Robust Graph Regularized NMF with Dissimilarity and Similarity Constraints for ScRNA-seq Data Clustering

Shu, Zhenqiu; Long, Qinghan; Zhang, Luping; Yu, Zhengtao; Wu, Xiao-Jun

doi:10.1021/acs.jcim.2c01305

Cited by 11 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea behind the graph regularization is to incorporate prior knowledge into LMF learning-that similar categories of solutes exhibit similar miscibility behavior-by promoting vector representations of solutions of similar solutes to be near each other in the latent space. (GR-MF has been applied to single-cell RNA-seq clustering 48 and predicting drug-drug, drug-target, and metabolite-disease interactions ). We represent this information as a simple graph G = (V, E).…”

Section: Our Contributionmentioning

confidence: 99%

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Behnoudfar

Simon

Schrier

2023

Preprint

View full text Add to dashboard Cite

Aqueous, two-phase systems (ATPSs) may form upon mixing two solutions of independently water-soluble compounds. Many separation, purification, and extraction processes rely on ATPSs. Predicting the miscibility of solutions can accelerate and reduce the cost of the discovery of new ATPSs for these applications. Whereas previous machine learning approaches to ATPS prediction used physicochemical properties of each solute as a descriptor, in this work, we show how we can impute missing miscibility outcomes directly from an incomplete collection of pairwise miscibility experiments. We use graph-regularized logistic matrix factorization to learn a latent vector of each solution from (i) the observed entries in the pairwise miscibility matrix and (ii) a graph (nodes: solutes, edges: shared relationships) indicating the general category of the solute (i.e., polymer, surfactant, salt, protein). Using an experimental dataset of the pairwise miscibility of 68 solutions from Peacock et al. [ACS Appl. Mater. Interfaces 2021, 13, 9], we show that graph-regularized logistic matrix factorization more accurately predicts missing (im)miscibility outcomes of pairs of solutions than ordinary logistic matrix factorization and random forest classifiers using physicochemical features of the compounds.

show abstract

Section: Our Contributionmentioning

confidence: 99%

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Behnoudfar

Simon

Schrier

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…(GR-MF has been applied to single-cell RNA-seq clustering 49 and predicting drug-drug, drugtarget, and metabolite-disease interactions 48,[50][51][52][53] and side effects of drugs. 54 ) Starting from only (1) incomplete experimental observations of (im)miscibility of pairs of 68 solutions of distinct compounds from Peacock et al 20 (2) and the rough grouping of the compounds into the categories of polymer, protein, surfactant, or salt, we show that GR-LMF learns latent representations of the solutions that give ATPS predictions on missing entries outperforming (i) ordinary LMF and (ii) a standard supervised machine learning approach using a random forest classifiers taking as input physicochemical features of the compounds in the solutions.…”

Section: Our Contributionmentioning

confidence: 99%

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Behnoudfar,

Simon,

Schrier

2023

Preprint

View full text Add to dashboard Cite

Aqueous, two-phase systems (ATPSs) may form upon mixing two solutions of independently water-soluble compounds. Many separation, purification, and extraction processes rely on ATPSs. Predicting the miscibility of solutions can accelerate and reduce the cost of the discovery of new ATPSs for these applications. Whereas previous machine learning approaches to ATPS prediction used physicochemical properties of each solute as a descriptor, in this work, we show how to impute missing miscibility outcomes directly from an incomplete collection of pairwise miscibility experiments. We use graph-regularized logistic matrix factorization (GR-LMF) to learn a latent vector of each solution from (i) the observed entries in the pairwise miscibility matrix and (ii) a graph (nodes: solutes, edges: shared relationships) indicating the general category of the solute (i.e., polymer, surfactant, salt, protein). For an experimental dataset of the pairwise miscibility of 68 solutions from Peacock et al. [ACS Appl. Mater. Interfaces 2021, 13, 11449--11460], we find that GR-LMF more accurately predicts missing (im)miscibility outcomes of pairs of solutions than ordinary logistic matrix factorization and random forest classifiers that use physicochemical features of the solutes. GR-LMF obviates the need for features of the solutions/solutes to impute missing miscibility outcomes, but it cannot predict the miscibility of a new solution without some observations of its miscibility with other solutions in the training data set.

show abstract

“…One such method is ScRNA by non-negative and low-rank representation (SinLRR), which assumes that scRNA-seq has an inherently low rank and attempts to find the smallest rank matrix that captures the original data . Numerous non-negative matrix factorization (NMF) methods with different constraints have also been developed, where the low-dimensional representation of scRNA-seq is a linear combination of the original data and acts as meta-genes. − Single-cell interpretation via multikernel learning (SIMLR) utilizes multiple kernels to learn a cell–cell similarity metric that generalizes to different biological experiments and experimental procedures . In addition, more traditional approaches, such as principal component analysis (PCA) and its derivatives, , and visualization techniques, such as uniform manifold approximation and projection (UMAP) and t-distributed stochastic neighbor embedding (t-SNE), have been heavily utilized for scRNA-seq data.…”

Section: Introductionmentioning

confidence: 99%

Preprocessing of Single Cell RNA Sequencing Data Using Correlated Clustering and Projection

Hozumi

Tanemura

Wei

2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) is widely used to reveal heterogeneity in cells, which has given us insights into cell−cell communication, cell differentiation, and differential gene expression. However, analyzing scRNA-seq data is a challenge due to sparsity and the large number of genes involved. Therefore, dimensionality reduction and feature selection are important for removing spurious signals and enhancing the downstream analysis. We present Correlated Clustering and Projection (CCP), a new data-domain dimensionality reduction method, for the first time. CCP projects each cluster of similar genes into a supergene defined as the accumulated pairwise nonlinear gene−gene correlations among all cells. Using 14 benchmark data sets, we demonstrate that CCP has significant advantages over classical principal component analysis (PCA) for clustering and/or classification problems with intrinsically high dimensionality. In addition, we introduce the Residue-Similarity index (RSI) as a novel metric for clustering and classification and the R-S plot as a new visualization tool. We show that the RSI correlates with accuracy without requiring the knowledge of the true labels. The R-S plot provides a unique alternative to the uniform manifold approximation and projection (UMAP) and t-distributed stochastic neighbor embedding (t-SNE) for data with a large number of cell types.

show abstract

Robust Graph Regularized NMF with Dissimilarity and Similarity Constraints for ScRNA-seq Data Clustering

Cited by 11 publications

References 47 publications

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Data-driven imputation of miscibility of aqueous solutions via graph-regularized logistic matrix factorization

Preprocessing of Single Cell RNA Sequencing Data Using Correlated Clustering and Projection

Contact Info

Product

Resources

About