UnbiasedDTI: Mitigating Real-World Bias of Drug-Target Interaction Prediction by Using Deep Ensemble-Balanced Learning

被引:9
作者
Tayebi, Aida [1 ]
Yousefi, Niloofar [1 ]
Yazdani-Jahromi, Mehdi [1 ]
Kolanthai, Elayaraja [2 ]
Neal, Craig J. [2 ]
Seal, Sudipta [2 ,3 ]
Garibay, Ozlem Ozmen [1 ]
机构
[1] Univ Cent Florida, Dept Ind Engn & Management Syst, Orlando, FL 32816 USA
[2] Univ Cent Florida, Adv Mat Proc & Anal Ctr, Dept Mat Sci & Engn, Orlando, FL 32816 USA
[3] Univ Cent Florida, Coll Med, Bionix Cluster, Orlando, FL 32816 USA
来源
MOLECULES | 2022年 / 27卷 / 09期
关键词
drug-target interaction; ensemble learning; deep learning; machine learning; spike protein; SARS-CoV-2; ACE2; receptor; IDENTIFICATION; EVOLUTIONARY;
D O I
10.3390/molecules27092980
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Drug-target interaction (DTI) prediction through in vitro methods is expensive and time-consuming. On the other hand, computational methods can save time and money while enhancing drug discovery efficiency. Most of the computational methods frame DTI prediction as a binary classification task. One important challenge is that the number of negative interactions in all DTI-related datasets is far greater than the number of positive interactions, leading to the class imbalance problem. As a result, a classifier is trained biased towards the majority class (negative class), whereas the minority class (interacting pairs) is of interest. This class imbalance problem is not widely taken into account in DTI prediction studies, and the few previous studies considering balancing in DTI do not focus on the imbalance issue itself. Additionally, they do not benefit from deep learning models and experimental validation. In this study, we propose a computational framework along with experimental validations to predict drug-target interaction using an ensemble of deep learning models to address the class imbalance problem in the DTI domain. The objective of this paper is to mitigate the bias in the prediction of DTI by focusing on the impact of balancing and maintaining other involved parameters at a constant value. Our analysis shows that the proposed model outperforms unbalanced models with the same architecture trained on the BindingDB both computationally and experimentally. These findings demonstrate the significance of balancing, which reduces the bias towards the negative class and leads to better performance. It is important to note that leaning on computational results without experimentally validating them and by relying solely on AUROC and AUPRC metrics is not credible, particularly when the testing set remains unbalanced.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Drug-target interaction prediction with deep learning
    YANG Shuo
    LI Shi-liang
    LI Hong-lin
    中国药理学与毒理学杂志, 2019, (10) : 855 - 855
  • [2] Drug-target interaction prediction using ensemble learning and dimensionality reduction
    Ezzat, Ali
    Wu, Min
    Li, Xiao-Li
    Kwoh, Chee-Keong
    METHODS, 2017, 129 : 81 - 88
  • [3] Comparative Studies on Resampling Techniques in Machine Learning and Deep Learning Models for Drug-Target Interaction Prediction
    Azlim Khan, Azwaar Khan
    Ahamed Hassain Malim, Nurul Hashimah
    MOLECULES, 2023, 28 (04):
  • [4] Drug-target interaction prediction using semi-bipartite graph model and deep learning
    Eslami Manoochehri, Hafez
    Nourani, Mehrdad
    BMC BIOINFORMATICS, 2020, 21 (Suppl 4)
  • [5] Drug-Target Interaction Prediction: End-to-End Deep Learning Approach
    Monteiro, Nelson R. C.
    Ribeiro, Bernardete
    Arrais, Joel P.
    IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2021, 18 (06) : 2364 - 2374
  • [6] NegStacking: Drug-Target Interaction Prediction Based on Ensemble Learning and Logistic Regression
    Yang, Jie
    He, Song
    Zhang, Zhongnan
    Bo, Xiaochen
    IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2021, 18 (06) : 2624 - 2634
  • [7] Drug-target interaction prediction with a deep-learning-based model
    Xie, Lingwei
    Zhang, Zhongnan
    He, Song
    Bo, Xiaochen
    Song, Xinyu
    2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2017, : 469 - 476
  • [8] Deep-Learning-Based Drug-Target Interaction Prediction
    Wen, Ming
    Zhang, Zhimin
    Niu, Shaoyu
    Sha, Haozhi
    Yang, Ruihan
    Yun, Yonghuan
    Lu, Hongmei
    JOURNAL OF PROTEOME RESEARCH, 2017, 16 (04) : 1401 - 1409
  • [9] Drug-target interaction prediction using semi-bipartite graph model and deep learning
    Hafez Eslami Manoochehri
    Mehrdad Nourani
    BMC Bioinformatics, 21
  • [10] DTi2Vec: Drug-target interaction prediction using network embedding and ensemble learning
    Thafar, Maha A.
    Olayan, Rawan S.
    Albaradei, Somayah
    Bajic, Vladimir B.
    Gojobori, Takashi
    Essack, Magbubah
    Gao, Xin
    JOURNAL OF CHEMINFORMATICS, 2021, 13 (01)