Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)

Abstract Background Liver cancer (Hepatocellular carcinoma; HCC) prevalence is increasing and with poor clinical outcome expected it means greater understanding of HCC aetiology is urgently required. This study explored a deep learning solution to detect biologically important features that distingu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alice R. Owens, Caitríona E. McInerney, Kevin M. Prise, Darragh G. McArt, Anna Jurek-Loughrey
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Hepatocellular carcinoma Deep learning Clustering Prognostic subgroups Autoencoders Survival analysis Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/4ecee810662d4de480abda7b6aa9c228
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4ecee810662d4de480abda7b6aa9c228
record_format	dspace
spelling	oai:doaj.org-article:4ecee810662d4de480abda7b6aa9c2282021-11-28T12:11:06ZNovel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)10.1186/s12859-021-04454-41471-2105https://doaj.org/article/4ecee810662d4de480abda7b6aa9c2282021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04454-4https://doaj.org/toc/1471-2105Abstract Background Liver cancer (Hepatocellular carcinoma; HCC) prevalence is increasing and with poor clinical outcome expected it means greater understanding of HCC aetiology is urgently required. This study explored a deep learning solution to detect biologically important features that distinguish prognostic subgroups. A novel architecture of an Artificial Neural Network (ANN) trained with a customised objective function (LRSC) was developed. The ANN should discover new data representations, to detect patient subgroups that are biologically homogenous (clustering loss) and similar in survival (survival loss) while removing noise from the data (reconstruction loss). The model was applied to TCGA-HCC multi-omics data and benchmarked against baseline models that only use a reconstruction objective function (BCE, MSE) for learning. With the baseline models, the new features are then filtered based on survival information and used for clustering patients. Different variants of the customised objective function, incorporating only reconstruction and clustering losses (LRC); and reconstruction and survival losses (LRS) were also evaluated. Robust features consistently detected were compared between models and validated in TCGA and LIRI-JP HCC cohorts. Results The combined loss (LRSC) discovered highly significant prognostic subgroups (P-value = 1.55E−77) with more accurate sample assignment (Silhouette scores: 0.59–0.7) compared to baseline models (0.18–0.3). All LRSC bottleneck features (N = 100) were significant for survival, compared to only 11–21 for baseline models. Prognostic subgroups were not explained by disease grade or risk factors. Instead LRSC identified robust features including 377 mRNAs, many of which were novel (61.27%) compared to those identified by the other losses. Some 75 mRNAs were prognostic in TCGA, while 29 were prognostic in LIRI-JP also. LRSC also identified 15 robust miRNAs including two novel (hsa-let-7g; hsa-mir-550a-1) and 328 methylation features with 71% being prognostic. Gene-enrichment and Functional Annotation Analysis identified seven pathways differentiating prognostic clusters. Conclusions Combining cluster and survival metrics with the reconstruction objective function facilitated superior prognostic subgroup identification. The hybrid model identified more homogeneous clusters that consequently were more biologically meaningful. The novel and prognostic robust features extracted provide additional information to improve our understanding of a complex disease to help reveal its aetiology. Moreover, the gene features identified may have clinical applications as therapeutic targets.Alice R. OwensCaitríona E. McInerneyKevin M. PriseDarragh G. McArtAnna Jurek-LoughreyBMCarticleHepatocellular carcinomaDeep learningClusteringPrognostic subgroupsAutoencodersSurvival analysisComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss 1, Pp 1-22 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hepatocellular carcinoma Deep learning Clustering Prognostic subgroups Autoencoders Survival analysis Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	Hepatocellular carcinoma Deep learning Clustering Prognostic subgroups Autoencoders Survival analysis Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Alice R. Owens Caitríona E. McInerney Kevin M. Prise Darragh G. McArt Anna Jurek-Loughrey Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
description	Abstract Background Liver cancer (Hepatocellular carcinoma; HCC) prevalence is increasing and with poor clinical outcome expected it means greater understanding of HCC aetiology is urgently required. This study explored a deep learning solution to detect biologically important features that distinguish prognostic subgroups. A novel architecture of an Artificial Neural Network (ANN) trained with a customised objective function (LRSC) was developed. The ANN should discover new data representations, to detect patient subgroups that are biologically homogenous (clustering loss) and similar in survival (survival loss) while removing noise from the data (reconstruction loss). The model was applied to TCGA-HCC multi-omics data and benchmarked against baseline models that only use a reconstruction objective function (BCE, MSE) for learning. With the baseline models, the new features are then filtered based on survival information and used for clustering patients. Different variants of the customised objective function, incorporating only reconstruction and clustering losses (LRC); and reconstruction and survival losses (LRS) were also evaluated. Robust features consistently detected were compared between models and validated in TCGA and LIRI-JP HCC cohorts. Results The combined loss (LRSC) discovered highly significant prognostic subgroups (P-value = 1.55E−77) with more accurate sample assignment (Silhouette scores: 0.59–0.7) compared to baseline models (0.18–0.3). All LRSC bottleneck features (N = 100) were significant for survival, compared to only 11–21 for baseline models. Prognostic subgroups were not explained by disease grade or risk factors. Instead LRSC identified robust features including 377 mRNAs, many of which were novel (61.27%) compared to those identified by the other losses. Some 75 mRNAs were prognostic in TCGA, while 29 were prognostic in LIRI-JP also. LRSC also identified 15 robust miRNAs including two novel (hsa-let-7g; hsa-mir-550a-1) and 328 methylation features with 71% being prognostic. Gene-enrichment and Functional Annotation Analysis identified seven pathways differentiating prognostic clusters. Conclusions Combining cluster and survival metrics with the reconstruction objective function facilitated superior prognostic subgroup identification. The hybrid model identified more homogeneous clusters that consequently were more biologically meaningful. The novel and prognostic robust features extracted provide additional information to improve our understanding of a complex disease to help reveal its aetiology. Moreover, the gene features identified may have clinical applications as therapeutic targets.
format	article
author	Alice R. Owens Caitríona E. McInerney Kevin M. Prise Darragh G. McArt Anna Jurek-Loughrey
author_facet	Alice R. Owens Caitríona E. McInerney Kevin M. Prise Darragh G. McArt Anna Jurek-Loughrey
author_sort	Alice R. Owens
title	Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
title_short	Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
title_full	Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
title_fullStr	Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
title_full_unstemmed	Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)
title_sort	novel deep learning-based solution for identification of prognostic subgroups in liver cancer (hepatocellular carcinoma)
publisher	BMC
publishDate	2021
url	https://doaj.org/article/4ecee810662d4de480abda7b6aa9c228
work_keys_str_mv	AT alicerowens noveldeeplearningbasedsolutionforidentificationofprognosticsubgroupsinlivercancerhepatocellularcarcinoma AT caitrionaemcinerney noveldeeplearningbasedsolutionforidentificationofprognosticsubgroupsinlivercancerhepatocellularcarcinoma AT kevinmprise noveldeeplearningbasedsolutionforidentificationofprognosticsubgroupsinlivercancerhepatocellularcarcinoma AT darraghgmcart noveldeeplearningbasedsolutionforidentificationofprognosticsubgroupsinlivercancerhepatocellularcarcinoma AT annajurekloughrey noveldeeplearningbasedsolutionforidentificationofprognosticsubgroupsinlivercancerhepatocellularcarcinoma
_version_	1718408138791583744

Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)

Ejemplares similares