Molecular classification of ovarian carcinomas using deep learning-based multi-omics data integration
Aristotle University of Thessaloniki · 01.01.2024
DOI: 10.26262/heal.auth.ir.355382 ↗Kurz gefasst
Fachartikel in der Zeitschrift Aristotle University of Thessaloniki, erschienen am 01.01.2024. Verfasst von Ioannis Sotirios Tikas.
Abstract (Originalsprache)
Modern cancer care is based on segregating cancer patients into smaller subgroups, to provide more individualized treatment. In turn, they benefit from better outcomes using different therapeutic modalities. Epithelial ovarian cancer is the fifth most common malignancy across women, yet only 5-10\% of patients, who harbor BRCA1/2 mutations, are treated with targeted agents. High throughput methods enabled comprehensive molecular profiling of tumor tissues. Nonetheless, little progress has been made in determining molecular subtypes and providing personalized treatment to those patients. Recent developments in artificial intelligence, more importantly, the development of unsupervised, semi- or self- supervised algorithms, hold promise to solve this elusive task. Our work attempts to provide a template for evaluating multi-omics integration algorithms by using a series of discrete steps 1) applying a dimensionality reduction method, 2) perform clustering, 3) validate results using metrics. Retrospectively, the generated clusters can be statistically summarized and compared for potential differences.
Schlagwörter
Zitieren
APA
Tikas, I. S. (2024). Molecular classification of ovarian carcinomas using deep learning-based multi-omics data integration. Aristotle University of Thessaloniki. https://doi.org/10.26262/heal.auth.ir.355382
Vancouver
Tikas IS. Molecular classification of ovarian carcinomas using deep learning-based multi-omics data integration. Aristotle University of Thessaloniki. 2024. doi:10.26262/heal.auth.ir.355382
BibTeX
@article{Tikas2024,
author = {Tikas, Ioannis Sotirios},
title = {Molecular classification of ovarian carcinomas using deep learning-based multi-omics data integration},
journal = {Aristotle University of Thessaloniki},
year = {2024},
doi = {10.26262/heal.auth.ir.355382}
}
EUVIMED