Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization

Abstract Background Protein-RNA interactions play key roles in many processes regulating gene expression. To understand the underlying binding preference, ultraviolet cross-linking and immunoprecipitation (CLIP)-based methods have been used to identify the binding sites for hundreds of RNA-binding p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shitao Zhao, Michiaki Hamada
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	RNA-binding protein Residual network Multi-label classification Integrated gradients Photoactivatable ribonucleoside enhanced cross-linking and immunoprecipitation Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/ea3391ee6b744fe68c495de855c6b42c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ea3391ee6b744fe68c495de855c6b42c
record_format	dspace
spelling	oai:doaj.org-article:ea3391ee6b744fe68c495de855c6b42c2021-11-21T12:09:13ZMulti-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization10.1186/s12859-021-04430-y1471-2105https://doaj.org/article/ea3391ee6b744fe68c495de855c6b42c2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04430-yhttps://doaj.org/toc/1471-2105Abstract Background Protein-RNA interactions play key roles in many processes regulating gene expression. To understand the underlying binding preference, ultraviolet cross-linking and immunoprecipitation (CLIP)-based methods have been used to identify the binding sites for hundreds of RNA-binding proteins (RBPs) in vivo. Using these large-scale experimental data to infer RNA binding preference and predict missing binding sites has become a great challenge. Some existing deep-learning models have demonstrated high prediction accuracy for individual RBPs. However, it remains difficult to avoid significant bias due to the experimental protocol. The DeepRiPe method was recently developed to solve this problem via introducing multi-task or multi-label learning into this field. However, this method has not reached an ideal level of prediction power due to the weak neural network architecture. Results Compared to the DeepRiPe approach, our Multi-resBind method demonstrated substantial improvements using the same large-scale PAR-CLIP dataset with respect to an increase in the area under the receiver operating characteristic curve and average precision. We conducted extensive experiments to evaluate the impact of various types of input data on the final prediction accuracy. The same approach was used to evaluate the effect of loss functions. Finally, a modified integrated gradient was employed to generate attribution maps. The patterns disentangled from relative contributions according to context offer biological insights into the underlying mechanism of protein-RNA interactions. Conclusions Here, we propose Multi-resBind as a new multi-label deep-learning approach to infer protein-RNA binding preferences and predict novel interactions. The results clearly demonstrate that Multi-resBind is a promising tool to predict unknown binding sites in vivo and gain biology insights into why the neural network makes a given prediction.Shitao ZhaoMichiaki HamadaBMCarticleRNA-binding proteinResidual networkMulti-label classificationIntegrated gradientsPhotoactivatable ribonucleoside enhanced cross-linking and immunoprecipitationComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	RNA-binding protein Residual network Multi-label classification Integrated gradients Photoactivatable ribonucleoside enhanced cross-linking and immunoprecipitation Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	RNA-binding protein Residual network Multi-label classification Integrated gradients Photoactivatable ribonucleoside enhanced cross-linking and immunoprecipitation Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Shitao Zhao Michiaki Hamada Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
description	Abstract Background Protein-RNA interactions play key roles in many processes regulating gene expression. To understand the underlying binding preference, ultraviolet cross-linking and immunoprecipitation (CLIP)-based methods have been used to identify the binding sites for hundreds of RNA-binding proteins (RBPs) in vivo. Using these large-scale experimental data to infer RNA binding preference and predict missing binding sites has become a great challenge. Some existing deep-learning models have demonstrated high prediction accuracy for individual RBPs. However, it remains difficult to avoid significant bias due to the experimental protocol. The DeepRiPe method was recently developed to solve this problem via introducing multi-task or multi-label learning into this field. However, this method has not reached an ideal level of prediction power due to the weak neural network architecture. Results Compared to the DeepRiPe approach, our Multi-resBind method demonstrated substantial improvements using the same large-scale PAR-CLIP dataset with respect to an increase in the area under the receiver operating characteristic curve and average precision. We conducted extensive experiments to evaluate the impact of various types of input data on the final prediction accuracy. The same approach was used to evaluate the effect of loss functions. Finally, a modified integrated gradient was employed to generate attribution maps. The patterns disentangled from relative contributions according to context offer biological insights into the underlying mechanism of protein-RNA interactions. Conclusions Here, we propose Multi-resBind as a new multi-label deep-learning approach to infer protein-RNA binding preferences and predict novel interactions. The results clearly demonstrate that Multi-resBind is a promising tool to predict unknown binding sites in vivo and gain biology insights into why the neural network makes a given prediction.
format	article
author	Shitao Zhao Michiaki Hamada
author_facet	Shitao Zhao Michiaki Hamada
author_sort	Shitao Zhao
title	Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
title_short	Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
title_full	Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
title_fullStr	Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
title_full_unstemmed	Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization
title_sort	multi-resbind: a residual network-based multi-label classifier for in vivo rna binding prediction and preference visualization
publisher	BMC
publishDate	2021
url	https://doaj.org/article/ea3391ee6b744fe68c495de855c6b42c
work_keys_str_mv	AT shitaozhao multiresbindaresidualnetworkbasedmultilabelclassifierforinvivornabindingpredictionandpreferencevisualization AT michiakihamada multiresbindaresidualnetworkbasedmultilabelclassifierforinvivornabindingpredictionandpreferencevisualization
_version_	1718419217207787520

Multi-resBind: a residual network-based multi-label classifier for in vivo RNA binding prediction and preference visualization

Ejemplares similares