De Falco, Antonio (2024) AI-based computational methods for tumor heterogeneity characterization, early cancer detection and oncology drug target. [Tesi di dottorato]
Anteprima |
Testo
De_Falco_Antonio_36.pdf Download (40MB) | Anteprima |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | AI-based computational methods for tumor heterogeneity characterization, early cancer detection and oncology drug target |
| Autori: | Autore Email De Falco, Antonio antonio.defalco4@unina.it |
| Data: | 8 Marzo 2024 |
| Numero di pagine: | 132 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Computational and quantitative biology |
| Ciclo di dottorato: | 36 |
| Coordinatore del Corso di dottorato: | nome email Ceccarelli, Michele michele.ceccarelli@unina.it |
| Tutor: | nome email Ceccarelli, Michele [non definito] Cerulo, Luigi [non definito] |
| Data: | 8 Marzo 2024 |
| Numero di pagine: | 132 |
| Parole chiave: | Liquid biopsy, Machine Learning, Early cancer detection, Minimal residual disease, Tumor heterogeneity, Drug Prioritization |
| Settori scientifico-disciplinari del MIUR: | Area 05 - Scienze biologiche > BIO/11 - Biologia molecolare Area 01 - Scienze matematiche e informatiche > INF/01 - Informatica |
| Depositato il: | 19 Giu 2024 12:20 |
| Ultima modifica: | 24 Mar 2026 08:15 |
| URI: | http://www.fedoa.unina.it/id/eprint/15522 |
Abstract
The Ph.D. thesis presents a comprehensive analysis framework that exploits the advances in sequencing technologies and statistical machine learning to address critical aspects of cancer research. These advancements have revolutionized our ability to analyze a large amount of biological data and also with unprecedented resolution, allowing us to analyze every single cell and detect the presence of even the smallest percentage of circulating tumor DNA fragments in liquid biopsies. Indeed, the increase in the accuracy and cost reduction of sequencing led to an exponential increase in the amount of data generated, which allows the creation of large-scale human genomics, transcriptomics, and proteomics datasets, allowing and requiring the need to develop novel computational methods capable of analyzing this large-scale data that can help advance our understanding of cancer biology, promising to improve diagnostic accuracy and therapeutic strategies for cancer patients. The work presented in this thesis is divided into three main chapters: in the first chapter, a method is presented to segregate non-malignant tumor microenvironment (TME) cells from malignant ones and characterize tumor heterogeneity at high resolution by automatically identifying clonal copy number substructure from single cell RNA-seq data; In the second chapter, the potential of fragmentomics combined with deep learning models in early cancer diagnosis and minimal residual disease (MRD) analysis based on liquid biopsy data is explored; finally, the last chapter describes a method based on Gaussian processes for the prioritization of oncology drug targets based on a proteomic dataset.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
