Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis
Abstract Alzheimer’s disease (AD) involves complex genetic interactions that remain challenging to model computationally. We present a novel deep learning framework integrating Single Nucleotide Polymorphism (SNP) data with Graph Convolutional Networks (GCNs) to predict gene-disease relationships in...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-07-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-025-01228-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234910561173504 |
|---|---|
| author | Belal A. Hamed Heba Mamdouh Farghaly Ahmed Omar Tarek Abd El-Hafeez |
| author_facet | Belal A. Hamed Heba Mamdouh Farghaly Ahmed Omar Tarek Abd El-Hafeez |
| author_sort | Belal A. Hamed |
| collection | DOAJ |
| description | Abstract Alzheimer’s disease (AD) involves complex genetic interactions that remain challenging to model computationally. We present a novel deep learning framework integrating Single Nucleotide Polymorphism (SNP) data with Graph Convolutional Networks (GCNs) to predict gene-disease relationships in AD. Our dual-pathway architecture combines: (1) linear SNP feature processing for individual genetic variants and (2) non-linear GCN analysis of functional gene networks, fused through an optimized integration module. Using rigorously curated data from the GWAS Catalog and AD-specific functional networks (FGN), the model achieved exceptional performance (accuracy: 98.04 ± 0.32%, AUROC: 0.996). Ablation studies demonstrated statistically significant contributions from both GCN (Δaccuracy − 7.92%, p < 0.001) and SNP pathways (Δaccuracy − 5.74%, p < 0.001), validating their complementary roles in AD prediction. The framework’s biological interpretability revealed known AD risk genes (APOE, PSEN1) while identifying novel network-level associations. This study advances precision medicine in neurodegeneration by providing: (i) a validated tool for early genetic risk assessment, and (ii) mechanistic insights into AD pathogenesis through network medicine paradigms. The model’s modular design permits adaptation to other complex diseases, with immediate applications in clinical trial stratification and therapeutic target discovery. |
| format | Article |
| id | doaj-art-8929cb477e9140f397d61fbff75796da |
| institution | Kabale University |
| issn | 2196-1115 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj-art-8929cb477e9140f397d61fbff75796da2025-08-20T04:02:57ZengSpringerOpenJournal of Big Data2196-11152025-07-0112113210.1186/s40537-025-01228-0Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysisBelal A. Hamed0Heba Mamdouh Farghaly1Ahmed Omar2Tarek Abd El-Hafeez3Department of Computer Science, Faculty of Science, Minia UniversityDepartment of Computer Science, Faculty of Science, Minia UniversityDepartment of Computer Science, Faculty of Science, Minia UniversityDepartment of Computer Science, Faculty of Science, Minia UniversityAbstract Alzheimer’s disease (AD) involves complex genetic interactions that remain challenging to model computationally. We present a novel deep learning framework integrating Single Nucleotide Polymorphism (SNP) data with Graph Convolutional Networks (GCNs) to predict gene-disease relationships in AD. Our dual-pathway architecture combines: (1) linear SNP feature processing for individual genetic variants and (2) non-linear GCN analysis of functional gene networks, fused through an optimized integration module. Using rigorously curated data from the GWAS Catalog and AD-specific functional networks (FGN), the model achieved exceptional performance (accuracy: 98.04 ± 0.32%, AUROC: 0.996). Ablation studies demonstrated statistically significant contributions from both GCN (Δaccuracy − 7.92%, p < 0.001) and SNP pathways (Δaccuracy − 5.74%, p < 0.001), validating their complementary roles in AD prediction. The framework’s biological interpretability revealed known AD risk genes (APOE, PSEN1) while identifying novel network-level associations. This study advances precision medicine in neurodegeneration by providing: (i) a validated tool for early genetic risk assessment, and (ii) mechanistic insights into AD pathogenesis through network medicine paradigms. The model’s modular design permits adaptation to other complex diseases, with immediate applications in clinical trial stratification and therapeutic target discovery.https://doi.org/10.1186/s40537-025-01228-0Alzheimer's diseaseMutationsFeature extractionBiological impactBrain diseaseGene-disease association |
| spellingShingle | Belal A. Hamed Heba Mamdouh Farghaly Ahmed Omar Tarek Abd El-Hafeez Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis Journal of Big Data Alzheimer's disease Mutations Feature extraction Biological impact Brain disease Gene-disease association |
| title | Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis |
| title_full | Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis |
| title_fullStr | Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis |
| title_full_unstemmed | Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis |
| title_short | Identifying key genetic variants in Alzheimer’s disease progression using Graph Convolutional Networks (GCN) and biological impact analysis |
| title_sort | identifying key genetic variants in alzheimer s disease progression using graph convolutional networks gcn and biological impact analysis |
| topic | Alzheimer's disease Mutations Feature extraction Biological impact Brain disease Gene-disease association |
| url | https://doi.org/10.1186/s40537-025-01228-0 |
| work_keys_str_mv | AT belalahamed identifyingkeygeneticvariantsinalzheimersdiseaseprogressionusinggraphconvolutionalnetworksgcnandbiologicalimpactanalysis AT hebamamdouhfarghaly identifyingkeygeneticvariantsinalzheimersdiseaseprogressionusinggraphconvolutionalnetworksgcnandbiologicalimpactanalysis AT ahmedomar identifyingkeygeneticvariantsinalzheimersdiseaseprogressionusinggraphconvolutionalnetworksgcnandbiologicalimpactanalysis AT tarekabdelhafeez identifyingkeygeneticvariantsinalzheimersdiseaseprogressionusinggraphconvolutionalnetworksgcnandbiologicalimpactanalysis |