Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment

Wang, Xin; Wang, Hongjiu; Liú, Dan; Wang, Na; He, Danni; Wu, Zheyu; Xu, Zhu; Wen, Xiao-Ling; Li, Xuhua; Li, Jin; Wang, Zhenzhen

doi:10.1080/2162402x.2022.2043662

Cited by 5 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the datasets in this study, we evaluated their cell abundance profiles by used DCNet including 106 immune cells, 322 stromal cells, and 6 cancer cells [ 11 ]. To characterize the cell states associated with patients expressing endogenous IFN-λ, 14 cell states and their signature genes were obtained from the CancerSEA.…”

Section: Methodsmentioning

confidence: 99%

Portraying the dark side of endogenous IFN-λ for promoting cancer progression and immunoevasion in pan-cancer

Wang,

Wen,

Wang

et al. 2023

J Transl Med

Self Cite

View full text Add to dashboard Cite

Background IFN-λ has been shown to have a dual function in cancer, with its tumor-suppressive roles being well-established. However, the potential existence of a negative ‘‘tumor-promoting’’ effect of endogenous IFN-λ is still not fully understood. Methods We conducted a comprehensive review and analysis of the perturbation of IFN-λ genes across various cancer types. Correlation coefficients were utilized to examine the relationship between endogenous IFN-λ expression and clinical factors, immune cell infiltration, tumor microenvironment, and response to immunotherapy. Genes working together with IFN-λ were obtained by constructing the correlation-based network related to IFN-λ and the gene interaction network in the KEGG pathway and IFN-λ-related genes obtained from the networks were integrated as candidate markers for the prognosis model. We then applied univariate and multivariate COX regression models to select cancer-specific independent prognostic markers associated with IFN-λ and to investigate risk factors for these genes by survival analysis. Additionally, computational methods were used to analyze the transcriptome, copy number variations, genetic mutations, and methylation of IFN-λ-related patient groups. Result Endogenous expression of IFN-λ has been linked to poor prognosis in cancer patients, with the genes IFN-λ2 and IFN-λ3 serving as independent prognostic markers. IFN-λ acts in conjunction with related genes such as STAT1, STAT2, and STAT3 to affect the JAK-STAT signaling pathway, which promotes tumor progression. Abnormalities in IFN-λ genes are associated with changes in immune checkpoints and immune cell infiltration, which in turn affects cancer- and immune-related pathways. While there is increased immune cell infiltration in patients with IFN-λ expression, this does not improve survival prognosis, as T-cell dysfunction and an inflammatory environment are also present. The amplification of IFNL2 and IFNL3 copy number variants drives specific endogenous expression of IFN-λ in patients, and those with this specific expression have been found to have more mutations in the TP53 gene and lower levels of DNA methylation. Conclusion Our study integrated multi-omics data to provide a comprehensive insight into the dark side of endogenous IFN-λ, providing a fundamental resource for further discovery and therapeutic exploration in cancer.

show abstract

Section: Methodsmentioning

confidence: 99%

Portraying the dark side of endogenous IFN-λ for promoting cancer progression and immunoevasion in pan-cancer

Wang,

Wen,

Wang

et al. 2023

J Transl Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…Subtypes of lung cancer can be classified by applying ensemble machine learning tools with multi-class classification capability. The process starts with an analysis ( Huang et al, 2017 ; Hsu and Dong, 2018 ) that classifies malignant and benign based binary classification using various machine learning techniques ( Cai et al, 2015 ; Tian, 2017 ; Su et al, 2020 ; Huang et al, 2021 ; Wang et al, 2022 ).…”

Section: Rna-sequencing Analysis Identified By Targetmentioning

confidence: 99%

“…DCNet is an autoencoder-based deep learning model that predicts about 400 cell types from a bulk RNA-seq dataset and discovers marker genes ( Wang et al, 2022 ). As presented in Figure 5 , the DCNet model consists of a total of three layers: an input layer corresponding to the marker gene, a hidden layer represented by the cell type, and an output layer composed of TCGA gene data.…”

Section: Rna-sequencing Analysis Using Artificial Intelligence Techni...mentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-based non-small cell lung cancer transcriptome RNA-sequence analysis technology selection guide

Joo

Pyo²,

Chung³

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

The incidence and mortality rates of lung cancer are high worldwide, where non-small cell lung cancer (NSCLC) accounts for more than 85% of lung cancer cases. Recent non-small cell lung cancer research has been focused on analyzing patient prognosis after surgery and identifying mechanisms in connection with clinical cohort and ribonucleic acid (RNA) sequencing data, including single-cell ribonucleic acid (scRNA) sequencing data. This paper investigates statistical techniques and artificial intelligence (AI) based non-small cell lung cancer transcriptome data analysis methods divided into target and analysis technology groups. The methodologies of transcriptome data were schematically categorized so researchers can easily match analysis methods according to their goals. The most widely known and frequently utilized transcriptome analysis goal is to find essential biomarkers and classify carcinomas and cluster NSCLC subtypes. Transcriptome analysis methods are divided into three major categories: Statistical analysis, machine learning, and deep learning. Specific models and ensemble techniques typically used in NSCLC analysis are summarized in this paper, with the intent to lay a foundation for advanced research by converging and linking the various analysis methods available.

show abstract

The hitchhikers’ guide to RNA sequencing and functional analysis

Chen

Shrestha

Green

et al. 2023

Briefings in Bioinformatics

View full text Add to dashboard Cite

DNA and RNA sequencing technologies have revolutionized biology and biomedical sciences, sequencing full genomes and transcriptomes at very high speeds and reasonably low costs. RNA sequencing (RNA-Seq) enables transcript identification and quantification, but once sequencing has concluded researchers can be easily overwhelmed with questions such as how to go from raw data to differential expression (DE), pathway analysis and interpretation. Several pipelines and procedures have been developed to this effect. Even though there is no unique way to perform RNA-Seq analysis, it usually follows these steps: 1) raw reads quality check, 2) alignment of reads to a reference genome, 3) aligned reads’ summarization according to an annotation file, 4) DE analysis and 5) gene set analysis and/or functional enrichment analysis. Each step requires researchers to make decisions, and the wide variety of options and resulting large volumes of data often lead to interpretation challenges. There also seems to be insufficient guidance on how best to obtain relevant information and derive actionable knowledge from transcription experiments. In this paper, we explain RNA-Seq steps in detail and outline differences and similarities of different popular options, as well as advantages and disadvantages. We also discuss non-coding RNA analysis, multi-omics, meta-transcriptomics and the use of artificial intelligence methods complementing the arsenal of tools available to researchers. Lastly, we perform a complete analysis from raw reads to DE and functional enrichment analysis, visually illustrating how results are not absolute truths and how algorithmic decisions can greatly impact results and interpretation.

show abstract

Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment

Cited by 5 publications

References 41 publications

Portraying the dark side of endogenous IFN-λ for promoting cancer progression and immunoevasion in pan-cancer

Portraying the dark side of endogenous IFN-λ for promoting cancer progression and immunoevasion in pan-cancer

Artificial intelligence-based non-small cell lung cancer transcriptome RNA-sequence analysis technology selection guide

The hitchhikers’ guide to RNA sequencing and functional analysis

Contact Info

Product

Resources

About