Learning from low-rank multimodal representations for predicting disease-drug associations

Abstract Background Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuabl...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pengwei Hu, Yu-an Huang, Jing Mei, Henry Leung, Zhan-heng Chen, Ze-min Kuang, Zhu-hong You, Lun Hu
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Disease-drug associations prediction Low-rank tensors Multimodal fusion Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/5ff8c9e48d6041029f17dc26c75b30c0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5ff8c9e48d6041029f17dc26c75b30c0
record_format	dspace
spelling	oai:doaj.org-article:5ff8c9e48d6041029f17dc26c75b30c02021-11-08T10:59:20ZLearning from low-rank multimodal representations for predicting disease-drug associations10.1186/s12911-021-01648-x1472-6947https://doaj.org/article/5ff8c9e48d6041029f17dc26c75b30c02021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01648-xhttps://doaj.org/toc/1472-6947Abstract Background Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuable associations, it would be useful to develop computational methods for predicting unobserved disease-drug associations. With the advent of various datasets describing diseases and drugs, it has become more feasible to build a model describing the potential correlation between disease and drugs. Results In this work, we propose a new prediction method, called LMFDA, which works in several stages. First, it studies the drug chemical structure, disease MeSH descriptors, disease-related phenotypic terms, and drug-drug interactions. On this basis, similarity networks of different sources are constructed to enrich the representation of drugs and diseases. Based on the fused disease similarity network and drug similarity network, LMFDA calculated the association score of each pair of diseases and drugs in the database. This method achieves good performance on Fdataset and Cdataset, AUROCs were 91.6% and 92.1% respectively, higher than many of the existing computational models. Conclusions The novelty of LMFDA lies in the introduction of multimodal fusion using low-rank tensors to fuse multiple similar networks and combine matrix complement technology to predict potential association. We have demonstrated that LMFDA can display excellent network integration ability for accurate disease-drug association inferring and achieve substantial improvement over the advanced approach. Overall, experimental results on two real-world networks dataset demonstrate that LMFDA able to delivers an excellent detecting performance. Results also suggest that perfecting similar networks with as much domain knowledge as possible is a promising direction for drug repositioning.Pengwei HuYu-an HuangJing MeiHenry LeungZhan-heng ChenZe-min KuangZhu-hong YouLun HuBMCarticleDisease-drug associations predictionLow-rank tensorsMultimodal fusionComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss S1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Disease-drug associations prediction Low-rank tensors Multimodal fusion Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Disease-drug associations prediction Low-rank tensors Multimodal fusion Computer applications to medicine. Medical informatics R858-859.7 Pengwei Hu Yu-an Huang Jing Mei Henry Leung Zhan-heng Chen Ze-min Kuang Zhu-hong You Lun Hu Learning from low-rank multimodal representations for predicting disease-drug associations
description	Abstract Background Disease-drug associations provide essential information for drug discovery and disease treatment. Many disease-drug associations remain unobserved or unknown, and trials to confirm these associations are time-consuming and expensive. To better understand and explore these valuable associations, it would be useful to develop computational methods for predicting unobserved disease-drug associations. With the advent of various datasets describing diseases and drugs, it has become more feasible to build a model describing the potential correlation between disease and drugs. Results In this work, we propose a new prediction method, called LMFDA, which works in several stages. First, it studies the drug chemical structure, disease MeSH descriptors, disease-related phenotypic terms, and drug-drug interactions. On this basis, similarity networks of different sources are constructed to enrich the representation of drugs and diseases. Based on the fused disease similarity network and drug similarity network, LMFDA calculated the association score of each pair of diseases and drugs in the database. This method achieves good performance on Fdataset and Cdataset, AUROCs were 91.6% and 92.1% respectively, higher than many of the existing computational models. Conclusions The novelty of LMFDA lies in the introduction of multimodal fusion using low-rank tensors to fuse multiple similar networks and combine matrix complement technology to predict potential association. We have demonstrated that LMFDA can display excellent network integration ability for accurate disease-drug association inferring and achieve substantial improvement over the advanced approach. Overall, experimental results on two real-world networks dataset demonstrate that LMFDA able to delivers an excellent detecting performance. Results also suggest that perfecting similar networks with as much domain knowledge as possible is a promising direction for drug repositioning.
format	article
author	Pengwei Hu Yu-an Huang Jing Mei Henry Leung Zhan-heng Chen Ze-min Kuang Zhu-hong You Lun Hu
author_facet	Pengwei Hu Yu-an Huang Jing Mei Henry Leung Zhan-heng Chen Ze-min Kuang Zhu-hong You Lun Hu
author_sort	Pengwei Hu
title	Learning from low-rank multimodal representations for predicting disease-drug associations
title_short	Learning from low-rank multimodal representations for predicting disease-drug associations
title_full	Learning from low-rank multimodal representations for predicting disease-drug associations
title_fullStr	Learning from low-rank multimodal representations for predicting disease-drug associations
title_full_unstemmed	Learning from low-rank multimodal representations for predicting disease-drug associations
title_sort	learning from low-rank multimodal representations for predicting disease-drug associations
publisher	BMC
publishDate	2021
url	https://doaj.org/article/5ff8c9e48d6041029f17dc26c75b30c0
work_keys_str_mv	AT pengweihu learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT yuanhuang learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT jingmei learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT henryleung learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT zhanhengchen learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT zeminkuang learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT zhuhongyou learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations AT lunhu learningfromlowrankmultimodalrepresentationsforpredictingdiseasedrugassociations
_version_	1718442428950642688

Learning from low-rank multimodal representations for predicting disease-drug associations

Ejemplares similares