Machine learning analysis of lung squamous cell carcinoma gene expression datasets reveals novel prognostic signatures

Joon, Hemant Kumar; Thalor, Anamika; Gupta, Dinesh

doi:10.1016/j.compbiomed.2023.107430

Cited by 8 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, the use of a limited number of marker genes could introduce noise into practical applications; substituting them with more extensive sets of markers could enhance score reliability without substantial accuracy compromise. Thirdly, some more advanced techniques, such as machine learning, can be used to improve the accuracy of the prediction (47)(48)(49). Lastly, our analysis relied on bioinformatics approaches; additional cell or animal experiments are requisite to unveil the prospective roles of the identified genes in the progression of colon cancer.…”

Section: Discussionmentioning

confidence: 99%

Integrative analysis reveals a four-gene signature for predicting survival and immunotherapy response in colon cancer patients using bulk and single-cell RNA-seq data

Chai,

Zhao,

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

BackgroundColon cancer (CC) ranks as one of the leading causes of cancer-related mortality globally. Single-cell transcriptome sequencing (scRNA-seq) offers precise gene expression data for distinct cell types. This study aimed to utilize scRNA-seq and bulk transcriptome sequencing (bulk RNA-seq) data from CC samples to develop a novel prognostic model.MethodsscRNA-seq data was downloaded from the GSE161277 database. R packages including “Seurat”, “Harmony”, and “singleR” were employed to categorize eight major cell types within normal and tumor tissues. By comparing tumor and normal samples, differentially expressed genes (DEGs) across these major cell types were identified. Gene Ontology (GO) enrichment analyses of DEGs for each cell type were conducted using “Metascape”. DEGs-based signature construction involved Cox regression and least absolute shrinkage operator (LASSO) analyses, performed on The Cancer Genome Atlas (TCGA) training cohort. Validation occurred in the GSE39582 and GSE33382 datasets. The expression pattern of prognostic genes was verified using spatial transcriptome sequencing (ST-seq) data. Ultimately, an established prognostic nomogram based on the gene signature and age was established and calibrated. Sensitivity to chemotherapeutic drugs was predicted with the “oncoPredict” R package.ResultsUsing scRNA-Seq data, we examined 33,213 cells, categorizing them into eight cell types within normal and tumor samples. GO enrichment analysis revealed various cancer-related pathways across DEGs in these cell types. Among the 55 DEGs identified via univariate Cox regression, four independent prognostic genes emerged: PTPN6, CXCL13, SPINK4, and NPDC1. Expression validation through ST-seq confirmed PTPN6 and CXCL13 predominance in immune cells, while SPINK4 and NPDC1 were relatively epithelial cell-specific. Creating a four-gene prognostic signature, Kaplan-Meier survival analyses emphasized higher risk scores correlating with unfavorable prognoses, confirmed across training and validation cohorts. The risk score emerged as an independent prognostic factor, supported by a reliable nomogram. Intriguingly, drug sensitivity analysis unveiled contrasting anti-cancer drug responses in the two risk groups, suggesting significant clinical implications.ConclusionWe developed a novel prognostic four-gene risk model, and these genes may act as potential therapeutic targets for CC.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrative analysis reveals a four-gene signature for predicting survival and immunotherapy response in colon cancer patients using bulk and single-cell RNA-seq data

Chai,

Zhao,

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Firstly, we focused on those genes with large variations, which presented a median absolute deviation (MAD) value greater than 1 [ 24 ]. Secondly, the univariate Cox analysis was utilized to identify the genes related to prognosis, of which genes with a P value less than 0.05 were included for further analysis [ 25 ]. Thirdly, we randomly opted for 80 % patients to do univariate Cox analysis and repeated this operation 1000 times.…”

Section: Methodsmentioning

confidence: 99%

A robust primary liver cancer subtype related to prognosis and drug response based on a multiple combined classifying strategy

Deng,

Lai,

Zhang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Cytotoxicity and toxicoproteomics analysis of thiazolidinedione exposure in human‐derived cardiomyocytes

Al Sultan,

Rattray,

Rattray

2024

J of Applied Toxicology

View full text Add to dashboard Cite

Thiazolidinediones (TZDs) (e.g. pioglitazone and rosiglitazone), known insulin sensitiser agents for type II diabetes mellitus, exhibit controversial effects on cardiac tissue. Despite consensus on their association with increased heart failure risk, limiting TZD use in diabetes management, the underlying mechanisms remain uncharacterised. Herein, we report a comprehensive in vitro investigation utilising a novel toxicoproteomics pipeline coupled with cytotoxicity assays in human adult cardiomyocytes to elucidate mechanistic insights into TZD cardiotoxicity. The cytotoxicity assay findings showed a significant loss of mitochondrial adenosine triphosphate production upon exposure to either TZD agents, which may underpin TZD cardiotoxicity. Our toxicoproteomics analysis revealed that mitochondrial dysfunction primarily stems from oxidative phosphorylation impairment, with distinct signalling mechanisms observed for both agents. The type of cell death differed strikingly between the two agents, with rosiglitazone exhibiting features of caspase‐dependent apoptosis and pioglitazone implicating mitochondrial‐mediated necroptosis, as evidenced by the protein upregulation in the phosphoglycerate mutase family 5–dynamin‐related protein 1 axis. Furthermore, our analysis revealed additional mechanistic aspects of cardiotoxicity, showcasing drug specificity. The downregulation of various proteins involved in protein machinery and protein processing in the endoplasmic reticulum was observed in rosiglitazone‐treated cells, implicating proteostasis in the rosiglitazone cardiotoxicity. Regarding pioglitazone, the findings suggested the potential activation of the interplay between the complement and coagulation systems and the disruption of the cytoskeletal architecture, which was primarily mediated through the integrin‐signalling pathways responsible for pioglitazone‐induced myocardial contractile failure. Collectively, this study unlocks substantial mechanistic insight into TZD cardiotoxicity, providing the rationale for future optimisation of antidiabetic therapies.

show abstract

Machine learning analysis of lung squamous cell carcinoma gene expression datasets reveals novel prognostic signatures

Cited by 8 publications

References 62 publications

Integrative analysis reveals a four-gene signature for predicting survival and immunotherapy response in colon cancer patients using bulk and single-cell RNA-seq data

Integrative analysis reveals a four-gene signature for predicting survival and immunotherapy response in colon cancer patients using bulk and single-cell RNA-seq data

A robust primary liver cancer subtype related to prognosis and drug response based on a multiple combined classifying strategy

Cytotoxicity and toxicoproteomics analysis of thiazolidinedione exposure in human‐derived cardiomyocytes

Contact Info

Product

Resources

About