Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning

Abstract Over the past years, large consortia have been established to fuel the sequencing of whole genomes of many cancer patients. Despite the increased abundance in tools to study the impact of SNVs, non-coding SVs have been largely ignored in these data. Here, we introduce svMIL2, an improved ve...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marleen M. Nieboer, Luan Nguyen, Jeroen de Ridder
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0b53ef2e3f784aba84c29c9f9d64c804
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0b53ef2e3f784aba84c29c9f9d64c804
record_format	dspace
spelling	oai:doaj.org-article:0b53ef2e3f784aba84c29c9f9d64c8042021-12-02T16:14:17ZPredicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning10.1038/s41598-021-93917-y2045-2322https://doaj.org/article/0b53ef2e3f784aba84c29c9f9d64c8042021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93917-yhttps://doaj.org/toc/2045-2322Abstract Over the past years, large consortia have been established to fuel the sequencing of whole genomes of many cancer patients. Despite the increased abundance in tools to study the impact of SNVs, non-coding SVs have been largely ignored in these data. Here, we introduce svMIL2, an improved version of our Multiple Instance Learning-based method to study the effect of somatic non-coding SVs disrupting boundaries of TADs and CTCF loops in 1646 cancer genomes. We demonstrate that svMIL2 predicts pathogenic non-coding SVs with an average AUC of 0.86 across 12 cancer types, and identifies non-coding SVs affecting well-known driver genes. The disruption of active (super) enhancers in open chromatin regions appears to be a common mechanism by which non-coding SVs exert their pathogenicity. Finally, our results reveal that the contribution of pathogenic non-coding SVs as opposed to driver SNVs may highly vary between cancers, with notably high numbers of genes being disrupted by pathogenic non-coding SVs in ovarian and pancreatic cancer. Taken together, our machine learning method offers a potent way to prioritize putatively pathogenic non-coding SVs and leverage non-coding SVs to identify driver genes. Moreover, our analysis of 1646 cancer genomes demonstrates the importance of including non-coding SVs in cancer diagnostics.Marleen M. NieboerLuan NguyenJeroen de RidderNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Marleen M. Nieboer Luan Nguyen Jeroen de Ridder Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
description	Abstract Over the past years, large consortia have been established to fuel the sequencing of whole genomes of many cancer patients. Despite the increased abundance in tools to study the impact of SNVs, non-coding SVs have been largely ignored in these data. Here, we introduce svMIL2, an improved version of our Multiple Instance Learning-based method to study the effect of somatic non-coding SVs disrupting boundaries of TADs and CTCF loops in 1646 cancer genomes. We demonstrate that svMIL2 predicts pathogenic non-coding SVs with an average AUC of 0.86 across 12 cancer types, and identifies non-coding SVs affecting well-known driver genes. The disruption of active (super) enhancers in open chromatin regions appears to be a common mechanism by which non-coding SVs exert their pathogenicity. Finally, our results reveal that the contribution of pathogenic non-coding SVs as opposed to driver SNVs may highly vary between cancers, with notably high numbers of genes being disrupted by pathogenic non-coding SVs in ovarian and pancreatic cancer. Taken together, our machine learning method offers a potent way to prioritize putatively pathogenic non-coding SVs and leverage non-coding SVs to identify driver genes. Moreover, our analysis of 1646 cancer genomes demonstrates the importance of including non-coding SVs in cancer diagnostics.
format	article
author	Marleen M. Nieboer Luan Nguyen Jeroen de Ridder
author_facet	Marleen M. Nieboer Luan Nguyen Jeroen de Ridder
author_sort	Marleen M. Nieboer
title	Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
title_short	Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
title_full	Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
title_fullStr	Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
title_full_unstemmed	Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning
title_sort	predicting pathogenic non-coding svs disrupting the 3d genome in 1646 whole cancer genomes using multiple instance learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0b53ef2e3f784aba84c29c9f9d64c804
work_keys_str_mv	AT marleenmnieboer predictingpathogenicnoncodingsvsdisruptingthe3dgenomein1646wholecancergenomesusingmultipleinstancelearning AT luannguyen predictingpathogenicnoncodingsvsdisruptingthe3dgenomein1646wholecancergenomesusingmultipleinstancelearning AT jeroenderidder predictingpathogenicnoncodingsvsdisruptingthe3dgenomein1646wholecancergenomesusingmultipleinstancelearning
_version_	1718384333463486464

Predicting pathogenic non-coding SVs disrupting the 3D genome in 1646 whole cancer genomes using multiple instance learning

Ejemplares similares