SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction
Abstract Background The experimental verification of a drug discovery process is expensive and time-consuming. Therefore, efficiently and effectively identifying drug–target interactions (DTIs) has been the focus of research. At present, many machine learning algorithms are used for predicting DTIs....
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-02-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12859-023-05153-y |
_version_ | 1811171526612877312 |
---|---|
author | Lingzhi Hu Chengzhou Fu Zhonglu Ren Yongming Cai Jin Yang Siwen Xu Wenhua Xu Deyu Tang |
author_facet | Lingzhi Hu Chengzhou Fu Zhonglu Ren Yongming Cai Jin Yang Siwen Xu Wenhua Xu Deyu Tang |
author_sort | Lingzhi Hu |
collection | DOAJ |
description | Abstract Background The experimental verification of a drug discovery process is expensive and time-consuming. Therefore, efficiently and effectively identifying drug–target interactions (DTIs) has been the focus of research. At present, many machine learning algorithms are used for predicting DTIs. The key idea is to train the classifier using an existing DTI to predict a new or unknown DTI. However, there are various challenges, such as class imbalance and the parameter optimization of many classifiers, that need to be solved before an optimal DTI model is developed. Methods In this study, we propose a framework called SSELM-neg for DTI prediction, in which we use a screening approach to choose high-quality negative samples and a spherical search approach to optimize the parameters of the extreme learning machine. Results The results demonstrated that the proposed technique outperformed other state-of-the-art methods in 10-fold cross-validation experiments in terms of the area under the receiver operating characteristic curve (0.986, 0.993, 0.988, and 0.969) and AUPR (0.982, 0.991, 0.982, and 0.946) for the enzyme dataset, G-protein coupled receptor dataset, ion channel dataset, and nuclear receptor dataset, respectively. Conclusion The screening approach produced high-quality negative samples with the same number of positive samples, which solved the class imbalance problem. We optimized an extreme learning machine using a spherical search approach to identify DTIs. Therefore, our models performed better than other state-of-the-art methods. |
first_indexed | 2024-04-10T17:16:32Z |
format | Article |
id | doaj.art-be68071e775c4f8ab1f05b1a6e0dc4bd |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-10T17:16:32Z |
publishDate | 2023-02-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-be68071e775c4f8ab1f05b1a6e0dc4bd2023-02-05T12:25:37ZengBMCBMC Bioinformatics1471-21052023-02-0124112110.1186/s12859-023-05153-ySSELM-neg: spherical search-based extreme learning machine for drug–target interaction predictionLingzhi Hu0Chengzhou Fu1Zhonglu Ren2Yongming Cai3Jin Yang4Siwen Xu5Wenhua Xu6Deyu Tang7School of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversitySchool of Medical Information Engineering, Guangdong Pharmaceutical UniversityAbstract Background The experimental verification of a drug discovery process is expensive and time-consuming. Therefore, efficiently and effectively identifying drug–target interactions (DTIs) has been the focus of research. At present, many machine learning algorithms are used for predicting DTIs. The key idea is to train the classifier using an existing DTI to predict a new or unknown DTI. However, there are various challenges, such as class imbalance and the parameter optimization of many classifiers, that need to be solved before an optimal DTI model is developed. Methods In this study, we propose a framework called SSELM-neg for DTI prediction, in which we use a screening approach to choose high-quality negative samples and a spherical search approach to optimize the parameters of the extreme learning machine. Results The results demonstrated that the proposed technique outperformed other state-of-the-art methods in 10-fold cross-validation experiments in terms of the area under the receiver operating characteristic curve (0.986, 0.993, 0.988, and 0.969) and AUPR (0.982, 0.991, 0.982, and 0.946) for the enzyme dataset, G-protein coupled receptor dataset, ion channel dataset, and nuclear receptor dataset, respectively. Conclusion The screening approach produced high-quality negative samples with the same number of positive samples, which solved the class imbalance problem. We optimized an extreme learning machine using a spherical search approach to identify DTIs. Therefore, our models performed better than other state-of-the-art methods.https://doi.org/10.1186/s12859-023-05153-yDrug–target interactionsDrug discoveryExtreme learning machineSpherical searchClass imbalance |
spellingShingle | Lingzhi Hu Chengzhou Fu Zhonglu Ren Yongming Cai Jin Yang Siwen Xu Wenhua Xu Deyu Tang SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction BMC Bioinformatics Drug–target interactions Drug discovery Extreme learning machine Spherical search Class imbalance |
title | SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction |
title_full | SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction |
title_fullStr | SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction |
title_full_unstemmed | SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction |
title_short | SSELM-neg: spherical search-based extreme learning machine for drug–target interaction prediction |
title_sort | sselm neg spherical search based extreme learning machine for drug target interaction prediction |
topic | Drug–target interactions Drug discovery Extreme learning machine Spherical search Class imbalance |
url | https://doi.org/10.1186/s12859-023-05153-y |
work_keys_str_mv | AT lingzhihu sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT chengzhoufu sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT zhongluren sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT yongmingcai sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT jinyang sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT siwenxu sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT wenhuaxu sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction AT deyutang sselmnegsphericalsearchbasedextremelearningmachinefordrugtargetinteractionprediction |