Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information
Interactions between drugs and target proteins provide important information for the drug discovery. Currently, experiments identified only a small number of drug-target interactions. Therefore, the development of computational methods for drug-target interaction prediction is an urgent task of theo...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-11-01
|
Series: | Molecules |
Subjects: | |
Online Access: | https://www.mdpi.com/1420-3049/22/12/2056 |
id |
doaj-d7e33a57aae042699d96362ac5dbca0b |
---|---|
record_format |
Article |
spelling |
doaj-d7e33a57aae042699d96362ac5dbca0b2020-11-24T21:14:31ZengMDPI AGMolecules1420-30492017-11-012212205610.3390/molecules22122056molecules22122056Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood InformationWen Zhang0Yanlin Chen1Dingfang Li2School of Computer, Wuhan University, Wuhan 430072, ChinaSchool of Mathematics and Statistics, Wuhan University, Wuhan 430072, ChinaSchool of Mathematics and Statistics, Wuhan University, Wuhan 430072, ChinaInteractions between drugs and target proteins provide important information for the drug discovery. Currently, experiments identified only a small number of drug-target interactions. Therefore, the development of computational methods for drug-target interaction prediction is an urgent task of theoretical interest and practical significance. In this paper, we propose a label propagation method with linear neighborhood information (LPLNI) for predicting unobserved drug-target interactions. Firstly, we calculate drug-drug linear neighborhood similarity in the feature spaces, by considering how to reconstruct data points from neighbors. Then, we take similarities as the manifold of drugs, and assume the manifold unchanged in the interaction space. At last, we predict unobserved interactions between known drugs and targets by using drug-drug linear neighborhood similarity and known drug-target interactions. The experiments show that LPLNI can utilize only known drug-target interactions to make high-accuracy predictions on four benchmark datasets. Furthermore, we consider incorporating chemical structures into LPLNI models. Experimental results demonstrate that the model with integrated information (LPLNI-II) can produce improved performances, better than other state-of-the-art methods. The known drug-target interactions are an important information source for computational predictions. The usefulness of the proposed method is demonstrated by cross validation and the case study.https://www.mdpi.com/1420-3049/22/12/2056drug-target interactionslabel propagationlinear neighborhoodintegrated information |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wen Zhang Yanlin Chen Dingfang Li |
spellingShingle |
Wen Zhang Yanlin Chen Dingfang Li Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information Molecules drug-target interactions label propagation linear neighborhood integrated information |
author_facet |
Wen Zhang Yanlin Chen Dingfang Li |
author_sort |
Wen Zhang |
title |
Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information |
title_short |
Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information |
title_full |
Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information |
title_fullStr |
Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information |
title_full_unstemmed |
Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information |
title_sort |
drug-target interaction prediction through label propagation with linear neighborhood information |
publisher |
MDPI AG |
series |
Molecules |
issn |
1420-3049 |
publishDate |
2017-11-01 |
description |
Interactions between drugs and target proteins provide important information for the drug discovery. Currently, experiments identified only a small number of drug-target interactions. Therefore, the development of computational methods for drug-target interaction prediction is an urgent task of theoretical interest and practical significance. In this paper, we propose a label propagation method with linear neighborhood information (LPLNI) for predicting unobserved drug-target interactions. Firstly, we calculate drug-drug linear neighborhood similarity in the feature spaces, by considering how to reconstruct data points from neighbors. Then, we take similarities as the manifold of drugs, and assume the manifold unchanged in the interaction space. At last, we predict unobserved interactions between known drugs and targets by using drug-drug linear neighborhood similarity and known drug-target interactions. The experiments show that LPLNI can utilize only known drug-target interactions to make high-accuracy predictions on four benchmark datasets. Furthermore, we consider incorporating chemical structures into LPLNI models. Experimental results demonstrate that the model with integrated information (LPLNI-II) can produce improved performances, better than other state-of-the-art methods. The known drug-target interactions are an important information source for computational predictions. The usefulness of the proposed method is demonstrated by cross validation and the case study. |
topic |
drug-target interactions label propagation linear neighborhood integrated information |
url |
https://www.mdpi.com/1420-3049/22/12/2056 |
work_keys_str_mv |
AT wenzhang drugtargetinteractionpredictionthroughlabelpropagationwithlinearneighborhoodinformation AT yanlinchen drugtargetinteractionpredictionthroughlabelpropagationwithlinearneighborhoodinformation AT dingfangli drugtargetinteractionpredictionthroughlabelpropagationwithlinearneighborhoodinformation |
_version_ |
1716746968136417280 |