{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:02:06Z","timestamp":1790787726298,"version":"4.1.0"},"reference-count":40,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2020M2D9A1094070"],"award-info":[{"award-number":["2020M2D9A1094070"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>The image texture features obtained from 18F-fluorodeoxyglucose positron emission tomography\/computed tomography (18F-FDG PET\/CT) images of non-small cell lung cancer (NSCLC) have revealed tumor heterogeneity. A combination of genomic data and radiomics may improve the prediction of tumor prognosis. This study aimed to predict NSCLC metastasis using a graph neural network (GNN) obtained by combining a protein\u2013protein interaction (PPI) network based on gene expression data and image texture features. 18F-FDG PET\/CT images and RNA sequencing data of 93 patients with NSCLC were acquired from The Cancer Imaging Archive. Image texture features were extracted from 18F-FDG PET\/CT images and area under the curve receiver operating characteristic curve (AUC) of each image feature was calculated. Weighted gene co-expression network analysis (WGCNA) was used to construct gene modules, followed by functional enrichment analysis and identification of differentially expressed genes. The PPI of each gene module and genes belonging to metastasis-related processes were converted via a graph attention network. Images and genomic features were concatenated. The GNN model using PPI modules from WGCNA and metastasis-related functions combined with image texture features was evaluated quantitatively. Fifty-five image texture features were extracted from 18F-FDG PET\/CT, and radiomic features were selected based on AUC (n = 10). Eighty-six gene modules were clustered by WGCNA. Genes (n = 19) enriched in the metastasis-related pathways were filtered using DEG analysis. The accuracy of the PPI network, derived from WGCNA modules and metastasis-related genes, improved from 0.4795 to 0.5830 (p &lt; 2.75 \u00d7 10\u221212). Integrating PPI of four metastasis-related genes with 18F-FDG PET\/CT image features in a GNN model elevated its accuracy over a without image feature model to 0.8545 (95% CI = 0.8401\u20130.8689, p-value &lt; 0.02). This model demonstrated significant enhancement compared to the model using PPI and 18F-FDG PET\/CT derived from WGCNA (p-value &lt; 0.02), underscoring the critical role of metastasis-related genes in prediction model. The enhanced predictive capability of the lymph node metastasis prediction GNN model for NSCLC, achieved through the integration of comprehensive image features with genomic data, demonstrates promise for clinical implementation.<\/jats:p>","DOI":"10.3390\/ijms25020698","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T05:12:17Z","timestamp":1704431537000},"page":"698","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Graph Neural Network Model for Prediction of Non-Small Cell Lung Cancer Lymph Node Metastasis Using Protein\u2013Protein Interaction Network and 18F-FDG PET\/CT Radiomics"],"prefix":"10.3390","volume":"25","author":[{"given":"Hyemin","family":"Ju","sequence":"first","affiliation":[{"name":"Radiological and Medico-Oncological Sciences, University of Science and Technology, Daejeon 34113, Republic of Korea"},{"name":"Division of RI-Convergence Research, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangsan","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of RI-Convergence Research, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung Il","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6728-8876","authenticated-orcid":false,"given":"Sang-Keun","family":"Woo","sequence":"additional","affiliation":[{"name":"Radiological and Medico-Oncological Sciences, University of Science and Technology, Daejeon 34113, Republic of Korea"},{"name":"Division of RI-Convergence Research, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Meza, R., Meernik, C., Jeon, J., and Cote, M.L. (2015). Lung cancer incidence trends by gender, race and histology in the United States, 1973\u20132010. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0121323"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1093\/jjco\/hyu003","article-title":"Cancer incidence and incidence rates in Japan in 2008: A study of 25 population-based cancer registries for the Monitoring of Cancer Incidence in Japan (MCIJ) project","volume":"44","author":"Matsuda","year":"2014","journal-title":"Jpn. J. Clin. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.lungcan.2007.03.012","article-title":"National survey of non-small cell lung cancer in the United States: Epidemiology, pathology and patterns of care","volume":"57","author":"Little","year":"2007","journal-title":"Lung Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: The process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reason. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4704","DOI":"10.1002\/sim.8749","article-title":"Tumor heterogeneity estimation for radiomics in cancer","volume":"39","author":"Eloyan","year":"2020","journal-title":"Stat. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11864-007-0023-3","article-title":"Management of locally advanced non small cell lung cancer from a surgical perspective","volume":"8","author":"Roy","year":"2007","journal-title":"Curr. Treat. Options Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: Extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur. J. Cancer"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1002\/jmri.25874","article-title":"Tumor radiomic heterogeneity: Multiparametric functional imaging to characterize variability and predict response following cervical cancer radiation therapy","volume":"47","author":"Bowen","year":"2018","journal-title":"J. Magn. Reason. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1136\/jmg.2006.041376","article-title":"Predicting disease genes using protein\u2013protein interactions","volume":"43","author":"Oti","year":"2006","journal-title":"J. Med. Genet."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"147648","DOI":"10.1155\/2014\/147648","article-title":"Protein-protein interaction detection: Methods and analysis","volume":"2014","author":"Rao","year":"2014","journal-title":"Int. J. Proteom."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1002\/med.21585","article-title":"Emerging roles of allosteric modulators in the regulation of protein-protein interactions (PPIs): A new paradigm for PPI drug discovery","volume":"39","author":"Ni","year":"2019","journal-title":"Med. Res. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Bebek, G., and Yang, J. (2007). PathFinder: Mining signal transduction pathway segments from protein-protein interaction networks. BMC Bioinform., 8.","DOI":"10.1186\/1471-2105-8-335"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2012","DOI":"10.1002\/anie.201107616","article-title":"Small-Molecule Stabilization of Protein\u2013Protein Interactions: An Underestimated Concept in Drug Discovery?","volume":"51","author":"Thiel","year":"2012","journal-title":"Angew. Chem. Int. Ed."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kar, G., Gursoy, A., and Keskin, O. (2009). Human cancer protein-protein interaction network: A structural perspective. PLoS Comput Biol., 5.","DOI":"10.1371\/journal.pcbi.1000601"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Engin, H.B., Guney, E., Keskin, O., Oliva, B., and Gursoy, A. (2013). Integrating structure to protein-protein interaction networks that drive metastasis to brain and lung in breast cancer. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0081035"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1109\/TCBB.2021.3063532","article-title":"Enhancing cancer driver gene prediction by protein-protein interaction network","volume":"19","author":"Liu","year":"2022","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1021\/acs.jproteome.6b00950","article-title":"Identification of genes associated with breast cancer metastasis to bone on a protein\u2013protein interaction network with a shortest path algorithm","volume":"16","author":"Cai","year":"2017","journal-title":"J. Proteome Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Veyrin-Forrer, L., Kamal, A., Duffner, S., Plantevit, M., and Robardet, C. (2022). On gnn explainability with activation rules. Data Min. Knowl. Discov., 1\u201335.","DOI":"10.1007\/s10618-022-00870-z"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"345","DOI":"10.35833\/MPCE.2021.000058","article-title":"A review of graph neural networks and their applications in power systems","volume":"10","author":"Liao","year":"2021","journal-title":"J. Mod. Power Syst. Clean Energy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107528","DOI":"10.1016\/j.knosys.2021.107528","article-title":"Improving graph neural network via complex-network-based anchor structure","volume":"233","author":"Dong","year":"2012","journal-title":"Knowl. Based Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, S., Tang, H., Shan, P., Wu, Z., and Zuo, L. (2023). ProS-GNN: Predicting effects of mutations on protein stability using graph neural networks. Comput. Biol. Chem., 107.","DOI":"10.1016\/j.compbiolchem.2023.107952"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100758","DOI":"10.1016\/j.patter.2023.100758","article-title":"Biology-inspired graph neural network encodes reactome and reveals biochemical reactions of disease","volume":"4","author":"Burkhart","year":"2023","journal-title":"Patterns Prejud."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"La Rosa, M., Fiannaca, A., La Paglia, L., and Urso, A.A. (2022). Graph Neural Network Approach for the Analysis of siRNA-Target Biological Networks. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms232214211"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1533033818782788","DOI":"10.1177\/1533033818782788","article-title":"Radiomics for response and outcome assessment for non-small cell lung cancer","volume":"17","author":"Shi","year":"2018","journal-title":"Technol. Cancer Res. Treat."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3643","DOI":"10.1007\/s00259-021-05371-7","article-title":"Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer","volume":"48","author":"Kirienko","year":"2021","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1148\/radiol.2017161845","article-title":"Non\u2013small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications","volume":"286","author":"Zhou","year":"2018","journal-title":"Radiology"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5333","DOI":"10.21037\/qims-23-2","article-title":"A graph neural network model for the diagnosis of lung adenocarcinoma based on multimodal features and an edge-generation network","volume":"13","author":"Li","year":"2023","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1126\/science.aaf4405","article-title":"Hypoxic Control of Metastasis","volume":"352","author":"Rankin","year":"2016","journal-title":"Science"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.lungcan.2005.03.036","article-title":"Expression of HIF-1\u03b1, CA IX, VEGF, and MMP-9 in surgically resected non-small cell lung cancer","volume":"49","author":"Kim","year":"2005","journal-title":"Lung Cancer"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1136\/jcp.2003.015032","article-title":"The role of hypoxia inducible factor 1 (HIF-1) in hypoxia induced apoptosis","volume":"57","author":"Greijer","year":"2004","journal-title":"J. Clin. Pathol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1186\/1476-4598-9-191","article-title":"Anti-apoptotic role of HIF-1 and AP-1 in paclitaxel exposed breast cancer cells under hypoxia","volume":"9","author":"Flamant","year":"2010","journal-title":"Mol. Cancer"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10549-007-9732-3","article-title":"Central carbon metabolism in the progression of mammary carcinoma","volume":"110","author":"Richardson","year":"2008","journal-title":"Breast Cancer Res. Treat."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.canlet.2009.07.005","article-title":"Focal adhesion kinase: A prominent determinant in breast cancer initiation, progression and metastasis","volume":"289","author":"Luo","year":"2010","journal-title":"Cancer Lett."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1002\/(SICI)1097-0347(199812)20:8<745::AID-HED14>3.0.CO;2-Z","article-title":"Focal adhesion kinase and its potential involvement in tumor invasion and metastasis","volume":"20","author":"Kornberg","year":"1998","journal-title":"Head Neck J. Sci. Spec. Head Neck"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1517\/14728220903460340","article-title":"Targeting focal adhesion kinase signaling in tumor growth and metastasis","volume":"14","author":"Schwock","year":"2010","journal-title":"Expert Opin. Ther. Targets"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1158\/1535-7163.MCT-11-0555","article-title":"The ubiquitin-proteasome system meets angiogenesis","volume":"11","author":"Rahimi","year":"2012","journal-title":"Mol. Cancer Ther."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"22642","DOI":"10.1074\/jbc.272.36.22642","article-title":"Hypoxia-inducible factor 1\u03b1 (HIF-1\u03b1) protein is rapidly degraded by the ubiquitin-proteasome system under normoxic conditions: Its stabilization by hypoxia depends on redox-induced changes","volume":"272","author":"Salceda","year":"1997","journal-title":"J. Biol. Chem."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/25\/2\/698\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:40:34Z","timestamp":1760103634000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/25\/2\/698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["ijms25020698"],"URL":"https:\/\/doi.org\/10.3390\/ijms25020698","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,5]]}}}