CoChat

HiGLDP: a hierarchical graph neural network for predicting lncRNA-disease associations through multi-omic integration

Open access
Wang, Yongtian, Wang, Zhiyuan, Wang, Tao, Hu, Jialu, You, Zhuhong, Peng, Jiajie · 2026 · BMC Biology

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

Background: Long noncoding RNAs (lncRNAs) have emerged as crucial regulators in the pathogenesis of complex human diseases. Despite significant advances, identifying disease-associated lncRNAs remains challenging due to the vast noncoding transcriptome and the complexity of lncRNA interaction networks. Results: We propose HiGLDP, a computational framework for predicting lncRNA-disease associations through the integration of multi-omic data and advanced graph neural network techniques. HiGLDP constructs comprehensive similarity networks for lncRNAs and diseases using genomic, transcriptomic, and proteomic information, which are refined using random walk with restart (RWR) and denoising autoencoders (DAE). The bipartite lncRNA-disease association network is transformed into an interconnected graph with relationship nodes, while an association feature graph is constructed based on cosine similarity. A hybrid graph neural network architecture combining graph convolutional networks (GCN) and graph attention networks (GAT) is employed to capture both local and global graph structures, followed by a multilayer perceptron (MLP) for association classification. Comprehensive evaluations demonstrate that HiGLDP achieves superior predictive performance, accuracy, and robustness compared with existing methods. Case studies further validate its effectiveness in identifying novel lncRNA-disease associations. Conclusions: HiGLDP provides a robust and interpretable computational framework for lncRNA-disease association prediction. By integrating multi-omic information with hybrid graph learning, it offers valuable insights into lncRNA-disease interactions and represents a meaningful advancement in predictive modeling in this field.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s12915-026-02557-z

Cites

Statistics

Figures

Fig. 1 Overview of the HiGLDP model for predicting lncRNA-disease associations. A Construction of similarity networks for lncRNAs and diseases using Jaccard and GIP kernels for lncRNAs and FNSemSim for diseases. These similarity matrices are refined using RWR and DAE. B The bipartite graph of lncRNA-disease associations is transformed into an interconnected graph, while features from lncRNAs and diseases are concatenated to form an association feature graph using cosine similarity. C Extraction of key features from these graphs using a hybrid graph neural network with GCN and GAT, followed by classification with a MLP to predict lncRNA-disease associations
Fig. 1 Overview of the HiGLDP model for predicting lncRNA-disease associations. A Construction of similarity networks for lncRNAs and diseases using Jaccard and GIP kernels for lncRNAs and FNSemSim for diseases. These similarity matrices are refined using RWR and DAE. B The bipartite graph of lncRNA-disease associations is transformed into an interconnected graph, while features from lncRNAs and diseases are concatenated to form an association feature graph using cosine similarity. C Extraction of key features from these graphs using a hybrid graph neural network with GCN and GAT, followed by classification with a MLP to predict lncRNA-disease associationsCC BY · PubMed Central
Fig. 2 Comprehensive performance evaluation of HiGLDP
Fig. 2 Comprehensive performance evaluation of HiGLDPCC BY · PubMed Central
Fig. 3 Comparative performance analysis of computational models in predicting LncRNA-disease associations. It offers a thorough comparison of multiple computational models using a fivefold cross-validation approach. The ROC curves depict the true-positive rates plotted against false-positive rates. The AUC violin and AUPR violin plots illustrate the distribution and peak performance of each model. Individual data values for all performance metrics are provided in Additional file 1
Fig. 3 Comparative performance analysis of computational models in predicting LncRNA-disease associations. It offers a thorough comparison of multiple computational models using a fivefold cross-validation approach. The ROC curves depict the true-positive rates plotted against false-positive rates. The AUC violin and AUPR violin plots illustrate the distribution and peak performance of each model. Individual data values for all performance metrics are provided in Additional file 1CC BY · PubMed Central
Fig. 4 Comparison of predictive probability heatmaps for lncRNA-disease associations across multiple models. It provides a comprehensive visualization of predictive performance across various computational models for predicting lncRNA-disease associations. Each panel features a heatmap illustrating the predicted probabilities of 30 lncRNAs against 30 diseases, where darker shades denote higher probabilities of lncRNA-disease associations. Alongside each heatmap, a scatter plot depicts the predictive performance of each disease across the 30 lncRNAs. Red dots on the scatter plot indicate true-positive labels, representing lncRNAs known to be associated with the disease
Fig. 4 Comparison of predictive probability heatmaps for lncRNA-disease associations across multiple models. It provides a comprehensive visualization of predictive performance across various computational models for predicting lncRNA-disease associations. Each panel features a heatmap illustrating the predicted probabilities of 30 lncRNAs against 30 diseases, where darker shades denote higher probabilities of lncRNA-disease associations. Alongside each heatmap, a scatter plot depicts the predictive performance of each disease across the 30 lncRNAs. Red dots on the scatter plot indicate true-positive labels, representing lncRNAs known to be associated with the diseaseCC BY · PubMed Central
Fig. 5 Performance evaluation of HiGLDP and its ablated variants. It provides a comprehensive comparison of its ablated variants using a fivefold cross-validation method. The AUC violin plots illustrate the variability and peak performance of each model. The AUPR violin plots highlight the performance under imbalanced association samples. Individual data values for all performance metrics are provided in Additional file 1
Fig. 5 Performance evaluation of HiGLDP and its ablated variants. It provides a comprehensive comparison of its ablated variants using a fivefold cross-validation method. The AUC violin plots illustrate the variability and peak performance of each model. The AUPR violin plots highlight the performance under imbalanced association samples. Individual data values for all performance metrics are provided in Additional file 1CC BY · PubMed Central
Fig. 6 Performance evaluation of different machine learning classifiers used in the HiGLDP model. It provides a comprehensive comparison of different machine learning classifiers using a fivefold cross-validation method. Individual data values for all performance metrics are provided in Additional file 1
Fig. 6 Performance evaluation of different machine learning classifiers used in the HiGLDP model. It provides a comprehensive comparison of different machine learning classifiers using a fivefold cross-validation method. Individual data values for all performance metrics are provided in Additional file 1CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 42 · Cited by 13

Metadata

Authors
Wang, Y., Wang, Z., Wang, T., Hu, J., You, Z., & Peng, J.
Affiliations
Northwestern Polytechnical University (CN)
Corresponding author
  • Wang, Yongtian
  • Peng, Jiajie
Venue
BMC Biology
Published
2026-02-20
Volume
24
Issue
1
ISSN
1741-7007 (ISSN-L)
OpenAlex
W7130575998
Cited by
13
References
42
Citations by year
2026: 13
FWCI
41.27
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Biology (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515010676)
  • National Natural Science Foundation of China (62572397)
  • China Postdoctoral Science Foundation (2023M732860)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Cancer-related molecular mechanisms research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Circular RNAs in diseases
Keywords
lncRNA-disease association prediction, long non-coding RNA, multi-omics integration, hierarchical graph neural networks, graph convolutional networks, graph attention networks, random walk with restart, denoising autoencoder, disease similarity network
MeSH terms
Multiomics, Graph Neural Networks, Humans, Computational Biology, Genetic Predisposition to Disease, RNA, Long Noncoding

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: HiGLDP: a hierarchical graph neural network for predicting lncRNA-disease associations through multi-omic integration. https://app.cochat.ai/papers/10.1186/s12915-026-02557-z
The paper
Wang, Y., Wang, Z., Wang, T., Hu, J., You, Z., & Peng, J. (2026). HiGLDP: a hierarchical graph neural network for predicting lncRNA-disease associations through multi-omic integration. BMC Biology. https://doi.org/10.1186/s12915-026-02557-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.