Tensor-Decomposition-Based Unsupervised Feature Extraction Applied to Prostate Cancer Multiomics Data

Abstract

The large p small n problem is a challenge without a de facto standard method available to it. In this study, we propose a tensor-decomposition (TD)-based unsupervised feature extraction (FE) formalism applied to multiomics datasets, in which the number of features is more than 100,000 whereas the number of samples is as small as about 100, hence constituting a typical large p small n problem. The proposed TD-based unsupervised FE outperformed other conventional supervised feature selection methods, random forest, categorical regression (also known as analysis of variance, or ANOVA), penalized linear discriminant analysis, and two unsupervised methods, multiple non-negative matrix factorization and principal component analysis (PCA) based unsupervised FE when applied to synthetic datasets and four methods other than PCA based unsupervised FE when applied to multiomics datasets. The genes selected by TD-based unsupervised FE were enriched in genes known to be related to tissues and transcription factors measured. TD-based unsupervised FE was demonstrated to be not only the superior feature selection method but also the method that can select biologically reliable genes. To our knowledge, this is the first study in which TD-based unsupervised FE has been successfully applied to the integration of this variety of multiomics measurements.

Unsupervised tensor decomposition-based method to extract candidate transcription factors as histone modification bookmarks in post-mitotic transcriptional reactivation

“…• We have successfully used the region length [49,50]. When started to employ this procedure, we tried multiple values and identified that it is most successful.…”

Tensor decompositions in cancer study; A comprehensive review

“…Tensor decompositions provide a natural framework for integrating heterogeneous omics data types. By decomposing the multi-omics tensor, tensor decomposition techniques can reveal shared and specific patterns across different data sources, enabling the identification of cross-modal relationships and uncovering novel insights [20].…”

“…The article, [20] proposes a novel approach for predicting the progression of Alzheimer's disease using MRI (Magnetic Resonance Imaging) data. The method leverages tensor multi-task learning, which is a machine learning technique that jointly learns multiple related tasks to improve performance.The authors focus on capturing both spatial and temporal characteristics of the MRI data.…”

“…This is usually accomplished by minimizing the sum of squared deviations between the original tensor and its estimated approximation [22]. According to reference [20], the figure 3 shows that the PARAFAC decomposition process reveals that the morphological changing patterns among biomarkers, which indicate similarity, can be represented as multiple rank-one tensors [16]. Each rank-one tensor is obtained by taking the outer product of three latent components.…”

“…Tucker decomposition, also known as higher-order singular value decomposition (HOSVD), is a tensor factorization method that aims to decompose a tensor into a core tensor and factor matrices along each mode. It is an extension of the matrix singular value decomposition (SVD) to higher-dimensional data [20]. Due to its versatility and the manner in which it treats the PARAFAC model as a specific case, the Tucker model is commonly employed for decomposition, compression, and interpretation in various applications.…”