemia and a document corpus of full-text articles from the PubMed Open Access Subset.

关键词： transcriptomic data literature mining data explanation

来源：评论

学校读者我要写书评

暂无评论

Identification of candidate genes controlling fiber quality traits in upland cotton through integration of meta-QTL,significant SNP and transcriptomic data

引用

Journal of Cotton Research 2020年第4期3卷 324-335页

作者： XU Shudi PAN Zhenyuan YIN Feifan YANG Qingyong LIN Zhongxu WEN Tianwang ZHU Longfu ZHANG Dawei NIE Xinhui Key Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Coprs Agricultural CollegeShihezi UniversityShihezi 832000XinjiangChina Hubei Key Laboratory of Agricultural Bioinformatics College of InformaticsHuazhong Agricultural UniversityWuhan 430070HubeiChina National Key Laboratory of Crop Genetic Improvement College of Plant Science and TechnologyHuazhong Agricultural UniversityWuhan 430070HubeiChina Research Institute of Economic Crops Xinjiang Academy of Agricultural SciencesUrumqi 830091China

Background:Meta-analysis of quantitative trait locus(QTL)is a computational technique to identify consensus QTL and refine QTL positions on the consensus map from multiple mapping *** combination of meta-QTL intervals,significant SNPs and transcriptome analysis has been widely used to identify candidate genes in various ***:In our study,884 QTLs associated with cotton fiber quality traits from 12 studies were used for meta-QTL analysis based on reference genome TM-1,as a result,74 meta-QTLs were identified,including 19 meta-QTLs for fiber length;18 meta-QTLs for fiber strength;11 meta-QTLs for fiber uniformity;11 meta-QTLs for fiber elongation;and 15 meta-QTLs for *** with 8589 significant single nucleotide polymorphisms associated with fiber quality traits collected from 15 studies,297 candidate genes were identified in the meta-QTL intervals,20 of which showed high expression levels specifically in the developing *** to the function annotations,some of the 20 key candidate genes are associated with the fiber ***:This study provides not only stable QTLs used for marker-assisted selection,but also candidate genes to uncover the molecular mechanisms for cotton fiber development.

关键词： Fiber quality traits Meta-QTL Significant SNPs Candidate genes transcriptomic data

来源：评论

学校读者我要写书评

暂无评论

Insights on the evolution of metabolic networks of unicellular translationally biased organisms from transcriptomic data and sequence analysis

引用

JOURNAL OF MOLECULAR EVOLUTION 2005年第4期61卷 456-U28页

作者： Carbone, A Madden, R Univ Paris 06 INSERM U511 F-75013 Paris France Inst Hautes Etud Sci F-91440 Bures Sur Yvette France

Codon bias is related to metabolic functions in translationally biased organisms, and two facts are argued about. First, genes with high codon bias describe in meaningful ways the metabolic characteristics of the organism;important metabolic pathways corresponding to crucial characteristics of the lifestyle of an organism, such as photosynthesis, nitrification, anaerobic versus aerobic respiration, sulfate reduction, methanogenesis, and others, happen to involve especially biased genes. Second, gene transcriptional levels of sets of experiments representing a significant variation of biological conditions strikingly confirm, in the case of Saccharomyces cerevisiae, that metabolic preferences are detectable by purely statistical analysis: the high metabolic activity of yeast during fermentation is encoded in the high bias of enzymes involved in the associated pathways, suggesting that this genome was affected by a strong evolutionary pressure that favored a predominantly fermentative metabolism of yeast in the wild. The ensemble of metabolic pathways involving enzymes with high codon bias is rather well defined and remains consistent across many species, even those that have not been considered as translationally biased, such as Helicobacter pylori, for instance, reveal some weak form of translational bias for this genome. We provide numerical evidence, supported by experimental data, of these facts and conclude that the metabolic networks of translationally biased genomes, observable today as projections of eons of evolutionary pressure, can be analyzed numerically and predictions of the role of specific pathways during evolution can be derived. The new concepts of Comparative Pathway Index, used to compare organisms with respect to their metabolic networks, and Evolutionary Pathway Index, used to detect evolutionarily meaningful bias in the genetic code from transcriptional data, are introduced.

关键词： codon bias metabolic networks unicellular organisms Codon Adaptation Index transcriptomic data

来源：评论

学校读者我要写书评

暂无评论

Analysis of Two-Component System in Pseudomonas aeruginosa PAO1 Using Publicly Available transcriptomic data

Analysis of Two-Component System in Pseudomonas aeruginosa P...

引用

全国农业生物化学与分子生物学第十六届学术研讨会

作者： Shaomin Yan Guang Wu National Engineering Research Center for Non-food Biorefinery Guangxi Academy of Sciences 98 Daling Road Nanning Guangxi530007 China

Pseudomonas aeruginosa is an opportunistic bacterium infecting humans,animals and *** terms of plants,it can cause soft rot,for example,in Arabidopsis thaliana(Thale cress)and Lactuca sativa(lettuce).On the other hand,*** can produce various phenazines,of which phenazine-1-carboxylic acid(PCA)is an important biopesticide with trade mark Shenqinmycin against a broad spectrum of plant ***-component systems in bacteria are important to sense environmental stimuli and regulate bacteria in response to environmental *** a model bacterium,*** has about 140 genes related to two-component *** it is important to understand how those two-component systems respond to different environmental stimuli altogether,which will also help to enrich our knowledge on the production of *** this study,the publicly available transcriptomic data generated from GPL84 platform from NIH Gene Expression Omnibus(GEO)in 104 publications have been analyzed using co-expression *** results show the whole picture on how two-component system genes react to different environmental stimuli,and how these genes reorganized under different conditions.

关键词： Two-component systems Pseudomonas aeruginosa transcriptomic data GPL84

来源：评论

学校读者我要写书评

暂无评论

In silico secretome analysis approach for next generation sequencing transcriptomic data

引用

BMC GENOMICS 2011年第Sup3期12卷 S14-S14页

作者： Garg, Gagan Ranganathan, Shoba Macquarie Univ Dept Chem & Biomol Sci Sydney NSW 2109 Australia Natl Univ Singapore Yong Loo Lin Sch Med Dept Biochem Singapore 117597 Singapore

Background: Excretory/secretory proteins (ESPs) play a major role in parasitic infection as they are present at the host-parasite interface and regulate host immune system. In case of parasitic helminths, transcriptomics has been used extensively to understand the molecular basis of parasitism and for developing novel therapeutic strategies against parasitic infections. However, none of transcriptomic studies have extensively covered ES protein prediction for identifying novel therapeutic targets, especially as parasites adopt non-classical secretion pathways. Results: We developed a semi-automated computational approach for prediction and annotation of ES proteins using transcriptomic data from next generation sequencing platforms. For the prediction of non-classically secreted proteins, we have used an improved computational strategy, together with homology matching to a dataset of experimentally determined parasitic helminth ES proteins. We applied this protocol to analyse 454 short reads of parasitic nematode, Strongyloides ratti. From 296231 reads, we derived 28901 contigs, which were translated into 20877 proteins. Based on our improved ES protein prediction pipeline, we identified 2572 ES proteins, of which 407 (1.9%) proteins have classical N-terminal signal peptides, 923 (4.4%) were computationally identified as non-classically secreted while 1516 (7.26%) were identified by homology to experimentally identified parasitic helminth ES proteins. Out of 2572 ES proteins, 2310 (89.8%) ES proteins had homologues in the free-living nematode Caenorhabditis elegans and 2220 (86.3%) in parasitic nematodes. We could functionally annotate 1591 (61.8%) ES proteins with protein families and domains and establish pathway associations for 691 (26.8%) proteins. In addition, we have identified 19 representative ES proteins, which have no homologues in the host organism but homologous to lethal RNAi phenotypes in C. elegans, as potential therapeutic targets. Conclusion: We re

关键词： Next Generation Sequencing transcriptomic data Parasitic Nematode Next Generation Sequencing data Strongyloidiasis

来源：评论

学校读者我要写书评

暂无评论

Refinement of bamboo genome annotations through integrative analyses of transcriptomic and epigenomic data

引用

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL 2021年 19卷 2708-2718页

作者： Ma, Xuelian Zhao, Hansheng Yan, Hengyu Sheng, Minghao Cao, Yaxin Yang, Kebin Xu, Hao Xu, Wenying Gao, Zhimin Su, Zhen China Agr Univ Coll Biol Sci State Key Lab Plant Physiol & Biochem Beijing 100193 Peoples R China Int Ctr Bamboo & Rattan Inst Gene Sci & Industrializat Bamboo & Rattan Re Beijing Bamboo & Rattan Sci & Technol Key Lab Natl Forestry & Grassland Adm Beijing 100102 Peoples R China Qingdao Agr Univ Coll Agron Qingdao Shandong Peoples R China

Bamboo, one of the most crucial nontimber forest resources worldwide, has the capacity for rapid growth. In recent years, the genome of moso bamboo (Phyllostachys edulis) has been decoded, and a large amount of transcriptome data has been published. In this study, we generated the genome-wide profiles of the histone modification H3K4me3 in leaf, stem, and root tissues of bamboo. The trends in the distribution patterns were similar to those in rice. We developed a processing pipeline for predicting novel transcripts to refine the structural annotation of the genome using H3K4me3 ChIP-seq data and 29 RNA-seq datasets. As a result, 12,460 novel transcripts were predicted in the bamboo genome. Compared with the transcripts in the newly released version 2.0 of the bamboo genome, these novel transcripts are tissue-specific and shorter, and most have a single exon. Some representative novel transcripts were validated by semiquantitative RT-PCR and qRT-PCR analyses. Furthermore, we put these novel transcripts back into the ChIP-seq analysis pipeline and discovered that the percentages of H3K4me3 in genic elements were increased. Overall, this work integrated transcriptomic data and epigenomic data to refine the annotation of the genome in order to discover more functional genes and study bamboo growth and development, and the application of this predicted pipeline may help refine the structural annotation of the genome in other species. (C) 2021 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology.

关键词： Moso bamboo Genome annotation transcriptomic data Epigenomic data H3K4me3

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：