In recent years, due to the high availability of omic data, data-driven biology has greatly expanded. However, the analysis of different data sources is still an open challenge. A few multi-omics approaches have been proposed in the literature, none of which takes into consideration the intrinsic topology of each omic, though. In this work, an unsupervised learning method based on a deep neural network is proposed. Foreach omic, a separate network is trained, whose outputs are fused into a single graph; at this purpose, an innovative loss function has been designed to better represent the data cluster manifolds. The graph adjacency matrix is exploited to determine similarities among samples. With this approach, omics having a different number of features are merged into a unique representation. Quantitative and qualitative analyses show that the proposed method has comparable results to the state of the art. The method has great intrinsic flexibility as it can be customized according to the complexity of the tasks and it has a lot of room for future improvements compared to more fine-tuned methods, opening the way for future research.
Unsupervised Multi-Omic Data Fusion: the Neural Graph Learning Network / Barbiero, Pietro; Lovino, Marta; Siviero, Mattia; Ciravegna, Gabriele; Randazzo, Vincenzo; Ficarra, Elisa; Cirrincione, Giansalvo. - ELETTRONICO. - 12463:(2020), pp. 172-182. (Intervento presentato al convegno 16th International Conference on Intelligent Computing, ICIC 2020 tenutosi a Bari (ita) nel Ottobre 2020) [10.1007/978-3-030-60799-9_15].
Unsupervised Multi-Omic Data Fusion: the Neural Graph Learning Network
Marta Lovino;Gabriele Ciravegna;Vincenzo Randazzo;Elisa Ficarra;Giansalvo Cirrincione
2020
Abstract
In recent years, due to the high availability of omic data, data-driven biology has greatly expanded. However, the analysis of different data sources is still an open challenge. A few multi-omics approaches have been proposed in the literature, none of which takes into consideration the intrinsic topology of each omic, though. In this work, an unsupervised learning method based on a deep neural network is proposed. Foreach omic, a separate network is trained, whose outputs are fused into a single graph; at this purpose, an innovative loss function has been designed to better represent the data cluster manifolds. The graph adjacency matrix is exploited to determine similarities among samples. With this approach, omics having a different number of features are merged into a unique representation. Quantitative and qualitative analyses show that the proposed method has comparable results to the state of the art. The method has great intrinsic flexibility as it can be customized according to the complexity of the tasks and it has a lot of room for future improvements compared to more fine-tuned methods, opening the way for future research.File | Dimensione | Formato | |
---|---|---|---|
ICIC_2020_barbiero_Lovino.pdf
non disponibili
Descrizione: Articolo principale
Tipologia:
1. Preprint / submitted version [pre- review]
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
13.32 MB
Formato
Adobe PDF
|
13.32 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
bookExtracted_Unsupervised Multi-omic Data Fusion.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
2.42 MB
Formato
Adobe PDF
|
2.42 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Neural Graph Learning for Multi-Omic Data Fusion_4_cameraReady.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
588.44 kB
Formato
Adobe PDF
|
588.44 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2846898