Unsupervised Learning Framework With Multidimensional Scaling in Predicting Epithelial-Mesenchymal Transitions

SSNMDI: a novel joint learning model of semi-supervised non-negative matrix factorization and data imputation for clustering of single-cell RNA-seq data

MOTIVATION

Single-cell RNA sequencing (scRNA-seq) technology attracts extensive attention in the biomedical field. It can be used to measure gene expression and analyze the transcriptome at the single-cell level, enabling the identification of cell types based on unsupervised clustering. Data imputation and dimension reduction are conducted before clustering because scRNA-seq has a high 'dropout' rate, noise and linear inseparability. However, independence of dimension reduction, imputation and clustering cannot fully characterize the pattern of the scRNA-seq data, resulting in poor clustering performance. Herein, we propose a novel and accurate algorithm, SSNMDI, that utilizes a joint learning approach to simultaneously perform imputation, dimensionality reduction and cell clustering in a non-negative matrix factorization (NMF) framework. In addition, we integrate the cell annotation as prior information, then transform the joint learning into a semi-supervised NMF model. Through experiments on 14 datasets, we demonstrate that SSNMDI has a faster convergence speed, better dimensionality reduction performance and a more accurate cell clustering performance than previous methods, providing an accurate and robust strategy for analyzing scRNA-seq data. Biological analysis are also conducted to validate the biological significance of our method, including pseudotime analysis, gene ontology and survival analysis. We believe that we are among the first to introduce imputation, partial label information, dimension reduction and clustering to the single-cell field.

AVAILABILITY AND IMPLEMENTATION

The source code for SSNMDI is available at https://github.com/yushanqiu/SSNMDI.

Statistical Analysis of Microarray Data Clustering using NMF, Spectral Clustering, Kmeans, and GMM

In unsupervised learning literature, the study of clustering using microarray gene expression datasets has been extensively conducted with nonnegative matrix factorization (NMF), spectral clustering, kmeans, and gaussian mixture model (GMM)are some of the most used methods. However, there is still a limited number of works that utilize statistical analysis to measure the significances of performance differences between these methods. In this paper, statistical analysis of performance differences between ten NMF, six spectral clustering, four GMM, and the standard kmeans algorithms in clustering eleven publicly available microarray gene expression datasets with the number of clusters ranges from two to ten is presented. The experimental results show that statistically NMFs and kmeans have similar performances and outperform spectral clustering. As spectral clustering can be used to uncover hidden manifold structures, the underperformance of spectral methods leads us to question whether the datasets have manifold structures. Visual inspection using multidimensional scaling plots indicates that such structures do not exist. Moreover, as the plots indicate that clusters in some datasets have elliptical boundaries, GMM methods are also utilized. The experimental results show that GMM methods outperform the other methods to some degree, and thus imply that the datasets follow gaussian distributions.

Deep Learning-Based Classification of Epithelial-Mesenchymal Transition for Predicting Response to Therapy in Clear Cell Renal Cell Carcinoma

Epithelial-mesenchymal transition (EMT) profoundly impacts prognosis and immunotherapy of clear cell renal cell carcinoma (ccRCC). However, not every patient is tested for EMT status because this requires additional genetic studies. In this study, we developed an EMT gene signature to classify the H&E-stained slides from The Cancer Genome Atlas (TCGA) into epithelial and mesenchymal subtypes, then we trained a deep convolutional neural network to classify ccRCC which according to our EMT subtypes accurately and automatically and to further predict genomic data and prognosis. The clinical significance and multiomics analysis of the EMT signature was investigated. Patient cohorts from TCGA (n = 252) and whole slide images were used for training, testing, and validation using an algorithm to predict the EMT subtype. Our approach can robustly distinguish features predictive of the EMT subtype in H&E slides. Visualization techniques also detected EMT-associated histopathological features. Moreover, EMT subtypes were characterized by distinctive genomes, metabolic states, and immune components. Deep learning convolutional neural networks could be an extremely useful tool for predicting the EMT molecular classification of ccRCC tissue. The underlying multiomics information can be crucial in applying the appropriate and tailored targeted therapy to the patient.

An Adaptive Unsupervised Feature Selection Algorithm Based on MDS for Tumor Gene Data Classification

Identifying the key genes related to tumors from gene expression data with a large number of features is important for the accurate classification of tumors and to make special treatment decisions. In recent years, unsupervised feature selection algorithms have attracted considerable attention in the field of gene selection as they can find the most discriminating subsets of genes, namely the potential information in biological data. Recent research also shows that maintaining the important structure of data is necessary for gene selection. However, most current feature selection methods merely capture the local structure of the original data while ignoring the importance of the global structure of the original data. We believe that the global structure and local structure of the original data are equally important, and so the selected genes should maintain the essential structure of the original data as far as possible. In this paper, we propose a new, adaptive, unsupervised feature selection scheme which not only reconstructs high-dimensional data into a low-dimensional space with the constraint of feature distance invariance but also employs ℓ2,1-norm to enable a matrix with the ability to perform gene selection embedding into the local manifold structure-learning framework. Moreover, an effective algorithm is developed to solve the optimization problem based on the proposed scheme. Comparative experiments with some classical schemes on real tumor datasets demonstrate the effectiveness of the proposed method.