Multi-omics Combined with Machine Learning Facilitating the Diagnosis of Gastric Cancer
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This review explores gastric cancer biomarkers using multi-omics data, including genomics and metabolomics. It examines environmental factors and machine learning for early detection and precision medicine.
Area Of Science
- Oncology
- Genetics
- Biochemistry
Background
- Gastric cancer (GC) is a complex gastrointestinal malignancy.
- Early detection is crucial for effective precision medicine strategies.
- Existing research often focuses on single omics, overlooking integrated molecular changes.
Purpose Of The Study
- To comprehensively investigate multi-omics alterations (genomics, transcriptomics, proteomics, metabolomics) in gastric cancer development.
- To elucidate the impact of environmental exposures and family history on these biomarkers.
- To summarize machine learning applications for integrating multi-omics data in GC.
Main Methods
- Genomics, transcriptomics, proteomics, and metabolomics analyses were employed.
- Investigated alterations in DNA mutation, methylation, RNA (mRNA, lncRNA, miRNA, circRNA), proteins, and metabolism (glucose, amino acids, nucleotides, lipids).
- Evaluated the influence of factors like Helicobacter pylori (HP), Epstein-Barr virus (EBV), nitrosamines, smoking, alcohol, and family history.
Main Results
- Identified specific multi-omics biomarkers associated with gastric cancer progression.
- Demonstrated how environmental exposures and genetic predisposition modify endogenous substances and diagnostic markers.
- Highlighted the utility of machine learning in synthesizing complex multi-omics datasets for GC insights.
Conclusions
- Multi-omics approaches provide a deeper understanding of gastric cancer pathogenesis.
- Environmental and hereditary factors significantly influence GC biomarkers.
- Machine learning is a powerful tool for integrating diverse data types for improved GC diagnostics and personalized treatment.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
