A spectral clustering with self-weighted multiple kernel learning method for single-cell RNA-seq data

Abstract

Single-cell RNA-sequencing (scRNA-seq) data widely exist in bioinformatics. It is crucial to devise a distance metric for scRNA-seq data. Almost all existing clustering methods based on spectral clustering algorithms work in three separate steps: similarity graph construction; continuous labels learning; discretization of the learned labels by k-means clustering. However, this common practice has potential flaws that may lead to severe information loss and degradation of performance. Furthermore, the performance of a kernel method is largely determined by the selected kernel; a self-weighted multiple kernel learning model can help choose the most suitable kernel for scRNA-seq data. To this end, we propose to automatically learn similarity information from data. We present a new clustering method in the form of a multiple kernel combination that can directly discover groupings in scRNA-seq data. The main proposition is that automatically learned similarity information from scRNA-seq data is used to transform the candidate solution into a new solution that better approximates the discrete one. The proposed model can be efficiently solved by the standard support vector machine (SVM) solvers. Experiments on benchmark scRNA-Seq data validate the superior performance of the proposed model. Spectral clustering with multiple kernels is implemented in Matlab, licensed under Massachusetts Institute of Technology (MIT) and freely available from the Github website, https://github.com/Cuteu/SMSC/.

A Novel Early-Stage Lung Adenocarcinoma Prognostic Model Based on Feature Selection With Orthogonal Regression

“…In conclusion, the proposed FSOR method can deliver better prediction performance for the early-stage prognosis and has the potential to improve therapy strategy, but with few predictor consideration and computation burden. The future work should focus on integrating multi-omics and multiscale profiling information (Tang et al, 2017), together with proposing novel analytical approaches (Liu et al, 2020;Qi et al, 2020), thus to optimize therapy targets and boost precision medicine.…”

Application of Sparse Representation in Bioinformatics

“…Typical linear feature extraction algorithms include sparse principal component analysis (PCA) ( Min et al, 2018 ; Islam et al, 2020 ), independent component analysis ( Moysés et al, 2017 ), and LDA. Nonlinear transformation methods primarily include neural networks, kernel methods ( Qi et al, 2021b ), manifold learning ( Shen et al, 2017 ), sparse representation ( Min et al, 2017 ), and matrix factorization methods ( Wang et al, 2017 ; Yang et al, 2017 ; Yang and Hu, 2017 ; McCall et al, 2019 ). With the continuous development of machine learning and data mining, new feature extraction methods continue to arise.…”

D3K: The Dissimilarity-Density-Dynamic Radius K-means Clustering Algorithm for scRNA-Seq Data

“…It is an interdisciplinary subject composed of life science and computer science, which can dig out the biological significance contained in the chaotic biological data (Sun et al, 2022). Transcriptome is an important research field in bioinformatics, which can study gene function and gene structure from an overall level, and reveal specific biological processes and molecular mechanisms in the process of disease occurrence (Qi et al, 2021;Tang et al, 2020). In order to study the transcriptome, it must be sequenced first, but traditional sequencing techniques ignore the critical differences of individual cells, which will mask the heterogeneous expression between cells and make it difficult to detect subtle potential changes (Huang et al, 2017;Liu et al, 2020).…”