Semi-Supervised Topological Analysis for Elucidating Hidden Structures in High-Dimensional Transcriptome Datasets

Feng, Tianshu; Davila, Jaime; Liu, Yuanhang; Lin, Sangdi; Huang, Shuai; Wang, Chen

doi:10.1109/tcbb.2019.2950657

Cited by 4 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, comprehending and interpreting the enormous number of genes has become a significant challenge ( Diniz et al, 2019 ; Maâtouk et al, 2019 ; Li and Yang, 2020 ; Summers et al, 2020 ; Nisar et al, 2021 ; Dang et al, 2022 ). Semi-supervised learning ( Chapelle et al, 2006 ) is a focused issue in the analysis of gene expression data, the research branches mainly include semi-supervised gene clustering ( Yu et al, 2014 ; Yu et al, 2016 ; Xia et al, 2018 ; Liu et al, 2021 ), semi-supervised gene classification ( Huang and Feng, 2012 ; Zhang et al, 2021 ), semi-supervised gene selection ( Mahendran et al, 2020 ), and semi-supervised gene dimensionality reduction ( Feng et al, 2021 ). In this paper, we focus on the semi-supervised gene clustering problem for identify co-expressed gene groups, which can provide a useful basis for the further investigation of gene function and gene regulation in the field of functional genomics ( Maâtouk et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

A self-training subspace clustering algorithm based on adaptive confidence for gene expression data

Liang

Pan

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

Gene clustering is one of the important techniques to identify co-expressed gene groups from gene expression data, which provides a powerful tool for investigating functional relationships of genes in biological process. Self-training is a kind of important semi-supervised learning method and has exhibited good performance on gene clustering problem. However, the self-training process inevitably suffers from mislabeling, the accumulation of which will lead to the degradation of semi-supervised learning performance of gene expression data. To solve the problem, this paper proposes a self-training subspace clustering algorithm based on adaptive confidence for gene expression data (SSCAC), which combines the low-rank representation of gene expression data and adaptive adjustment of label confidence to better guide the partition of unlabeled data. The superiority of the proposed SSCAC algorithm is mainly reflected in the following aspects. 1) In order to improve the discriminative property of gene expression data, the low-rank representation with distance penalty is used to mine the potential subspace structure of data. 2) Considering the problem of mislabeling in self-training, a semi-supervised clustering objective function with label confidence is proposed, and a self-training subspace clustering framework is constructed on this basis. 3) In order to mitigate the negative impact of mislabeled data, an adaptive adjustment strategy based on gravitational search algorithm is proposed for label confidence. Compared with a variety of state-of-the-art unsupervised and semi-supervised learning algorithms, the SSCAC algorithm has demonstrated its superiority through extensive experiments on two benchmark gene expression datasets.

show abstract