Enhancing Drug-Target Interaction Predictions Using a Divisive Computational Framework

Abstract:

Computational prediction of drug-target interactions (DTIs) is crucial for drug discovery. However, the sparse distribution of DTIs and the imbalance in the number of interactions among targets pose challenges. This study proposes a divisive computational framework. Firstly, it includes a novel preprocessing algorithm that adjusts the interaction matrix based on the number of interactions of a target and its neighbors, enhancing DTI predictions for targets with fewer interactions. Additionally, a new divisive computational testing method is introduced, which evaluates targets with similar numbers of interactions separately, ensuring that the results are not disproportionately influenced by targets with a large number of interactions. Furthermore, a weighted global testing method is proposed to provide a more comprehensive assessment of the enhanced prediction capabilities, which reduces the negative impact of low-interaction targets on the overall evaluation and offers a more balanced perspective on the algorithm's effectiveness. Experimental results demonstrate the efficacy of the proposed framework, where the means of AUCs in the divisive computational framework are respectively 9.45%, 10.64%, 4.21%, 7.04%, 3.67%, and 6.50% higher than those in the traditional framework on six DTI datasets.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 68)
• Pages: 21-42
• DOI: https://doi.org/10.4028/p-lxM25A
• Online since: June 2025
• Authors: Qing Ye, Ya Xin Sun*
• Keywords: Divisive Computational, Drug Discovery, Drug-Target Interaction, Sample Imbalance, Weighted Evaluation

References

[1] Bin Liu, Jin Wang, Kaiwei Sun, Grigorios Tsoumakas. Fine-grained selective similarity integration for drug–target interaction prediction. Briefings in Bioinformatics, 24(2) 2023 1-12.

DOI: 10.1093/bib/bbad085

[2] Cheng Yan, Guihua Duan, Yayan Zhang, Fang-Xiang Wu, Yi Pan, Jianxin Wang. Predicting drug-drug interactions Based on integrated similarity and semi-Supervised learning. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19(1) (2022) 168-179.

DOI: 10.1109/tcbb.2020.2988018

[3] Eugenio Mazzone, Yves Moreau, Piero Fariselli, Daniele Raimondi. Nonlinear data fusion over entity-relation graphs for drug-target interaction prediction. Bioinformatics, 39(6) (2023) btad348.

DOI: 10.1093/bioinformatics/btad348

[4] Ali Ghanbari Sorkhi, Zahra Abbasi, Majid Iranpour Mobarakeh, Jamshid Pirgazi. Drug-target interaction prediction using unifying of graph regularized nuclear norm with bilinear factorization. BMC Bioinformatics, 22(555) (2021) 1-23.

DOI: 10.1186/s12859-021-04464-2

[5] Donghua Yu, Huawen Liu, Shuang Yao. Drug-target interaction prediction based on improved heterogeneous graph representation learning and feature projection classification. Expert Systems with Application, 252 (2024) 124289.

DOI: 10.1016/j.eswa.2024.124289

[6] Yi Luo, Guihua Duan, Qichang Zhao, Xuehua Bi, Jianxin Wan. DTKGIN: Predicting drug-target interactions based on knowledge graph and intent graph. Methods, 226 (2024) 21–27.

DOI: 10.1016/j.ymeth.2024.04.010

[7] Bin Liu, Konstantinos Pliakos, Celine Vens, Grigorios Tsoumakas. Drug-target interaction prediction via an ensemble of weighted nearest neighbors with interaction recovery. Applied Intelligence, 52(2022) 3705–3727.

DOI: 10.1007/s10489-021-02495-z

[8] Yu Wang, Yu Zhang, Jianchun Wang, Fang Xie, Dequan Zheng, Xiang Zou, Mian Guo, Yijie Ding, Jie Wan, Ke Han. Prediction of drug-target interactions via neural tangent kernel extraction feature matrix factorization model. Computers in Biology and Medicine, 159 (2023) 106955.

DOI: 10.1016/j.compbiomed.2023.106955

[9] Huan Wang, Ruigang Liu, Baijing Wang, Yifan Hong, Ziwen Cui, Qiufen Ni. Multitype perception method for drug-target interaction prediction. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20(6) (2023) 3489-3498.

DOI: 10.1109/tcbb.2023.3285042

[10] Yijie Ding, Jijun Tang, Fei Guo. Identification of drug-target interactions via fuzzy bipartite local model. Neural Computing and Applications, 32(2020) 10303-10309.

DOI: 10.1007/s00521-019-04569-z

[11] Yu Zhang, Qian Liao, Prayag Tiwari, Ying Chu, Yu Wang, Yi Ding, Xianyi Zhao, Jie Wan, Yijie Ding, Ke Han. MvG-NRLMF: Multi-view graph neighborhood regularized logistic matrix factorization for identifying drug–target interaction. Future Generation Computer Systems, 160 (2024) 844–853.

DOI: 10.1016/j.future.2024.06.046

[12] Sangjin Ahn, Si Eun Lee, Mi‑hyun Kim. Random-forest model for drug–target interaction prediction via Kullbeck–Leibler divergence. Journal of Cheminformatics, 14(67) (2022) 1-13.

DOI: 10.21203/rs.3.rs-1357588/v1

[13] Heba Behery, Abdel‑Fattah Attia, Nawal Fishawy, Hanaa Torkey. An ensemble‑based drug–target interaction prediction approach using multiple feature information with data balancing. Journal of Biological Engineering, 16(21) (2022) 1-14.

DOI: 10.1186/s13036-022-00296-7

[14] Konstantinos Pliakos, Celine Vens, Grigorios Tsoumakas. Predicting drug-target interactions with multi-label classification and label partitioning. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(4) (2021) 1596–1607.

DOI: 10.1109/tcbb.2019.2951378

[15] Mohammad Reza Keyvanpour, Yasaman Asghari, Soheila Mehrmolaei. HEnsem_DTIs: A heterogeneous ensemble learning model for drug-target interactions prediction. Chemometrics and Intelligent Laboratory Systems, 253 (2024) 105224.

DOI: 10.1016/j.chemolab.2024.105224

[16] Ali Ezzat, MinWu, Xiao-LiLi, Chee-KeongKwoh. Drug-target interaction prediction using ensemble learning and dimensionality reduction. Methods, 129(1) (2017) 81-88.

DOI: 10.1016/j.ymeth.2017.05.016

[17] Majun Lian, Xinjie Wang, Wenli Du. Drug-target interactions prediction based on network topology feature representation embedded deep forest. Neurocomputing, 551 (2023) 126509.

DOI: 10.1016/j.neucom.2023.126509

[18] Guanyu Qiao, Guohua Wang, Yang Li. Causal enhanced drug-target interaction prediction based on graph generation and multi-source information fusion. Bioinformatics, 40(10) (2024) btae570.

DOI: 10.1093/bioinformatics/btae570

[19] Khandakar Tanvir Ahmed, Md. Istiaq Ansari, Wei Zhang. DTI-LM: language model powered drug–target interaction prediction. Bioinformatics, 40(9) (2024) btae533.

DOI: 10.1093/bioinformatics/btae533

[20] Yang Hua, Zhenhua Feng, Xiaoning Song, Xiao-Jun Wu, Josef Kittler. MMDG-DTI: Drug-target interaction prediction via multimodal feature fusion and domain generalization. Pattern Recognition, 157 (2025) 110887.

DOI: 10.1016/j.patcog.2024.110887

[21] Jingru Wang, Yihang Xiao, Xuequn Shang, Jiajie Peng. Predicting drug-target binding affinity with cross-scale graph contrastive learning. Briefings in Bioinformatics, 25(1) (2024) 1-9.

DOI: 10.1093/bib/bbad516

[22] Qi Zhang, Le Zuo, Ying Ren, Siyuan Wang, Wenfa Wang, Lerong Ma, Jing Zhang, Bisheng Xia. FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug-target interaction prediction. Bioinformatics, 40(6) (2024) btae347.

DOI: 10.1093/bioinformatics/btae347

[23] Yansen Su, Zhiyang Hu, Fei Wang, Yannan Bin, Chunhou Zheng, Haitao Li, Haowen Chen, Xiangxiang Zeng. AMGDTI: drug-target interaction prediction based on adaptive meta-graph learning in heterogeneous network. Briefings in Bioinformatics, 25(1) (2023) 1-11

DOI: 10.1093/bib/bbad474

[24] Youzhi Liu, Linlin Xing, Longbo Zhang, Hongzhen Cai, Maozu Guo. GEFormerDTA: drug target affinity prediction based on transformer graph for early fusion. Scientific Reports, 14(2024) 7416.

DOI: 10.1038/s41598-024-57879-1

[25] Qiao Ning, Yue Wang, Yaomiao Zhao, Jiahao Sun, Lu Jiang, Kaidi Wang, Minghao Yin. DMHGNN: Double multi-view heterogeneous graph neural network framework for drug-target interaction prediction. Artificial Intelligence in Medicine, 159 (2025) 103023.

DOI: 10.1016/j.artmed.2024.103023

[26] Yuxuan Wang, Ying Xia, Junchi Yan, Ye Yuan, Hong-Bin Shen, Xiaoyong Pan. ZeroBind: a protein-specific zero-shot predictor with subgraph matching for drug-target interactions. Nature Communications, 14(2023) 7861.

DOI: 10.1038/s41467-023-43597-1

[27] Yining Xie, Xiaodong Wang, Pengda Wang, Xueyan Bi. A pseudo-label supervised graph fusion attention network for drug-target interaction prediction. Expert Systems with Applications, 259 (2025) 125264.

DOI: 10.1016/j.eswa.2024.125264

[28] Yan Sun, Yan Yi Li, Carson K Leung, Pingzhao Hu. iNGNN-DTI: prediction of drug-target interaction with interpretable nested graph neural network and pretrained molecule models. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 40(3) 2024 1-12.

DOI: 10.1093/bioinformatics/btae135

[29] Mei Li, Xiangrui Cai, Sihan Xu, Hua Ji. Meta path-aggregated heterogeneous graph neural network for drug-target interaction prediction. Briefings in Bioinformatics, 24(1) (2023) 1-17.

DOI: 10.1093/bib/bbac578

[30] Hailong Yang, Yue Chen, Yun Zuo, Zhaohong Deng, Xiaoyong Pan, Hong-Bin Shen, Kup-Sze Choi, Dong-Jun Yu. MINDG: a drug–target interaction prediction method based on an integrated learning algorithm. Bioinformatics, 40(4) (2024)1-8.

DOI: 10.1093/bioinformatics/btae147

[31] Yang Li, Yuan Huang, Zhuhong You, Liping Li, Zheng Wang. MDTips: a multimodal-data-based drug-target interaction prediction system fusing knowledge, gene expression profile, and structural data. Bioinformatics, 39(7) (2023) btad411.

DOI: 10.1093/bioinformatics/btad411

[32] Yang Yue, Shan He. DEDTI versus IEDTI: efficient and predictive models of drug-target interactions. Scientific Reports, 13(2023) 1-18.

DOI: 10.1038/s41598-023-36438-0

[33] Zhimiao Yu, Jiarui Lu, Yuan Jin, and Yang Yang. KenDTI: an ensemble model for predicting drug-target interaction by integrating multi-source information. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(4) (2021) 1305-1314.

DOI: 10.1109/tcbb.2021.3074401

[34] Jehad Aldahdooh, Markus Vähä‑Koskela, Jing Tang, Ziaurrehman Tanoli. Using BERT to identify drug‑target interactions from whole PubMed. Chemometrics and Intelligent Laboratory Systems, 245(23) (2022) 1-13.

DOI: 10.1101/2021.09.10.459845

[35] Ali Ezzat, Min Wu, Xiao-Li Li, Chee-Keong Kwoh. Drug-target interaction prediction via class imbalance-aware ensemble learning. BMC Bioinformatics, 17(19) (2016) 267-276.

DOI: 10.1186/s12859-016-1377-y

[36] Farshid Rayhan, Sajid Ahmed, Swakkhar Shatabda, Dewan Md Farid, Zaynab Mousavian, Abdollah Dehzangi, M. Sohel Rahman. iDTI-ESBoost: identification of drug target interaction using evolutionary and structural features with boosting. Scientific Reports, 7(1) (2017) 17731-17748.

DOI: 10.1038/s41598-017-18025-2

[37] S.M. Hasan Mahmud, Wenyu Chen, Han Meng, Hosney Jahan, Yongsheng Liu S.M. Mamun Hasan. Prediction of drug-target interaction based on protein features using under sampling and feature selection techniques with boosting. Analytical Biochemistry, 589(2020) 1-14.

DOI: 10.1016/j.ab.2019.113507

[38] Shweta Redkar, Sukanta Mondal, Alex Joseph, K. S. Hareesha. Machine learning approach for drug-target interaction prediction using wrapper feature selection and class balancing. Molecular information, 39(5) (2020)1900062.

DOI: 10.1002/minf.201900062

[39] Twan van Laarhoven, Sander B. Nabuurs, Elena Marchiori. Gaussian interaction profile kernels for predicting drug-target interaction. Bioinformatics, 21(2011) 3036-3043.

DOI: 10.1093/bioinformatics/btr500

[40] L. Breiman. Random forests. Machine Learning, 45(1) (2001) 5-32.

[41] Yoshihiro Yamanishi 1, Michihiro Araki, Alex Gutteridge, Wataru Honda, Minoru Kanehisa. Prediction of drug–target interaction networks from the integration of chemical and genomic spaces. Bioinformatics, 24(13) (2008) 1232–1240.

DOI: 10.1093/bioinformatics/btn162

[42] Yasuo Tabei, Edouard Pauwels, Véronique Stoven, Kazuhiro Takemoto, Yoshihiro Yamanishi. Identification of chemogenomic features from drug-target interaction networks using interpretable classifiers. Bioinformatics, 28(18) (2012) i487-i494

DOI: 10.1093/bioinformatics/bts412

[43] David S Wishart, Yannick D Feunang, An C Guo, Elvis J Lo, Ana Marcu, Jason R Grant, Tanvir Sajed, Daniel Johnson, Carin Li, Zinat Sayeeda, Nazanin Assempour, Ithayavani Iynkkaran, Yifeng Liu, Adam Maciejewski, Nicola Gale, Alex Wilson, Lucy Chin, Ryan Cummings, Diana Le, Allison Pon, Craig Knox, Michael Wilson. DrugBank 5.0: a major update to the drugBank database for 2018. Nucleic Acids Research, 46(D1) (2011) D1074-D1082.

DOI: 10.1093/nar/gkx1037

[44] Chun Wei Yap. PaDEL-descriptor: An open-source software to calculate molecular descriptors and fingerprints. Journal of Computational Chemistry, 32(7) (2011) 1466-1474.

DOI: 10.1002/jcc.21707

[45] Peng Zhang, Lin Tao, Xian Zeng, Chu Qin, Shangying Chen, Feng Zhu, Sheng Yong Yang, Zerong Li, Weiping Chen, Yu Zong Chen. PROFEAT update: a protein features web server with added facility to compute network descriptors for studying omics-derived networks. Journal of Molecular Biology, 423(3) (2017) 416-425.

DOI: 10.1016/j.jmb.2016.10.013

[46] Twan van Laarhoven, Elena Marchiori. Predicting drug-target interactions for new drug compounds using a weighted nearest neighbor profile. PloS one, 8(6) (2013) e66952.

DOI: 10.1371/journal.pone.0066952

[47] Feixiong Cheng, Chuang Liu, Jing Jiang, Weiqiang Lu, Weihua Li, Guixia Liu, Weixing Zhou, Jin Huang, Yun Tang. Prediction of drug-target interactions and drug repositioning via network-based inference. PLoS computational biology, 8(5) (2012) e1002503

DOI: 10.1371/journal.pcbi.1002503