DTIP-TC2A: An analytical framework for drug-target interactions prediction methods

被引:3
作者
Keyvanpour, Mohammad Reza [1 ]
Haddadi, Faraneh [1 ]
Mehrmolaei, Soheila [2 ]
机构
[1] Alzahra Univ, Fac Engn, Dept Comp Engn, Tehran, Iran
[2] Alzahra Univ, Fac Engn, Dept Comp Engn, Data Min Lab, Tehran, Iran
关键词
Drug-target interactions; Challenge; Qualitative evaluation; Drug discovery; Biological network analysis; DTIP; MATRIX FACTORIZATION; INTERACTION NETWORKS; PROTEIN-SEQUENCE; IDENTIFICATION;
D O I
10.1016/j.compbiolchem.2022.107707
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Identifying drug-target interactions through computational methods is raised an important and key step in the process of drug discovery and drug-oriented research during the last years. In addition to the advantages of existing computational methods, there are also challenges that affect methods' efficiency and provide obstacles in the direction of developing these computational methods. However, the literature suffers from lacking a comprehensive and comparative analysis concerning drug-target interactions prediction (DTIP) focusing on the analysis of technical and challenging aspects. It seems necessary to provide a comparative perspective and a different analysis on a macro level due to the importance of the DTIP problem. In this paper, we presented the quadruple framework of analytical, named DTIP-TC2A consists of four main components for DTIP. The first component, categorizing DTIP methods based on the technical aspect ahead and investigating the strengths and weaknesses of different DTIP methods. Second, classify DTIP challenges with a major focus on a well-organized and coherent investigation of challenges and presenting a macro view of the DTIP challenges by systematic identification of them. Third, recommending some general criteria to analyze DTIP methods in form of the proposed classifications. Suggesting a suitable set of qualitative criteria along with using quantitative criteria can lead to a more proper choice of DTIP methods. Fourth, performing a two-phase qualitative analysis and comparison between each class of DTIP approaches based on the proposed functional criteria and the identified challenges ahead in order to understand the superiority of each class of DTIP methods over the other class. We believed that the DTIP-TC2A framework can offer a proper context for efficient selection of DTIP methods, improving the efficiency of a DTIP system due to the nature of computational methods, upgrading DTIP methods by removing the barriers, and presenting new directions of research for further studies through systematic identification of DTIP challenges and purposeful evaluation of challenges and methods.
引用
收藏
页数:26
相关论文
共 50 条
[41]   Predicting drug-target interactions using restricted Boltzmann machines [J].
Wang, Yuhao ;
Zeng, Jianyang .
BIOINFORMATICS, 2013, 29 (13) :126-134
[42]   PreDTIs: prediction of drug-target interactions based on multiple feature information using gradient boosting framework with data balancing and feature selection techniques [J].
Mahmud, S. M. Hasan ;
Chen, Wenyu ;
Liu, Yongsheng ;
Awal, Md Abdul ;
Ahmed, Kawsar ;
Rahman, Md Habibur ;
Moni, Mohammad Ali .
BRIEFINGS IN BIOINFORMATICS, 2021, 22 (05)
[43]   GEFA: Early Fusion Approach in Drug-Target Affinity Prediction [J].
Tri Minh Nguyen ;
Thin Nguyen ;
Thao Minh Le ;
Truyen Tran .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2022, 19 (02) :718-728
[44]   A heterogeneous network embedding framework for predicting similarity-based drug-target interactions [J].
An, Qi ;
Yu, Liang .
BRIEFINGS IN BIOINFORMATICS, 2021, 22 (06)
[45]   Current status and future prospects of drug-target interaction prediction [J].
Ru, Xiaoqing ;
Ye, Xiucai ;
Sakurai, Tetsuya ;
Zou, Quan ;
Xu, Lei ;
Lin, Chen .
BRIEFINGS IN FUNCTIONAL GENOMICS, 2021, 20 (05) :312-322
[46]   Dimensionality reduction based multi-kernel framework for drug-target interaction prediction [J].
Mahmud, S. M. Hasan ;
Chen, Wenyu ;
Jahan, Hosney ;
Liu, Yougsheng ;
Hasan, S. M. Mamun .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2021, 212
[47]   A unified drug-target interaction prediction framework based on knowledge graph and recommendation system [J].
Ye, Qing ;
Hsieh, Chang-Yu ;
Yang, Ziyi ;
Kang, Yu ;
Chen, Jiming ;
Cao, Dongsheng ;
He, Shibo ;
Hou, Tingjun .
NATURE COMMUNICATIONS, 2021, 12 (01)
[48]   Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework [J].
Yamanishi, Yoshihiro ;
Kotera, Masaaki ;
Kanehisa, Minoru ;
Goto, Susumu .
BIOINFORMATICS, 2010, 26 (12) :i246-i254
[49]   Drug-target interactions prediction via graph isomorphic network and cyclic training method [J].
Du, Yuhong ;
Yao, Yabing ;
Tang, Jianxin ;
Zhao, Zhili ;
Gou, Zhuoyue .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 249
[50]   Large-scale prediction of drug-target interactions using protein sequences and drug topological structures [J].
Cao, Dong-Sheng ;
Liu, Shao ;
Xu, Qing-Song ;
Lu, Hong-Mei ;
Huang, Jian-Hua ;
Hu, Qian-Nan ;
Liang, Yi-Zeng .
ANALYTICA CHIMICA ACTA, 2012, 752 :1-10