Developing a prognostic model using machine learning for disulfidptosis related lncRNA in lung adenocarcinoma DOI Creative Commons

Yang Pan,

Xuanhong Jin,

Haoting Xu

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 7, 2024

Abstract Disulfidptosis represents a novel cell death mechanism triggered by disulfide stress, with potential implications for advancements in cancer treatments. Although emerging evidence highlights the critical regulatory roles of long non-coding RNAs (lncRNAs) pathobiology lung adenocarcinoma (LUAD), research into lncRNAs specifically associated disulfidptosis LUAD, termed disulfidptosis-related (DRLs), remains insufficiently explored. Using The Cancer Genome Atlas (TCGA)-LUAD dataset, we implemented ten machine learning techniques, resulting 101 distinct model configurations. To assess predictive accuracy our model, employed both concordance index (C-index) and receiver operating characteristic (ROC) curve analyses. For deeper understanding underlying biological pathways, referred to Kyoto Encyclopedia Genes Genomes (KEGG) Gene Ontology (GO) functional enrichment analysis. Moreover, explored differences tumor microenvironment between high-risk low-risk patient cohorts. Additionally, thoroughly assessed prognostic value DRLs signatures predicting treatment outcomes. Kaplan–Meier (KM) survival analysis demonstrated significant difference overall (OS) cohorts (p < 0.001). showed robust performance, an area under ROC exceeding 0.75 at one year maintaining above 0.72 two three-year follow-ups. Further identified variations mutational burden (TMB) differential responses immunotherapies chemotherapies. Our validation, using three GEO datasets (GSE31210, GSE30219, GSE50081), revealed that C-index exceeded 0.67 GSE31210 GSE30219. Significant disease-free (DFS) OS were observed across all validation among different risk groups. offers as molecular biomarker LUAD prognosis.

Language: Английский

LncRNA PRBC induces autophagy to promote breast cancer progression through modulating PABPC1-mediated mRNA stabilization DOI
Yiran Liang, Bing Chen,

Fanchao Xu

et al.

Oncogene, Journal Year: 2024, Volume and Issue: 43(14), P. 1019 - 1032

Published: Feb. 16, 2024

Language: Английский

Citations

4
Perspective Chapter: Decoding Cancer’s Silent Players – A Comprehensive Guide to LncRNAs DOI Creative Commons
Abhijit Mandal, Sarbani Giri

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

Long non-coding RNAs (LncRNAs) are that do not code for proteins and were thus earlier known as Junk RNAs. Recently, LncRNAs have emerged critical regulators in the expression of coding genes various important biological signaling pathways, controlling crucial developmental processes. Reports association with several diseases including cancer also been implicated. play a diverse role regulating influencing tumorigenesis, progression, metastasis. They can function both oncogenes or tumor suppressors, modulating key pathways cellular Mutation epigenetic-induced aberrant dysregulates different essential leading to malignant phenotype hallmarks types cancer. Tumor cells secrete specific endogenous into fluids depending on type, giving rise stable circulating LncRNAs, proving be great potential non-invasive minimally invasive diagnostic biomarkers. In this chapter, we explore multifaceted roles types, highlighting their diagnostic/prognostic biomarkers therapeutic targets. Additionally, discuss innovative strategies targeting treatment, RNA interference CRISPR technology. This chapter will provide comprehensive overview LncRNAs’ implications research personalized medicine.

Language: Английский

Citations

0
Deciphering the oncogenic landscape: Unveiling the molecular machinery and clinical significance of LncRNA TMPO-AS1 in human cancers DOI

Shelesh krishna saraswat,

Bashar Shaker Mahmood,

Freddy Ajila

et al.

Pathology - Research and Practice, Journal Year: 2024, Volume and Issue: 255, P. 155190 - 155190

Published: Feb. 2, 2024

Language: Английский

Citations

1
A graphSAGE discovers synergistic combinations of Gefitinib, paclitaxel, and Icotinib for Lung adenocarcinoma management by targeting human genes and proteins: the RAIN protocol DOI Creative Commons
Sogand Sadeghi, Ali A. Kiaei, Mahnaz Boush

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: April 16, 2024

Abstract Background Adenocarcinoma of the lung is most common type cancer, and it characterized by distinct cellular molecular features. It occurs when abnormal cells multiply out control form a tumor in outer region lungs. serious life-threatening condition that requires effective timely management to improve survival quality life patients. One challenges this cancer treatment finding optimal combination drugs can target genes or proteins are involved disease process. Method In article, we propose novel method recommend combinations trending its associated proteins/genes, using Graph Neural Network (GNN) under RAIN protocol. The protocol three-step framework consists of: 1) Applying graph neural networks drug passing messages between for managing act as potential targets disease; 2) Retrieving relevant articles with clinical trials include those proposed previous step Natural Language Processing (NLP). search queries “Adenocarcinoma lung”, “Gefitinib”, “Paclitaxel”, “Icotinib” searched context based databases NLP; 3) Analyzing network meta-analysis measure comparative efficacy combinations. Result We applied our dataset nodes edges represent network, where each node gene, edge p-value them. found recommends combining Gefitinib, Paclitaxel, Icotinib proteins/genes. reviewed expert opinions on these medications they support claim. also confirmed effectiveness genes. Conclusion Our promising approach help clinicians researchers find best options patients, provide insights into underlying mechanisms disease. Highlights Proposing medicinal compounds together adenocarcinoma achieved 0.002858 targeted proteins/genes 3-Leveraging GraphSAGE Suggesting an Optimal Drug Combinations. Figure

Language: Английский

Citations

1
Developing a prognostic model using machine learning for disulfidptosis related lncRNA in lung adenocarcinoma DOI Creative Commons

Yang Pan,

Xuanhong Jin,

Haoting Xu

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 7, 2024

Abstract Disulfidptosis represents a novel cell death mechanism triggered by disulfide stress, with potential implications for advancements in cancer treatments. Although emerging evidence highlights the critical regulatory roles of long non-coding RNAs (lncRNAs) pathobiology lung adenocarcinoma (LUAD), research into lncRNAs specifically associated disulfidptosis LUAD, termed disulfidptosis-related (DRLs), remains insufficiently explored. Using The Cancer Genome Atlas (TCGA)-LUAD dataset, we implemented ten machine learning techniques, resulting 101 distinct model configurations. To assess predictive accuracy our model, employed both concordance index (C-index) and receiver operating characteristic (ROC) curve analyses. For deeper understanding underlying biological pathways, referred to Kyoto Encyclopedia Genes Genomes (KEGG) Gene Ontology (GO) functional enrichment analysis. Moreover, explored differences tumor microenvironment between high-risk low-risk patient cohorts. Additionally, thoroughly assessed prognostic value DRLs signatures predicting treatment outcomes. Kaplan–Meier (KM) survival analysis demonstrated significant difference overall (OS) cohorts (p < 0.001). showed robust performance, an area under ROC exceeding 0.75 at one year maintaining above 0.72 two three-year follow-ups. Further identified variations mutational burden (TMB) differential responses immunotherapies chemotherapies. Our validation, using three GEO datasets (GSE31210, GSE30219, GSE50081), revealed that C-index exceeded 0.67 GSE31210 GSE30219. Significant disease-free (DFS) OS were observed across all validation among different risk groups. offers as molecular biomarker LUAD prognosis.

Language: Английский

Citations

0