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
  • [31] Associative learning mechanism for drug-target interaction prediction
    Zhu, Zhiqin
    Yao, Zheng
    Qi, Guanqiu
    Mazur, Neal
    Yang, Pan
    Cong, Baisen
    CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023, 8 (04) : 1558 - 1577
  • [32] Drug-Target Interaction Prediction in Drug Repositioning Based on Deep Semi-Supervised Learning
    Bahi, Meriem
    Batouche, Mohamed
    COMPUTATIONAL INTELLIGENCE AND ITS APPLICATIONS, 2018, 522 : 302 - 313
  • [33] Predicting Drug-Target Interaction Using Deep Matrix Factorization
    Manoochehri, Hafez Eslami
    Nourani, Mehrdad
    2018 IEEE BIOMEDICAL CIRCUITS AND SYSTEMS CONFERENCE (BIOCAS): ADVANCED SYSTEMS FOR ENHANCING HUMAN HEALTH, 2018, : 551 - 554
  • [34] Identifying potential drug-target interactions based on ensemble deep learning
    Zhou, Liqian
    Wang, Yuzhuang
    Peng, Lihong
    Li, Zejun
    Luo, Xueming
    FRONTIERS IN AGING NEUROSCIENCE, 2023, 15
  • [35] Prediction of Drug-Target Interactions Based on Network Representation Learning and Ensemble Learning
    Xuan, Ping
    Chen, Bingxu
    Zhang, Tiangang
    Yang, Yan
    IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2021, 18 (06) : 2671 - 2681
  • [36] Enhancing drug discovery in schizophrenia: a deep learning approach for accurate drug-target interaction prediction - DrugSchizoNet
    J., Sherine Glory
    P., Durgadevi
    P., Ezhumalai
    COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING, 2025, 28 (02) : 170 - 187
  • [37] An ensemble-based drug-target interaction prediction approach using multiple feature information with data balancing
    El-Behery, Heba
    Attia, Abdel-Fattah
    El-Fishawy, Nawal
    Torkey, Hanaa
    JOURNAL OF BIOLOGICAL ENGINEERING, 2022, 16 (01)
  • [38] Drug-target interaction prediction via an ensemble of weighted nearest neighbors with interaction recovery
    Bin Liu
    Konstantinos Pliakos
    Celine Vens
    Grigorios Tsoumakas
    Applied Intelligence, 2022, 52 : 3705 - 3727
  • [39] An ensemble-based approach using structural feature extraction method with class imbalance handling technique for drug-target interaction prediction
    Arjun Puri
    Manoj Kumar Gupta
    Kanica Sachdev
    Multimedia Tools and Applications, 2022, 81 : 37499 - 37517
  • [40] SS-DTI: A deep learning method integrating semantic and structural information for drug-target interaction prediction
    Chun, Yujie
    Li, Huaihu
    Wang, Shunfang
    JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY, 2025, 23 (01)