What is it about?
This volume explains principal component analysis/tensor decomposition based unsupervised feature extraction that I have proposed at 2012 and 2017, respectively. You can learn the mathematical background and various applications. The method focuses so-called feature selection/extracttion.
Featured Image
Photo by davide ragusa on Unsplash
Why is it important?
It can process small samples with many variables without preparing cutting edge CPU/GPU. Although it sometimes requires large memory it can also provide the implementations that reduce required memories. Basic features can be performed by two Bioconductor packages. The topics applicable are biomarker identification, drug repositioning and identification of disease causing genes. The data sets targeted are gene expression profiles, multiomics profiles (DNA methylation, histone modification, ATAC-seq and so on), protein-protein interaction and Hi-C data sets. It is also applicable to single cell analysis.
Perspectives
This is a really memorized experience in my life; I have published 500 pages hard cover monograph that mainly discusses my own methodology. I am happy if readers can learn and use my methods for their researches.
Professor Y-h. Taguchi
Chuo Daigaku
Read the Original
This page is a summary of: Unsupervised Feature Extraction Applied to Bioinformatics, January 2024, Springer Science + Business Media,
DOI: 10.1007/978-3-031-60982-4.
You can read the full text:
Resources
TDbasedUFE : Tensor Decomposition Based Unsupervised Feature Extraction
This is a comprehensive package to perform Tensor decomposition based unsupervised feature extraction. It can perform unsupervised feature extraction. It uses tensor decomposition. It is applicable to gene expression, DNA methylation, and histone modification etc. It can perform multiomics analysis. It is also potentially applicable to single cell omics data sets.
TDbasedUFEadv : Advanced package of tensor decomposition based unsupervised feature extraction
This is an advanced version of TDbasedUFE, which is a comprehensive package to perform Tensor decomposition based unsupervised feature extraction. In contrast to TDbasedUFE which can perform simple the feature selection and the multiomics analyses, this package can perform more complicated and advanced features, but they are not so popularly required. Only users who require more specific features can make use of its functionality.
Introduction generated by NotebookLM
NotebookLM generates audio introduction of my book.
Contributors
The following have contributed to this page
