Single-cell RNA-seq data clustering by deep information fusion.

Recent advancements in single-cell RNA sequencing (scRNA-seq) technologies have allowed us to monitor the gene expression of individual cells. This level of detail in monitoring and characterization enables the research of cells in rapidly changing and heterogeneous environments such as early stage embryo or tumor tissue. However, the current scRNA-seq technologies are still facing many outstanding challenges. Due to the low amount of starting material, a large portion of expression values in scRNA-seq data is missing and reported as zeros. Moreover, scRNA-seq platforms are trending toward prioritizing high throughput over sequencing depth, which makes the problem become more serious in large datasets. These missing values can greatly affect the accuracy of downstream analyses. Here we introduce scINN, a neural network-based approach, that can reliably recover the missing values in single-cell data and thus can effectively improve the performance of downstream analyses. To impute the dropouts in single-cell data, we build a neural network that consists of two sub-networks: imputation sub-network and quality assessment sub-network. We compare scINN with state-of-the-art imputation methods using 10 scRNA-seq datasets with a total of more than 100,000 cells. In an extensive analysis, we demonstrate that scINN outperforms existing imputation methods in improving the identification of cell sub-populations and the Quality of transcriptome landscape visualization.

Rationale: As sequencing methodologies continue to improve, and new methods such as spatial transcriptomics technologies rapidly emerge, we must develop and streamline methods to effectively and efficiently communicate these vast quantities of data. The process of using an atlas data mining website to showcase single cell and single nucleus transcriptomics data has been successfully applied in research. Our IPF cell atlas (https://www.ipfcellatlas.com) and more recently ILD immune cell atlas (https://ildimmunecellatlas.com) had over 16,000 users since 2020 and combined 1,650 unique users over the last 12 months. We have developed a seven-step pipeline that allows our fellow researchers to showcase their own single cell data in interactive and comprehensive websites. Methods: Our pipeline uses the R programming language and the shiny package to create a website hosted on shinyapps.io, while storing the data is on a MySQL database hosted on Amazon Web Services (AWS). The resulting website will be able to collect user engagement statistics as well as queries regarding the data explored by the user. This is done via Google Analytics in combination with logging tables stored on the MySQL database. The website has interactive functions that generate plots in real time using R to create gene expression, violin and box plots among others of data extracted from the database. The output plots are presented to the user to explore. Results: We developed a seven-step blueprint which can be implemented by researchers with little to no coding experience. Our pipeline generates a fully functional website that allows users to explore (transcriptomics) data with an intuitive, customizable, user-friendly interface. Data is presented in a multitude of ways: individual gene exploration, differential gene expression by gene type, transcriptomic signatures, cell type, gene ontology. Conclusions: We have developed for the first time an easy-to-use pipeline as a tool to aid researchers in creating a platform to share and showcase their work which works within existing software pipelines.

Background and aimsAlcoholic hepatitis (AH) and hepatocellular carcinoma (HCC) are common liver diseases. Chronic inflammation caused by AH can progress to alcoholic cirrhosis (AC) and eventually HCC.MethodsThis study sought to ascertain potential shared genes between AH and HCC through the utilization of multiple transcriptome databases. Employing an immune infiltration analysis, and calculating the correlation between shared genes and immune infiltration results, in conjunction with independent bulk transcriptome validation sets, led to the identification of core shared genes. Subsequently, single-cell transcriptome data, clinical sample immunohistochemistry experiments, and overexpressed core shared genes in HepG2 cells were employed to validate the core shared genes of AH and HCC.ResultsThrough the bulk transcriptome discovery sets of AH and HCC, 206 potential shared genes were identified. After screening with two machine learning algorithms, five shared genes remained. Combining the results of the immune infiltration and bulk transcriptome results from an independent validation cohort, the core shared gene was determined to be RASGRF2. Single-cell data further demonstrated that RASGRF2 and its downstream genes were highly expressed in AH, AC, and HCC tissues. Spatial transcriptome data indicated that RASGRF2 was highly expressed in HCC tumor tissues. Compared with the paracancerous tissues, the RASGRF2 gene was significantly overexpressed in HCC tissues. Overexpression of RASGRF2 in HepG2 cells resulted in significantly enhanced migration, invasion, and proliferation abilities.ConclusionRASGRF2 serve as a pathogenic gene that mediates the progression of AH to AC and potentially to HCC.

The advancements of single-cell sequencing methods have paved the way for the characterization of cellular states at unprecedented resolution, revolutionizing the investigation on complex biological systems. Yet, single-cell sequencing experiments are hindered by several technical issues, which cause output data to be noisy, impacting the reliability of downstream analyses. Therefore, a growing number of data science methods has been proposed to recover lost or corrupted information from single-cell sequencing data. To date, however, no quantitative benchmarks have been proposed to evaluate such methods. We present a comprehensive analysis of the state-of-the-art computational approaches for denoising and imputation of single-cell transcriptomic data, comparing their performance in different experimental scenarios. In detail, we compared 19 denoising and imputation methods, on both simulated and real-world datasets, with respect to several performance metrics related to imputation of dropout events, recovery of true expression profiles, characterization of cell similarity, identification of differentially expressed genes and computation time. The effectiveness and scalability of all methods were assessed with regard to distinct sequencing protocols, sample size and different levels of biological variability and technical noise. As a result, we identify a subset of versatile approaches exhibiting solid performances on most tests and show that certain algorithmic families prove effective on specific tasks but inefficient on others. Finally, most methods appear to benefit from the introduction of appropriate assumptions on noise distribution of biological processes.

Non-small cell lung cancer (NSCLC), including lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), exhibits marked tumor heterogeneity and poor prognosis. Metabolic reprogramming is a hallmark of cancer, and long non-coding RNAs (lncRNAs) have emerged as important regulators of tumor metabolism and immune interactions. This study aimed to systematically characterize metabolism-related lncRNAs in NSCLC using single-cell and bulk transcriptomic data, and to evaluate their associations with tumor heterogeneity, immune microenvironment, and clinical outcomes. RNA sequencing and clinical data for LUAD and LUSC were obtained from The Cancer Genome Atlas. Metabolism-related lncRNAs were identified through partial correlation analysis combined with KEGG pathway-based gene set enrichment analysis. Tumor microenvironment characteristics were assessed using CIBERSORTx. Consensus clustering based on the top 20 metabolism-related lncRNAs was applied to define molecular subtypes. Cis- and trans-regulatory relationships were explored using Spearman correlation, and competing endogenous RNA networks were constructed by integrating TargetScan-predicted miRNA-mRNA interactions. Findings were validated across six independent datasets, and single-cell transcriptomic data were used to assess cell-type-specific expression patterns. A subset of metabolism-related lncRNAs was significantly enriched among differentially expressed and survival-associated lncRNAs in NSCLC. AL365181.2 was identified as a key lncRNA associated with multiple metabolic pathways and poor prognosis. Single-cell analysis revealed immune cell-specific expression patterns, particularly in B cells, CD8+ T cells, and natural killer cells. Metabolic lncRNA-based clustering defined distinct molecular subtypes with significant differences in immune profiles and clinical outcomes. Metabolism-related lncRNAs contribute substantially to tumor heterogeneity and prognosis in NSCLC and may serve as valuable biomarkers for patient stratification and personalized therapeutic strategies.

The article describes a new missing data imputation method. It is based on the use of a high-speed neural-like structure of the Successive Geometric Transformations Model. The importance of the research is based on the analysis of disadvantages of the known methods for missing data processing. Various simple and complex algorithms are analyzed, among which are the arithmetic mean algorithm, regression modeling, etc. It is shown that the above-mentioned imputation methods in data monitoring of air pollution do not allow to obtain reliable results due to the low prediction accuracy. An effective method for processing data imputation through SGTM neural-like structure is proposed. An example of filling data by forecasting CO, NO and NO2 missed parameters in data monitoring of air pollution is given. A comparison of the proposed method with the arithmetic mean algorithm is carried out. Accuracies of the data imputation by developed method and by arithmetic mean algorithm are based on calculated evaluation criteria: Root mean squared errors. Experimentally established that the data imputation method through SGTM neural-like structure has a three times higher accuracy of the data imputation than the arithmetic mean algorithm. The proposed approach can be used in various areas such as medicine, materials science, economics, science services, etc.

Cell clustering is foundational for analyzing the heterogeneity of biological tissues using single-cell sequencing data. With the maturation of single-cell multi-omics sequencing technologies, we can integrate multiple omics data to perform cell clustering, thereby overcoming the limitations of insufficient information from single omics data. Existing methods for cell clustering often only consider the differences in data patterns during the analysis of multi-omics data, but the dependencies between omics features of different cell types also significantly influence cell clustering. Moreover, the high dropout rates in scRNA-seq and scATAC-seq data can impact the performance of cell clustering. We propose a cell clustering model based on a masked autoencoder, scDRMAE. Utilizing a masking mechanism, scDRMAE effectively learns the relationships between different features and imputes false zeros caused by dropout events. To differentiate the importance of various omics data in cell clustering, we dynamically adjust the weights of different omics data through an attention mechanism. Finally, we use the K-means algorithm for cluster analysis of the fused multi-omics data. On commonly used sets of 15 multi-omics datasets, our method demonstrates superior cell clustering performance on multiple metrics compared to other computational methods. In addition, when datasets exhibit varying degrees of dropout noise, our method shows better performance and stronger stability on multiple metrics compared to other methods. Moreover, by analyzing the cell clusters classified by scDRMAE, we identified several biologically significant biomarkers that have been validated, further confirming the effectiveness of scDRMAE in cell clustering from a biological perspective.

Annotation of cells in single-cell clustering requires a homogeneous grouping of cell populations. There are various issues in single cell sequencing that effect homogeneous grouping (clustering) of cells, such as small amount of starting RNA, limited per-cell sequenced reads, cell-to-cell variability due to cell-cycle, cellular morphology, and variable reagent concentrations. Moreover, single cell data is susceptible to technical noise, which affects the quality of genes (or features) selected/extracted prior to clustering. Here we introduce sc-CGconv (copula based graph convolution network for single clustering), a stepwise robust unsupervised feature extraction and clustering approach that formulates and aggregates cell-cell relationships using copula correlation (Ccor), followed by a graph convolution network based clustering approach. sc-CGconv formulates a cell-cell graph using Ccor that is learned by a graph-based artificial intelligence model, graph convolution network. The learned representation (low dimensional embedding) is utilized for cell clustering. sc-CGconv features the following advantages. a. sc-CGconv works with substantially smaller sample sizes to identify homogeneous clusters. b. sc-CGconv can model the expression co-variability of a large number of genes, thereby outperforming state-of-the-art gene selection/extraction methods for clustering. c. sc-CGconv preserves the cell-to-cell variability within the selected gene set by constructing a cell-cell graph through copula correlation measure. d. sc-CGconv provides a topology-preserving embedding of cells in low dimensional space.

Single-cell RNA sequencing (scRNA-seq) has emerged as a transformative technology for elucidating cellular heterogeneity at unprecedented resolution. However, technical limitations such as limited sequencing depth and mRNA capture efficiency often result in zero counts, commonly referred to as "dropout zeros" in scRNA-seq data. These zeros pose significant challenges to downstream analysis, as they can distort the interpretation of cellular transcriptomes. While numerous computational methods have been developed to address this challenge, existing approaches frequently suffer from either insufficient imputation of zeros (under-imputation) or excessive modification of zeros (over-imputation). Here, we propose a precisely balanced imputation (PbImpute) method designed to achieve optimal equilibrium between dropout recovery and biological zero preservation in scRNA-seq data. PbImpute employs a multistage approach: (1) Initial discrimination between technical dropouts and biological zeros through parameter optimization of a new zero-inflated negative binomial (ZINB) distribution model, followed by initial imputation; (2) Application of a uniquely designed static repair algorithm to enhance data fidelity; (3) Secondary dropout identification based on gene expression frequency and partition-specific coefficient of variation; (4) Graph-embedding neural network-based imputation; and (5) Implementation of a uniquely designed dynamic repair mechanism to mitigate over-imputation effects. PbImpute distinguishes itself by uniquely integrating ZINB modeling with static and dynamic repair. This advantageous combined approach achieves a balance between over- and under-imputation, while simultaneously preserving true biological zeros and reducing signal distortion. Comprehensive evaluation using both simulated and real scRNA-seq data sets demonstrated that PbImpute achieves superior performance (F1 Score = 0.88 at 83% dropout rate, ARI = 0.78 on PBMC) in discriminating between technical dropouts and biological zeros compared to state-of-the-art methods. The method significantly improves gene-gene and cell-cell correlation structures, enhances differential expression analysis sensitivity, optimizes clustering resolution and dimensional reduction visualization, and facilitates more accurate trajectory inference. Ablation studies confirmed the essential contribution of both the imputation and repair modules to the method's performance. The code is available at https://github.com/WyBioTeam/PbImpute. By enhancing the accuracy of scRNA-seq data imputation, PbImpute can improve the identification of cell subpopulations and the detection of differentially expressed genes, thereby facilitating more precise analyses of cellular heterogeneity and advancing disease research.

High-resolution imaging has revolutionized the study of single cells in their spatial context. However, summarizing the great diversity of complex cell shapes found in tissues and inferring associations with other single-cell data remains a challenge. Here, we present CAJAL, a general computational framework for the analysis and integration of single-cell morphological data. By building upon metric geometry, CAJAL infers cell morphology latent spaces where distances between points indicate the amount of physical deformation required to change the morphology of one cell into that of another. We show that cell morphology spaces facilitate the integration of single-cell morphological data across technologies and the inference of relations with other data, such as single-cell transcriptomic data. We demonstrate the utility of CAJAL with several morphological datasets of neurons and glia and identify genes associated with neuronal plasticity in C. elegans. Our approach provides an effective strategy for integrating cell morphology data into single-cell omics analyses.

Many species on Earth can carry up to two different versions of a given gene, with each of these ‘alleles’ having only a 50/50 chance of being transmitted to the next generation via sexual reproduction. Certain ‘selfish’ sequences, however, can hijack this process and increase their probability of being passed on to an offspring. Known as transmission distortion, this phenomenon may result in alleles spreading through the population even if they are detrimental to fertility. Transmission distortion has been detected in many species such as flies, mice and some plants. It can take place at various stages during reproduction; for example, the selfish alleles may become overrepresented among eggs or sperm. However, scientists need to study a large number of offspring or reproductive cells to be able to detect whether an allele is inherited more often than expected. This has made it difficult to determine whether transmission distortion also happens in humans, and research so far has resulted in conflicting conclusions. A recently published dataset of human sperm from 25 donors offered Carioscia, Weaver et al. the opportunity to examine this question. Every volunteer had produced between 969 and 3377 sperm cells, each with about 1% of their genome sequenced. Carioscia, Weaver et al. developed a computational method, which they named rhapsodi, that allowed them to ‘fill in the gaps’ and infer missing regions of the genome for each cell. To do so, they relied on the fact that sperm cells from a given individual are highly related to one another. With this more complete data at hand, it became possible to look for evidence of transmission distortion by searching for alleles that were overrepresented in sperm from a given donor. No selfish sequence could be detected in any of the 25 individuals, suggesting that human sperm may not be subject to pervasive transmission distortion. Signatures of selfish alleles detected in previous human studies may have therefore not resulted from this mechanism taking place at the sperm level. Instead, transmission distortion in humans could primarily target eggs or happen at later stages (for instance, if embryos carrying the selfish allele have better chances of survival). The ‘rhapsodi’ method developed by Carioscia, Weaver et al. should allow other scientists to work with datasets for which large portions of the genetic information is missing. It may therefore become easier for researchers to track selfish alleles which are difficult to detect, and to examine bigger, more diverse samples which also include individuals with known fertility challenges.

Anomaly detection and fault analysis of wind turbine components based on deep learning network

In this paper, a data imputation method, which can achieve robust data collection and also extend network lifetime for Wireless Sensor Networks, is proposed. Due to the lossy nature of the wireless medium, it is common for packets to be lost. In order to provide some reliability for the application layer, a data imputation method which predicts the data values contained in missing packets is proposed. The method is able to maximize the use of both temporal and spatial predictors. The proposed imputation method improves accuracy by up to 73% when compared with a previously proposed imputation method. The method can also be used to reduce the number of retransmissions in the network by up to 12% at the cost of a small increase in error, thus increasing the network lifetime of the wireless sensor network.

The first step in single-cell RNAseq data analysis is the evaluation of the overall quality of the cell transcriptome and the preparation of the single-cell transcription data for clustering. In this chapter, we describe one of the possible approaches to perform single-cell data preprocessing for 3' end single-cell RNAseq transcriptomics data.

This study aims to understand the differences in cellular and molecular patterns between the Main and Accessory (Acc) regions of pterygium tissue, with a focus on inflammation and mitochondrial energy metabolism. We collected bulk RNA sequencing (RNA-seq) data from six pterygium patients and single-cell RNA-seq data from two pterygium patients. Subsequently, we investigated pathway enrichment, pathway correlation, differential gene expression, protein-protein interactions, and cell-cell communication in pterygium. Bulk RNA-seq analysis revealed distinct expression patterns in the Acc group compared to the Main and control groups. This finding suggested the need to separate the Main and Acc regions within pterygium samples and use single-cell data to understand differences between the Main and control groups that bulk data could not capture. The single-cell data identified a cluster of epithelial cells containing only pterygium samples, which contributed significantly to the ANGPTL, IL1, and KLK signaling networks. Cells involved in inflammatory pathways associated with the integrated stress response and the renin-angiotensin-aldosterone system, both of which exhibited high correlations with energy metabolism-associated pathways, were significantly upregulated. Additionally, expression changes in multiple proinflammatory, antioxidant, and immune-associated genes were identified. The distinctions between the Main and Acc groups suggest the necessity of distinguishing anatomical regions in future pterygium studies. Additionally, the pivotal role of epithelial cells from the Main group in the inflammation of pterygium indicates a potential clinical approach for managing the disease. This study aims to identify apex-specific biomarkers of pterygium for a more efficient diagnosis and treatment.