A novel feature selection for RNA-seq analysis

B cell-derived IL-10 promotes the resolution of lipopolysaccharide-induced acute lung injury

Inflammation resolution is critical for acute lung injury (ALI) recovery. Interleukin (IL)-10 is a potent anti-inflammatory factor. However, its role in ALI resolution remains unclear. We investigated the effects of IL-10 during the ALI resolution process in a murine lipopolysaccharide (LPS)-induced ALI model. Blockade of IL-10 signaling aggravates LPS-induced lung injury, as manifested by elevated pro-inflammatory factors production and increased neutrophils recruitment to the lung. Thereafter, we used IL-10 GFP reporter mice to discern the source cell of IL-10 during ALI. We found that IL-10 is predominantly generated by B cells during the ALI recovery process. Furthermore, we used IL-10-specific loss in B-cell mice to elucidate the effect of B-cell-derived IL-10 on the ALI resolution process. IL-10-specific loss in B cells leads to increased pro-inflammatory cytokine expression, persistent leukocyte infiltration, and prolonged alveolar barrier damage. Mechanistically, B cell-derived IL-10 inhibits the activation and recruitment of macrophages and downregulates the production of chemokine KC that recruits neutrophils to the lung. Moreover, we found that IL-10 deletion in B cells leads to alterations in the cGMP-PKG signaling pathway. In addition, an exogenous supply of IL-10 promotes recovery from LPS-induced ALI, and IL-10-secreting B cells are present in sepsis-related ARDS. This study highlights that B cell-derived IL-10 is critical for the resolution of LPS-induced ALI and may serve as a potential therapeutic target.

A Computational Approach to Identification of Candidate Biomarkers in High-Dimensional Molecular Data

Complex high-dimensional datasets that are challenging to analyze are frequently produced through ‘-omics’ profiling. Typically, these datasets contain more genomic features than samples, limiting the use of multivariable statistical and machine learning-based approaches to analysis. Therefore, effective alternative approaches are urgently needed to identify features-of-interest in ‘-omics’ data. In this study, we present the molecular feature selection tool, a novel, ensemble-based, feature selection application for identifying candidate biomarkers in ‘-omics’ data. As proof-of-principle, we applied the molecular feature selection tool to identify a small set of immune-related genes as potential biomarkers of three prostate adenocarcinoma subtypes. Furthermore, we tested the selected genes in a model to classify the three subtypes and compared the results to models built using all genes and all differentially expressed genes. Genes identified with the molecular feature selection tool performed better than the other models in this study in all comparison metrics: accuracy, precision, recall, and F1-score using a significantly smaller set of genes. In addition, we developed a simple graphical user interface for the molecular feature selection tool, which is available for free download. This user-friendly interface is a valuable tool for the identification of potential biomarkers in gene expression datasets and is an asset for biomarker discovery studies.

AutoDC: an Automatic Machine Learning Framework for Disease Classification

MOTIVATION

The emergence of next-generation sequencing techniques opens up tremendous opportunities for researchers to uncover the basic mechanisms of disease at the molecular level. Recently, automatic machine learning (AutoML) frameworks have been employed for genomic and epigenomic data analysis. However, to analyze those high-dimensional data, existing AutoML frameworks suffer from the following issues: 1) they could not effectively filter out the redundant features from the original data, and 2) they usually obey the rule of feature engineering first and algorithm hyper-parameter tuning later to build the machine learning pipeline, which could lead to sub-optimal outcomes. Thus, it is an urgent need to design a new AutoML framework for high-dimensional omics data analysis.

RESULTS

We introduce a new method: AutoDC, a tailored automatic machine learning framework, for different disease classification based on gene expression data. AutoDC designs two novel optimization strategies to improve the performance. One is that AutoDC designs a novel two-stage feature selection method to select the features with high gene contribution scores. The other is that AutoDC proposes a novel optimization method, based on a two-layer Multi-Armed Bandit framework, to jointly optimize the feature engineering, algorithm selection, and algorithm hyper-parameter tuning. We apply our framework to two public gene expression datasets. Compared with three state-of-the-art AutoML frameworks, AutoDC could effectively classify diseases with higher predictive accuracy.

AVAILABILITY

The data and codes of AutoDC are available at https://github.com/dingdian110/AutoDC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

ScGSLC: An unsupervised graph similarity learning framework for single-cell RNA-seq data clustering

Accurate clustering of cells from single-cell RNA sequencing (scRNA-seq) data is an essential step for biological analysis such as putative cell type identification. However, scRNA-seq data has high dimension and high sparsity, which makes traditional clustering methods less effective to reflect the similarity between cells. Since genetic network fundamentally defines the functions of cell and deep learning shows strong advantages in network representation learning, we propose a novel scRNA-seq clustering framework ScGSLC based on graph similarity learning. ScGSLC effectively integrates scRNA-seq data and protein-protein interaction network to a graph. Then graph convolution network is employed by ScGSLC to embedding graph and clustering the cells by the calculated similarity between graphs. Unsupervised clustering results of nine public data sets demonstrate that ScGSLC shows better performance than the state-of-the-art methods.

Identification of MMP1 and MMP2 by RNA-seq analysis in laryngeal squamous cell carcinoma

BACKGROUND

Laryngeal squamous cell carcinoma (LSCC) is the most common histologic subtype of laryngeal cancer characterized by a poor prognosis. Determining gene expression changes in LSCC should improve our understanding of putative risk factors and provide potential targets for therapy.

OBJECTIVES

To assess differential gene expression between LSCC tissue and paired normal laryngeal tissue, and to provide gene targets for future studies of this type of laryngeal cancer.

MATERIALS AND METHODS

Three paired-sample groups (tumor and normal tissue) from patients with laryngeal squamous cell carcinoma were analyzed by RNA sequencing (RNA-seq).

RESULTS

The six cDNA libraries generated raw reads ranging from 15,195,586 to 21,443,488 counts. Changes in gene expression levels were determined in 40,205 of these counts, with 18,466 deferentially expressed genes in all three groups. Compared to normal tissue, the expression levels of MMP1 and MMP2 increased significantly in tumor tissue of patients with laryngeal squamous cell carcinoma.

CONCLUSIONS

Whole transcriptome sequencing revealed that MMP1 and MMP2 are highly expressed in LSCC. These genes may be useful both as biomarkers for LSCC diagnosis and as targets for therapy, as well as for increasing our understanding of LSCC tumorigenesis.

Characterization and expression analysis of immune-related genes in the red swamp crayfish, Procambarus clarkii in response to lipopolysaccharide challenge

To learn more about red swamp crayfish related genes in response to bacterial infections, we investigated immune-related genes induced by lipopolysaccharide (LPS) in the hepatopancreas using high-throughput sequencing method. In present the study, a total of 55,107 unigenes were identified, with an average length of 678 bp. A total of 2215 differentially expressed genes (DEGs) were found, including 669 up-regulated genes and 1546 down-regulated genes. The result of Gene ontology (GO) analysis revealed that 3017 DEGs were enriched in 19 biological process subcategories, 17 cellular component subcategories and 15 molecular function subcategories. The top 20 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways showed that "ribosome" was the most abundant group, which had 34 DEGs. KEGG enrichment analysis identified several immune response pathways. Real-time quantitative reverse transcription-PCR (qRT-PCR) results exhibited that several immune responsive genes were greatly up-regulated following LPS stimulation as observed in the results of high-throughput sequencing. Overall, this study provides new insight into the immune defense mechanisms of P. clarkii against LPS infection.

How does normalization impact RNA-seq disease diagnosis?

With the surge of next generation high-throughput technologies, RNA-seq data is playing an increasingly important role in disease diagnosis, in which normalization is assumed as an essential procedure to produce comparable samples. Recent studies have seen different normalization methods proposed to remove various technical biases in RNA sequencing. However, there are no previous studies evaluating the impacts of normalization on RNA-seq disease diagnosis. In this study, we investigate this problem by analyzing structured big data: RNA-seq data acquired from the TCGA portal for its popularity in RNA-seq disease diagnosis. We propose a novel normalization effect test algorithm, diagnostic index (d-index), and data entropy to analyze and evaluate the impacts of normalization on RNA-seq disease diagnosis by using state-of-the-art machine learning models. Furthermore, we present an original visualization analysis to compare the performance of normalized data versus raw data. We have found that normalized data yields generally an equivalent or even lower level diagnosis than its raw data. Moreover, some normalization approaches (e.g. RPKM) even bring negative effects in disease diagnosis. On the other hand, raw data seems to have the potential to decipher pathological status better or at least comparable than when the data is normalized. Our visualization analysis also shows that some normalization methods even bring 'outliers', which unavoidably decreases sample detectability in diagnosis. More importantly, our data entropy analysis shows that normalized data usually demonstrates equivalent or lower entropy values than raw data. Those data with high entropy values tend to achieve better diagnosis than those with low entropy values. In addition, we found that high-dimensional imbalance (HDI) data is unaffected by any normalization procedures in diagnosis, and fails almost all machine learning models by only recognizing majority types in spite of raw or normalized data. Our results suggest that normalized data may not demonstrate statistically significant advantages in disease diagnosis than its raw form. It further implies that normalization may not be an indispensable procedure in RNA-seq disease diagnosis or at least some normalization processes may not be. Instead, raw data may perform better for capturing more original transcriptome patterns in different pathological conditions.