Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Journal of translational medicine
2025
|
| Subjects: | |
| Online Access: | https://pubmed.ncbi.nlm.nih.gov/40598554/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1868266184079572992 |
|---|---|
| author | Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed |
| author_facet | Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed |
| collection | PubMed - marine biology |
| contents | Comparative analysis of statistical and deep learning-based multi-omics integration for breast cancer subtype classification. Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed Humans Deep Learning Breast Neoplasms Female Genomics Transcriptome Gene Expression Profiling Multiomics Breast cancer (BC) is a critical cause of cancer-related death globally. The heterogeneity of BC subtypes poses challenges in understanding molecular mechanisms, early diagnosis, and disease management. Recent studies suggest that integrating multi-omics layers can significantly enhance BC subtype identification. However, evaluating different multi-omics integration methods for BC subtyping remains ambiguous. In this study, we conducted a multi-omics integration analysis on 960 BC patient samples, incorporating three omics layers: Host transcriptomics, epigenomics, and shotgun microbiome. We compared two integration approaches the statistical-based approach (MOFA+) and a deep learning-based approach (MOGCN) for this integration. We evaluated both methods using complementary evaluation criteria. First, we assessed the ability of selected features to discriminate between BC subtypes using both linear and nonlinear classification models. Second, we analyzed the biological relevance of the selected features to key BC pathways, focusing on transcriptomics-driven insights. Our results showed that MOFA+ outperformed MOGCN in feature selection, achieving the highest F1 score (0.75) in the nonlinear classification model, with MOFA+ also identifying 121 relevant pathways compared to 100 from MOGCN. Notably, one of the key pathways Fc gamma R-mediated phagocytosis and the SNARE pathway was implicated, offering insights into immune responses and tumor progression. These findings suggest that MOFA+ is a more effective unsupervised tool for feature selection in BC subtyping. Our study underscores the potential of multi-omics integration to improve BC subtype prediction and provides critical insights for advancing personalized medicine in BC. |
| format | Artículo científico |
| id | pubmed_40598554 |
| institution | PubMed |
| language | en |
| publishDate | 2025 |
| publisher | Journal of translational medicine |
| record_format | pubmed |
| spellingShingle | Comparative analysis of statistical and deep learning-based multi-omics integration for breast cancer subtype classification. Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed Humans Deep Learning Breast Neoplasms Female Genomics Transcriptome Gene Expression Profiling Multiomics Comparative analysis of statistical and deep learning-based multi-omics integration for breast cancer subtype classification. Omran, Mahmoud M Emam, Mohamed Gamaleldin, Mariam Abushady, Asmaa M Elattar, Mustafa A El-Hadidi, Mohamed Humans Deep Learning Breast Neoplasms Female Genomics Transcriptome Gene Expression Profiling Multiomics Breast cancer (BC) is a critical cause of cancer-related death globally. The heterogeneity of BC subtypes poses challenges in understanding molecular mechanisms, early diagnosis, and disease management. Recent studies suggest that integrating multi-omics layers can significantly enhance BC subtype identification. However, evaluating different multi-omics integration methods for BC subtyping remains ambiguous. In this study, we conducted a multi-omics integration analysis on 960 BC patient samples, incorporating three omics layers: Host transcriptomics, epigenomics, and shotgun microbiome. We compared two integration approaches the statistical-based approach (MOFA+) and a deep learning-based approach (MOGCN) for this integration. We evaluated both methods using complementary evaluation criteria. First, we assessed the ability of selected features to discriminate between BC subtypes using both linear and nonlinear classification models. Second, we analyzed the biological relevance of the selected features to key BC pathways, focusing on transcriptomics-driven insights. Our results showed that MOFA+ outperformed MOGCN in feature selection, achieving the highest F1 score (0.75) in the nonlinear classification model, with MOFA+ also identifying 121 relevant pathways compared to 100 from MOGCN. Notably, one of the key pathways Fc gamma R-mediated phagocytosis and the SNARE pathway was implicated, offering insights into immune responses and tumor progression. These findings suggest that MOFA+ is a more effective unsupervised tool for feature selection in BC subtyping. Our study underscores the potential of multi-omics integration to improve BC subtype prediction and provides critical insights for advancing personalized medicine in BC. |
| title | Comparative analysis of statistical and deep learning-based multi-omics integration for breast cancer subtype classification. |
| topic | Humans Deep Learning Breast Neoplasms Female Genomics Transcriptome Gene Expression Profiling Multiomics |
| url | https://pubmed.ncbi.nlm.nih.gov/40598554/ |