DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning

Abstract Drug–target interaction (DTI) prediction is a crucial step in drug discovery and repositioning as it reduces experimental validation costs if done right. Thus, developing in-silico methods to predict potential DTI has become a competitive research niche, with one of its main focuses being i...

Full description

Bibliographic Details
Main Authors: Maha A. Thafar, Rawan S. Olayan, Somayah Albaradei, Vladimir B. Bajic, Takashi Gojobori, Magbubah Essack, Xin Gao
Format: Article
Language:English
Published: BMC 2021-09-01
Series:Journal of Cheminformatics
Subjects:
Online Access:https://doi.org/10.1186/s13321-021-00552-w
id doaj-df451b2b7c4e484fab56585276a745fd
record_format Article
spelling doaj-df451b2b7c4e484fab56585276a745fd2021-09-26T11:43:51ZengBMCJournal of Cheminformatics1758-29462021-09-0113111810.1186/s13321-021-00552-wDTi2Vec: Drug–target interaction prediction using network embedding and ensemble learningMaha A. Thafar0Rawan S. Olayan1Somayah Albaradei2Vladimir B. Bajic3Takashi Gojobori4Magbubah Essack5Xin Gao6Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)The Jackson Laboratory for Genomic MedicineComputer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center, Computer (CBRC), King Abdullah University of Science and Technology (KAUST)Abstract Drug–target interaction (DTI) prediction is a crucial step in drug discovery and repositioning as it reduces experimental validation costs if done right. Thus, developing in-silico methods to predict potential DTI has become a competitive research niche, with one of its main focuses being improving the prediction accuracy. Using machine learning (ML) models for this task, specifically network-based approaches, is effective and has shown great advantages over the other computational methods. However, ML model development involves upstream hand-crafted feature extraction and other processes that impact prediction accuracy. Thus, network-based representation learning techniques that provide automated feature extraction combined with traditional ML classifiers dealing with downstream link prediction tasks may be better-suited paradigms. Here, we present such a method, DTi2Vec, which identifies DTIs using network representation learning and ensemble learning techniques. DTi2Vec constructs the heterogeneous network, and then it automatically generates features for each drug and target using the nodes embedding technique. DTi2Vec demonstrated its ability in drug–target link prediction compared to several state-of-the-art network-based methods, using four benchmark datasets and large-scale data compiled from DrugBank. DTi2Vec showed a statistically significant increase in the prediction performances in terms of AUPR. We verified the "novel" predicted DTIs using several databases and scientific literature. DTi2Vec is a simple yet effective method that provides high DTI prediction performance while being scalable and efficient in computation, translating into a powerful drug repositioning tool.https://doi.org/10.1186/s13321-021-00552-wDrug repositioningDrug–target interactionHeterogeneous networkNetwork embeddingRandom walkLink prediction
collection DOAJ
language English
format Article
sources DOAJ
author Maha A. Thafar
Rawan S. Olayan
Somayah Albaradei
Vladimir B. Bajic
Takashi Gojobori
Magbubah Essack
Xin Gao
spellingShingle Maha A. Thafar
Rawan S. Olayan
Somayah Albaradei
Vladimir B. Bajic
Takashi Gojobori
Magbubah Essack
Xin Gao
DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
Journal of Cheminformatics
Drug repositioning
Drug–target interaction
Heterogeneous network
Network embedding
Random walk
Link prediction
author_facet Maha A. Thafar
Rawan S. Olayan
Somayah Albaradei
Vladimir B. Bajic
Takashi Gojobori
Magbubah Essack
Xin Gao
author_sort Maha A. Thafar
title DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
title_short DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
title_full DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
title_fullStr DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
title_full_unstemmed DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning
title_sort dti2vec: drug–target interaction prediction using network embedding and ensemble learning
publisher BMC
series Journal of Cheminformatics
issn 1758-2946
publishDate 2021-09-01
description Abstract Drug–target interaction (DTI) prediction is a crucial step in drug discovery and repositioning as it reduces experimental validation costs if done right. Thus, developing in-silico methods to predict potential DTI has become a competitive research niche, with one of its main focuses being improving the prediction accuracy. Using machine learning (ML) models for this task, specifically network-based approaches, is effective and has shown great advantages over the other computational methods. However, ML model development involves upstream hand-crafted feature extraction and other processes that impact prediction accuracy. Thus, network-based representation learning techniques that provide automated feature extraction combined with traditional ML classifiers dealing with downstream link prediction tasks may be better-suited paradigms. Here, we present such a method, DTi2Vec, which identifies DTIs using network representation learning and ensemble learning techniques. DTi2Vec constructs the heterogeneous network, and then it automatically generates features for each drug and target using the nodes embedding technique. DTi2Vec demonstrated its ability in drug–target link prediction compared to several state-of-the-art network-based methods, using four benchmark datasets and large-scale data compiled from DrugBank. DTi2Vec showed a statistically significant increase in the prediction performances in terms of AUPR. We verified the "novel" predicted DTIs using several databases and scientific literature. DTi2Vec is a simple yet effective method that provides high DTI prediction performance while being scalable and efficient in computation, translating into a powerful drug repositioning tool.
topic Drug repositioning
Drug–target interaction
Heterogeneous network
Network embedding
Random walk
Link prediction
url https://doi.org/10.1186/s13321-021-00552-w
work_keys_str_mv AT mahaathafar dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT rawansolayan dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT somayahalbaradei dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT vladimirbbajic dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT takashigojobori dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT magbubahessack dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
AT xingao dti2vecdrugtargetinteractionpredictionusingnetworkembeddingandensemblelearning
_version_ 1716867816919924736