scholarly journals A tensor decomposition-based integrated analysis applicable to multiple gene expression profiles without sample matching

2021 ◽  
Author(s):  
Taguchi Y-h. ◽  
Turki Turki
Keyword(s):  
Gene Expression ◽  
Learning Strategies ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Tensor Decomposition ◽  
Integrated Analysis ◽  
Rna Seq ◽  
Prior Learning ◽  
Multiple Gene ◽  
Machine Learning Applications

Abstract The integrated analysis of multiple gene expression profiles measured in distinct studies is always problematic. Especially, missing sample matching and missing common labeling between distinct studies prevent the integration of multiple studies in fully data-driven and unsupervised manner. In this study, we propose a strategy enabling the integration of multiple gene expression profiles among multiple independent studies without either labeling or sample matching, using tensor decomposition-based unsupervised feature extraction. As an example, we applied this strategy to Alzheimer’s disease (AD)-related gene expression profiles that lack exact correspondence among samples as well as AD single-cell RNA-seq (scRNA-seq) data. We found that we could select biologically reasonable genes with integrated analysis. Overall, integrated gene expression profiles can function analogously to prior learning and/or transfer learning strategies in other machine learning applications. For scRNA-seq, the proposed approach was able to drastically reduce the required computational memory.

scholarly journals A tensor decomposition-based integrated analysis applicable to multiple gene expression profiles without sample matching

2021 ◽  
Author(s):  
Taguchi Y-h. ◽  
Turki Turki
Keyword(s):  
Gene Expression ◽  
Learning Strategies ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Tensor Decomposition ◽  
Integrated Analysis ◽  
Rna Seq ◽  
Prior Learning ◽  
Multiple Gene ◽  
Machine Learning Applications

Abstract The integrated analysis of multiple gene expression profiles measured in distinct studies is always problematic. Especially, missing sample matching and missing common labeling between distinct studies prevent the integration of multiple studies in fully data-driven and unsupervised manner. In this study, we propose a strategy enabling the integration of multiple gene expression profiles among multiple independent studies without either labeling or sample matching, using tensor decomposition-based unsupervised feature extraction. As an example, we applied this strategy to Alzheimer’s disease (AD)-related gene expression profiles that lack exact correspondence among samples as well as AD single-cell RNA-seq (scRNA-seq) data. We found that we could select biologically reasonable genes with integrated analysis. Overall, integrated gene expression profiles can function analogously to prior learning and/or transfer learning strategies in other machine learning applications. For scRNA-seq, the proposed approach was able to drastically reduce the required computational memory.

scholarly journals Universal nature of drug treatment responses in drug-tissue-wide model-animal experiments using tensor decomposition-based unsupervised feature extraction

2020 ◽  
Author(s):  
Y-h. Taguchi ◽  
Turki Turki
Keyword(s):  
Gene Expression ◽  
Feature Extraction ◽  
Drug Treatment ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Tensor Decomposition ◽  
Integrated Analysis ◽  
Model Animal ◽  
Multiple Drugs ◽  
Unsupervised Feature Extraction

ABSTRACTGene expression profiles of tissues treated with drugs have recently been used to infer clinical outcomes. Although this method is often successful from the application point of view, gene expression altered by drugs is rarely analyzed in detail, because of the extremely large number of genes involved. Here, we applied tensor decomposition (TD)-based unsupervised feature extraction (FE) to the gene expression profiles of 24 mouse tissues treated with 15 drugs. TD-based unsupervised FE enabled identification of the common effects of 15 drugs including an interesting universal feature: these drugs affect genes in a gene-group-wide manner and were dependent on three tissue types (neuronal, muscular, and gastroenterological). For each tissue group, TD-based unsupervised FE enabled identification of a few tens to a few hundreds of genes affected by the drug treatment. These genes are distinctly expressed between drug treatments and controls as well as between tissues in individual tissue groups and other tissues. We also validated the assignment of genes to individual tissue groups using multiple enrichment analyses. We conclude that TD-based unsupervised FE is a promising method for integrated analysis of gene expression profiles from multiple tissues treated with multiple drugs in a completely unsupervised manner.

scholarly journals Integrative machine learning analysis of multiple gene expression profiles in cervical cancer

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5285 ◽  
Author(s):  
Mei Sze Tan ◽  
Siow-Wee Chang ◽  
Phaik Leng Cheah ◽  
Hwa Jen Yap
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Cervical Cancer ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Hpv Infection ◽  
Gene Set Enrichment Analysis ◽  
Multiple Gene ◽  
Cervical Cancers ◽  
Learning Analysis

Although most of the cervical cancer cases are reported to be closely related to the Human Papillomavirus (HPV) infection, there is a need to study genes that stand up differentially in the final actualization of cervical cancers following HPV infection. In this study, we proposed an integrative machine learning approach to analyse multiple gene expression profiles in cervical cancer in order to identify a set of genetic markers that are associated with and may eventually aid in the diagnosis or prognosis of cervical cancers. The proposed integrative analysis is composed of three steps: namely, (i) gene expression analysis of individual dataset; (ii) meta-analysis of multiple datasets; and (iii) feature selection and machine learning analysis. As a result, 21 gene expressions were identified through the integrative machine learning analysis which including seven supervised and one unsupervised methods. A functional analysis with GSEA (Gene Set Enrichment Analysis) was performed on the selected 21-gene expression set and showed significant enrichment in a nine-potential gene expression signature, namely PEG3, SPON1, BTD and RPLP2 (upregulated genes) and PRDX3, COPB2, LSM3, SLC5A3 and AS1B (downregulated genes).

scholarly journals Novel analysis of drug-drug interactions reveals the appearance of non-linear dose dependence under the single drug treatment

2020 ◽  
Author(s):  
Yh. Taguchi ◽  
Turki Turki
Keyword(s):  
Gene Expression ◽  
Drug Interactions ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Tensor Decomposition ◽  
Dose Dependence ◽  
Linear Dose ◽  
Non Linear ◽  
New Interactions ◽  
Dose Dependent

ABSTRACTThe accurate prediction of new interactions between drugs is important for avoiding unknown (mild or severe) adverse reactions to drug combinations. The development of effective in silico methods for evaluating drug interactions based on gene expression data requires an under-standing of how various drugs alter gene expression. Current computational methods for the prediction of drug-drug interactions (DDIs) utilize data for known DDIs to predict unknown interactions. However, these methods are limited in the absence of known predictive DDIs. To improve DDIs’ interpretation, a recent study has demonstrated strong non-linear (i.e., dose-dependent) effects of DDIs. In this study, we present a new unsupervised learning approach involving tensor decomposition (TD)-based unsupervised feature extraction (FE) in 3D. We utilize our approach to reanalyze available gene expression profiles for Saccharomyces cerevisiae. We found that non-linearity is possible, even for single drugs. Thus, non-linear dose-dependence cannot always be attributed to DDIs. Our analysis provides a basis for the design of effective methods for evaluating DDIs.

The characteristics of mesenteric adipose tissue attached to different intestinal segments and their roles in immune regulation

2022 ◽  
Author(s):  
Haowei Zhang ◽  
Yujin Ding ◽  
Qin Zeng ◽  
Dandan Wang ◽  
Ganglei Liu ◽  
...  
Keyword(s):  
Gene Expression ◽  
Adipose Tissue ◽  
Immune Regulation ◽  
Expression Profiles ◽  
Critical Role ◽  
Gene Expression Profiles ◽  
Rna Seq ◽  
Mesenteric Adipose Tissue ◽  
Cell Components ◽  
Subsequent Effect

Background: Mesenteric adipose tissue (MAT) plays a critical role in the intestinal physiological ecosystems. Small and large intestines have evidently intrinsic and distinct characteristics. However, whether there exist any mesenteric differences adjacent to the small and large intestines (SMAT and LMAT) has not been properly characterized. We studied the important facets of these differences, such as morphology, gene expression, cell components and immune regulation of MATs, to characterize the mesenteric differences. Methods: The SMAT and LMAT of mice were utilized for comparison of tissue morphology. Paired mesenteric samples were analyzed by RNA-seq to clarify gene expression profiles. MAT partial excision models were constructed to illustrate the immune regulation roles of MATs, and 16S-seq was applied to detect the subsequent effect on microbiota. Results: Our data show that different segments of mesenteries have different morphological structures. SMAT not only has smaller adipocytes but also contains more fat-associated lymphoid clusters than LMAT. The gene expression profile is also discrepant between these two MATs in mice. B-cell markers were abundantly expressed in SMAT, while development-related genes were highly expressed in LMAT. Adipose-derived stem cells of LMAT exhibited higher adipogenic potential and lower proliferation rates than those of SMAT. In addition, SMAT and LMAT play different roles in immune regulation and subsequently affect microbiota components. Finally, our data clarified the described differences between SMAT and LMAT in humans. Conclusions: There were significant differences in cell morphology, gene expression profiles, cell components, biological characteristics, and immune and microbiota regulation roles between regional MATs.

scholarly journals Comparative Transcriptome Analysis of Different Dendrobium Species Reveals Active Ingredients-Related Genes and Pathways

2020 ◽  
Vol 21 (3) ◽  
pp. 861 ◽  
Author(s):  
Yingdan Yuan ◽  
Bo Zhang ◽  
Xinggang Tang ◽  
Jinchi Zhang ◽  
Jie Lin
Keyword(s):  
Gene Expression ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Rna Seq ◽  
Active Ingredients ◽  
Hub Genes ◽  
Transcriptome Database ◽  
Gene Modules ◽  
Functional Investigation ◽  
First Time

Dendrobium is widely used in traditional Chinese medicine, which contains many kinds of active ingredients. In recent years, many Dendrobium transcriptomes have been sequenced. Hence, weighted gene co-expression network analysis (WGCNA) was used with the gene expression profiles of active ingredients to identify the modules and genes that may associate with particular species and tissues. Three kinds of Dendrobium species and three tissues were sampled for RNA-seq to generate a high-quality, full-length transcriptome database. Based on significant changes in gene expression, we constructed co-expression networks and revealed 19 gene modules. Among them, four modules with properties correlating to active ingredients regulation and biosynthesis, and several hub genes were selected for further functional investigation. This is the first time the WGCNA method has been used to analyze Dendrobium transcriptome data. Further excavation of the gene module information will help us to further study the role and significance of key genes, key signaling pathways, and regulatory mechanisms between genes on the occurrence and development of medicinal components of Dendrobium.

Sign in / Sign up

Export Citation Format

Share Document