• Home
  • Search
  • A Denoising Adversarial Model Based on Hyperellipsoidal Knowledge Representation Learning for DTI Prediction.
  • https://doi.org/10.1109/tcbbio.2026.3710670Copy DOI Icon

A Denoising Adversarial Model Based on Hyperellipsoidal Knowledge Representation Learning for DTI Prediction.

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

The prediction of drug-target interactions (DTI) is of critical importance in the field of drug discovery. Knowledge representation learning is commonly used to embed high-dimensional, sparse drug knowledge graphs into low-dimensional, dense vector spaces. Existing methods primarily rely on node features of drug knowledge graphs, which often neglect inherent biases introduced by network characteristics, such as noise, long-tail distribution, data sparsity, and complex relations (1-N, N-1, N-N). This oversight leads to incomplete semantic representation of knowledge graphs during the embedding process, thereby resulting in suboptimal DTI prediction performance. To address these challenges, we propose a novel model termed DAH-DTI, which comprises four components: knowledge graph denoising, high-quality negative sample generation, hyperellipsoid knowledge graph embedding based on Mahalanobis distance, and DTI link prediction. Specifically, the knowledge graph is first denoised to filter out noisy triples and obtain a high-quality gold dataset. Subsequently, adversarial negative sampling is incorporated during pre-training to moderately expand the number of triples. Next, the tail entities of the triples are embedded into a predefined hyperellipsoid for model training. Finally, the trained model is applied to all potential unknown drug-target pairs through link prediction to predict potential DTIs. Experimental results demonstrate that by effectively addressing challenges including data noise, long-tail distribution, data sparsity, and complex relations. The DAH-DTI achieves significant improvements in ACCU, REC, MRR, and Hit@10 on a multi-level phenotype-drug-molecular knowledge graph. Furthermore, molecular docking simulations validate the reliability of DAH-DTI predictions for DTI involving the AR target. In summary, DAH-DTI provides a promising approach to mitigate inherent biases caused by network characteristics and accurately predict potential drug-target interactions.

Similar Papers
  • Preprint Article

DTI-LM: Language model powered drug-target ​ interaction prediction​

  • Nov 30, 2023
  • Faculty of 1000 Research Ltd
  • Khandakar Tanvir Ahmed +1
  • PDF
  • Research Article
  • Citations127

Link prediction in drug-target interactions network using similarity indices

  • Jan 17, 2017
  • BMC Bioinformatics
  • Yiding Lu +2
  • Research Article
  • Citations1

Drug-Target Interaction Prediction via Deep Multimodal Graph and Structural Learning.

  • Jul 15, 2024
  • Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
  • Haorun Li +1
  • Conference Article
  • Citations1

Drug Target Interaction Prediction with Non-random Missing Labels

  • Dec 01, 2018
  • Sheng Ni +3
  • Research Article

IPM-DTI: An Interaction-Pattern-Driven Multimodal Framework for Drug-Target Interaction Prediction via Knowledge Graphs.

  • Jun 09, 2026
  • Journal of chemical information and modeling
  • Yao Liu +3
  • Research Article
  • Citations93

DTI-HETA: prediction of drug-target interactions based on GCN and GAT on heterogeneous graph.

  • Apr 04, 2022
  • Briefings in Bioinformatics
  • Kanghao Shao +5
  • Research Article
  • Citations225

Discovering protein drug targets using knowledge graph embeddings.

  • Aug 01, 2019
  • Bioinformatics
  • Sameh K Mohamed +2
  • Research Article
  • Citations5

Drug-target interaction prediction using reliable negative samples and effective feature selection methods

  • Jun 20, 2022
  • Journal of Pharmacological and Toxicological Methods
  • Mohammad Morovvati Sharifabad +2
  • PDF
  • Research Article
  • Citations246

A unified drug\u2013target interaction prediction framework based on knowledge graph and recommendation system

  • Nov 22, 2021
  • Nature Communications
  • Qing Ye +7
  • Dissertation
  • Citations2

Challenges and solutions in drug-target interaction prediction

  • Jan 01, 2018
  • Ali Ezzat
  • Research Article
  • Citations35

DeepStack-DTIs: Predicting Drug–Target Interactions Using LightGBM Feature Selection and Deep-Stacked Ensemble Classifier

  • Nov 03, 2021
  • Interdisciplinary Sciences: Computational Life Sciences
  • Yan Zhang +5
  • PDF
  • Research Article
  • Citations13

Drug–Target Interaction Prediction Model Using Optimal Recurrent Neural Network

  • Jan 01, 2023
  • Intelligent Automation & Soft Computing
  • G Kavipriya +1
  • Conference Article
  • Citations1

Negative Sampling in Knowledge Representation Learning: A Mini-Review

  • Nov 28, 2020
  • Jing Qian +3
  • Research Article
  • Citations3

CBKG-DTI: Multi-Level Knowledge Distillation and Biomedical Knowledge Graph for Drug-Target Interaction Prediction.

  • Jan 01, 2025
  • IEEE journal of biomedical and health informatics
  • Xiaosa Zhao +5
  • PDF
  • Research Article
  • Citations19

Novel drug-target interactions via link prediction and network embedding

  • Apr 04, 2022
  • BMC Bioinformatics
  • E Amiri Souri +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.