DNA Methylation Analysis Identifies Clinically Relevant Lung Adenocarcinoma Subgroups
Afolabi, O. I.
Show abstract
Lung adenocarcinoma (LUAD) is the most prevalent subtype of lung cancer and is characterized by significant molecular heterogeneity and poor prognosis, primarily due to late-stage diagnoses. Therefore, detailed molecular characterization of LUAD is crucial for developing biomarkers to accurately detect the disease in its early stages. This study investigates the role of DNA methylation in LUAD, emphasizing its potential as a biomarker for cancer detection and as a tool for understanding tumor biology. The study identified 4,925 differentially methylated sites (DMSs) and prioritized the top 200 DMSs for downstream analyses. Functional enrichment analysis revealed that site-specific hypermethylation in exon 1 and distal promoter regions are linked to critical developmental processes, including morphogenesis, pattern specification, stem cell differentiation, and synaptic transmission, suggesting that these epigenetic changes may disrupt normal cellular functions and contribute to tumorigenesis. Support vector machines demonstrated the diagnostic potential of these hypermethylated sites, achieving perfect classification of LUAD and normal adjacent tissues with as few as five features. Additionally, the strong correlation between methylation levels and feature importance scores further explained the predictive accuracy of these methylation markers. The study also identified distinct methylation subgroups within LUAD tumors, independent of traditional staging, each associated with unique transcriptional dysregulation and biological processes, such as DNA repair, immune response, and ribosome biogenesis. These findings not only enhance our understanding of LUAD pathophysiology but also underscore the clinical utility of DNA methylation as a diagnostic tool and guide for patient management.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development of a Single Molecule Counting Assay to Differentiate Chromophobe Renal Cancer and Oncocytoma in Clinics 92%
- A novel role for the tumor suppressor gene ITF2 in lung tumorigenesis and chemotherapy response 92%
- Bimodal genomic approach predicting Semaphorin 7A (SEMA7A) as prognostic biomarker in adrenocortical carcinoma 92%
Similar papers in this journal
Similar papers in this journal
- Unveiling epigenetic regulatory elements associated with breast cancer development 93%
- Immunohistochemical Profiling of Histone Modification Biomarkers Identifies Subtype-Specific Epigenetic Signatures and Potential Drug Targets in Breast Cancer 92%
- Machine Learning-based Classification of transcriptome Signatures of non-ulcerative Bladder Pain Syndrome 91%
Similar papers in this journal
- Identification of differential hypothalamic DNA methylation and gene expression associated with sexual partner preferences in rams 94%
- Predicting cancer origins with a DNA methylation-based deep neural network model 93%
- Genome wide DNA methylation profiling identifies specific epigenetic features in high-risk cutaneous squamous cell carcinoma. 93%
Similar papers in this journal
- Distinct genome-wide DNA methylation and gene expression signatures in classical monocytes from African American patients with systemic sclerosis 92%
- Regulatory networks driving expression of genes critical for glioblastoma are controlled by the transcription factor c-Jun and the pre-existing epigenetic modifications. 92%
- Cancer-associated fibroblasts reveal aberrant DNA methylation across different types of cancer 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.