{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T08:04:18Z","timestamp":1779955458131,"version":"3.53.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["AG07664, AG057557, AG061388, and AG062272"],"award-info":[{"award-number":["AG07664, AG057557, AG061388, and AG062272"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000027","name":"National Institute on Alcohol Abuse and Alcoholism","doi-asserted-by":"publisher","award":["AA029831"],"award-info":[{"award-number":["AA029831"]}],"id":[{"id":"10.13039\/100000027","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Med Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Most existing approaches to drug combination discovery are disease-centered, aiming to identify drug pairs for specific diseases. Complementarily, a drug-centered strategy starts from known drug combinations and explores new therapeutic indications, facilitating translational applications by leveraging combinations with established safety profiles. Here, we introduce DualKG-DC, a drug centered computational framework that provides a complementary perspective by identifying potential disease indications for a given drug combination. The dual layer knowledge graph architecture, which is pretrained on a foundation biomedical knowledge graph and subsequently refined on a task specific drug combination subgraph, may reduce reliance on large, labeled datasets by leveraging existing knowledge on drug targets, biological pathways, and observed phenotypic effects. In systematic benchmarking against three state-of-the-art models, DualKG-DC outperformed all comparison models, achieving an average Hits@10 of 0.48, MRR of 0.30, AUROC of 0.99, and AUPRC of 0.31. Notably, in cold start scenarios, DualKG-DC outperformed baseline methods in predicting indications for unseen drug combinations, achieving superior results with an average Hits@10 score of 0.32, an MRR of 0.18, an AUROC of 0.98, and an AUPRC of 0.23. These results highlight DualKG-DC as an effective platform for systematically discovering therapeutic opportunities of drug combinations. By leveraging a dual-layer architecture, the model enables effective knowledge transfer, enhancing predictive performance and robustness, particularly for previously unseen drug combinations.<\/jats:p>","DOI":"10.1007\/s10916-026-02416-y","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T07:31:39Z","timestamp":1779953499000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DualKG-DC: A Drug-Centric Dual-Layer Knowledge Graph Framework for Drug Combination Prediction"],"prefix":"10.1007","volume":"50","author":[{"given":"Zhenxiang","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott W.","family":"Perkins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satya","family":"Parameswaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"2416_CR1","doi-asserted-by":"publisher","first-page":"2807","DOI":"10.1016\/j.csbj.2022.05.055","volume":"20","author":"W Kong","year":"2022","unstructured":"Kong, W., Midena, G., Chen, Y., Athanasiadis, P., Wang, T., Rousu, J., \u2026 Aittokallio, T. (2022). Systematic review of computational methods for drug combination prediction. Computational and structural biotechnology journal, 20, 2807\u20132814.","journal-title":"Computational and structural biotechnology journal"},{"issue":"1","key":"2416_CR2","doi-asserted-by":"publisher","first-page":"bbab355","DOI":"10.1093\/bib\/bbab355","volume":"23","author":"L Wu","year":"2022","unstructured":"Wu, L., Wen, Y., Leng, D., Zhang, Q., Dai, C., Wang, Z., \u2026 Bo, X. (2022). Machine learning methods, databases and tools for drug combination prediction. Briefings in bioinformatics, 23(1), bbab355.","journal-title":"Briefings in bioinformatics"},{"issue":"3","key":"2416_CR3","doi-asserted-by":"publisher","first-page":"bbac075","DOI":"10.1093\/bib\/bbac075","volume":"23","author":"A Torkamannia","year":"2022","unstructured":"Torkamannia, A., Omidi, Y., & Ferdousi, R. (2022). A review of machine learning approaches for drug synergy prediction in cancer. Briefings in Bioinformatics, 23(3), bbac075.","journal-title":"Briefings in Bioinformatics"},{"issue":"6","key":"2416_CR4","doi-asserted-by":"publisher","first-page":"bbab271","DOI":"10.1093\/bib\/bbab271","volume":"22","author":"K Fan","year":"2021","unstructured":"Fan, K., Cheng, L., & Li, L. (2021). Artificial intelligence and machine learning methods in predicting anti-cancer drug combination effects. Briefings in bioinformatics, 22(6), bbab271.","journal-title":"Briefings in bioinformatics"},{"issue":"1","key":"2416_CR5","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1038\/s41467-019-09186-x","volume":"10","author":"F Cheng","year":"2019","unstructured":"Cheng, F., Kov\u00e1cs, I. A., & Barab\u00e1si, A. L. (2019). Network-based prediction of drug combinations. Nature communications, 10(1), 1197.","journal-title":"Nature communications"},{"key":"2416_CR6","doi-asserted-by":"publisher","first-page":"104164","DOI":"10.1016\/j.jbi.2022.104164","volume":"133","author":"P Ding","year":"2022","unstructured":"Ding, P., Pan, Y., Wang, Q., & Xu, R. (2022). Prediction and evaluation of combination pharmacotherapy using natural language processing, machine learning and patient electronic health records. Journal of Biomedical Informatics, 133, 104164.","journal-title":"Journal of Biomedical Informatics"},{"issue":"3","key":"2416_CR7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s10462-023-10669-z","volume":"57","author":"M Besharatifard","year":"2024","unstructured":"Besharatifard, M., & Vafaee, F. (2024). A review on graph neural networks for predicting synergistic drug combinations. Artificial Intelligence Review, 57(3), 49.","journal-title":"Artificial Intelligence Review"},{"key":"2416_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, J., & Liu, Y. (2024). Deep learning for predicting synergistic drug combinations: State-of\u2010the\u2010arts and future directions. Clinical and Translational Discovery, 4(3), e317.","DOI":"10.1002\/ctd2.317"},{"issue":"7","key":"2416_CR9","doi-asserted-by":"publisher","first-page":"5975","DOI":"10.1007\/s10462-022-10306-1","volume":"56","author":"H Askr","year":"2023","unstructured":"Askr, H., Elgeldawi, E., Aboul Ella, H., Elshaier, Y. A., Gomaa, M. M., & Hassanien, A. E. (2023). Deep learning in drug discovery: an integrative review and future challenges. Artificial Intelligence Review, 56(7), 5975\u20136037.","journal-title":"Artificial Intelligence Review"},{"key":"2416_CR10","doi-asserted-by":"crossref","unstructured":"Baptista, D., Ferreira, P. G., & Rocha, M. (2023). A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer. PLOS Computational Biology, 19(3), e1010200.","DOI":"10.1371\/journal.pcbi.1010200"},{"key":"2416_CR11","doi-asserted-by":"crossref","unstructured":"Jin, W., Stokes, J. M., Eastman, R. T., Itkin, Z., Zakharov, A. V., Collins, J. J., \u2026 Barzilay, R. (2021). Deep learning identifies synergistic drug combinations for treating COVID-19. Proceedings of the National Academy of Sciences, 118(39), e2105070118.","DOI":"10.1073\/pnas.2105070118"},{"issue":"7","key":"2416_CR12","doi-asserted-by":"publisher","first-page":"2854","DOI":"10.1021\/acs.jcim.3c00709","volume":"64","author":"T Wang","year":"2023","unstructured":"Wang, T., Wang, R., & Wei, L. (2023). AttenSyn: An attention-based deep graph neural network for anticancer synergistic drug combination prediction. Journal of Chemical Information and Modeling, 64(7), 2854\u20132862.","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"6","key":"2416_CR13","doi-asserted-by":"publisher","first-page":"bbac404","DOI":"10.1093\/bib\/bbac404","volume":"23","author":"S Bonner","year":"2022","unstructured":"Bonner, S., Barrett, I. P., Ye, C., Swiers, R., Engkvist, O., Bender, A., \u2026 Hamilton, W. L. (2022). A review of biomedical datasets relating to drug discovery: a knowledge graph perspective. Briefings in Bioinformatics, 23(6), bbac404.","journal-title":"Briefings in Bioinformatics"},{"key":"2416_CR14","doi-asserted-by":"publisher","first-page":"104133","DOI":"10.1016\/j.jbi.2022.104133","volume":"132","author":"Z Gao","year":"2022","unstructured":"Gao, Z., Ding, P., & Xu, R. (2022). KG-Predict: A knowledge graph computational framework for drug repurposing. Journal of biomedical informatics, 132, 104133.","journal-title":"Journal of biomedical informatics"},{"issue":"3","key":"2416_CR15","doi-asserted-by":"publisher","first-page":"bbad167","DOI":"10.1093\/bib\/bbad167","volume":"24","author":"G Zhang","year":"2023","unstructured":"Zhang, G., Gao, Z., Yan, C., Wang, J., Liang, W., Luo, J., & Luo, H. (2023). KGANSynergy: knowledge graph attention network for drug synergy prediction. Briefings in Bioinformatics, 24(3), bbad167.","journal-title":"Briefings in Bioinformatics"},{"issue":"D1","key":"2416_CR16","first-page":"D845-D855","volume":"48","author":"J Pi\u00f1ero","year":"2020","unstructured":"Pi\u00f1ero, J., Ram\u00edrez-Anguita, J. M., Sa\u00fcch-Pitarch, J., Ronzano, F., Centeno, E., Sanz, F., & Furlong, L. I. (2020). The DisGeNET knowledge platform for disease genomics: 2019 update. Nucleic acids research, 48(D1), D845-D855.","journal-title":"Nucleic acids research"},{"issue":"D1","key":"2416_CR17","doi-asserted-by":"publisher","first-page":"D1265-D1275","DOI":"10.1093\/nar\/gkad976","volume":"52","author":"C Knox","year":"2024","unstructured":"Knox, C., Wilson, M., Klinger, C. M., Franklin, M., Oler, E., Wilson, A., \u2026 Wishart, D. S. (2024). DrugBank 6.0: the DrugBank knowledgebase for 2024. Nucleic acids research, 52(D1), D1265-D1275.","journal-title":"Nucleic acids research"},{"key":"2416_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1479-7364-3-3-291","volume":"3","author":"B Lehne","year":"2009","unstructured":"Lehne, B., & Schlitt, T. (2009). Protein-protein interaction databases: keeping up with growing interactomes. Human genomics, 3, 1\u20137.","journal-title":"Human genomics"},{"issue":"D1","key":"2416_CR19","doi-asserted-by":"publisher","first-page":"D1257-D1262","DOI":"10.1093\/nar\/gkac833","volume":"51","author":"AP Davis","year":"2023","unstructured":"Davis, A. P., Wiegers, T. C., Johnson, R. J., Sciaky, D., Wiegers, J., & Mattingly, C. J. (2023). Comparative toxicogenomics database (CTD): update 2023. Nucleic acids research, 51(D1), D1257-D1262.","journal-title":"Nucleic acids research"},{"issue":"D1","key":"2416_CR20","doi-asserted-by":"publisher","first-page":"D1207-D1217","DOI":"10.1093\/nar\/gkaa1043","volume":"49","author":"S K\u00f6hler","year":"2021","unstructured":"K\u00f6hler, S., Gargano, M., Matentzoglu, N., Carmody, L. C., Lewis-Smith, D., Vasilevsky, N. A., \u2026 Robinson, P. N. (2021). The human phenotype ontology in 2021. Nucleic acids research, 49(D1), D1207-D1217.","journal-title":"Nucleic acids research"},{"key":"2416_CR21","doi-asserted-by":"crossref","unstructured":"Law, M., & Shaw, D. R. (2018). Mouse Genome Informatics (MGI) is the international resource for information on the laboratory mouse. Eukaryotic Genomic Databases: Methods and Protocols, 141\u2013161.","DOI":"10.1007\/978-1-4939-7737-6_7"},{"issue":"17","key":"2416_CR22","doi-asserted-by":"publisher","first-page":"2186","DOI":"10.1093\/bioinformatics\/btt359","volume":"29","author":"R Xu","year":"2013","unstructured":"Xu, R., Li, L., & Wang, Q. (2013). Towards building a disease-phenotype knowledge base: extracting disease-manifestation relationship from literature. Bioinformatics, 29(17), 2186\u20132194.","journal-title":"Bioinformatics"},{"key":"2416_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-15-105","volume":"15","author":"R Xu","year":"2014","unstructured":"Xu, R., Li, L., & Wang, Q. (2014). dRiskKB: a large-scale disease-disease risk relationship knowledge base constructed from biomedical text. BMC bioinformatics, 15, 1\u201313.","journal-title":"BMC bioinformatics"},{"issue":"1","key":"2416_CR24","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Philip, S. Y. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1), 4\u201324.","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"2416_CR25","unstructured":"Vashishth, S., Sanyal, S., Nitin, V., & Talukdar, P. P. (2020, January). Composition-based Multi-Relational Graph Convolutional Networks. In ICLR."},{"key":"2416_CR26","doi-asserted-by":"crossref","unstructured":"Schlichtkrull, M., Kipf, T. N., Bloem, P., Van Den Berg, R., Titov, I., & Welling, M. (2018, June). Modeling relational data with graph convolutional networks. In European semantic web conference (pp. 593\u2013607). Cham: Springer International Publishing.","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"2416_CR27","unstructured":"Glorot, X., & Bengio, Y. (2010, March). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics (pp. 249\u2013256). JMLR Workshop and Conference Proceedings."},{"key":"2416_CR28","doi-asserted-by":"crossref","unstructured":"Vashishth, S., Sanyal, S., Nitin, V., Agrawal, N., & Talukdar, P. (2020, April). Interacte: Improving convolution-based knowledge graph embeddings by increasing feature interactions. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 03, pp. 3009\u20133016).","DOI":"10.1609\/aaai.v34i03.5694"},{"issue":"16","key":"2416_CR29","doi-asserted-by":"publisher","first-page":"4483","DOI":"10.1093\/bioinformatics\/btaa287","volume":"36","author":"Z Sun","year":"2020","unstructured":"Sun, Z., Huang, S., Jiang, P., & Hu, P. (2020). DTF: deep tensor factorization for predicting anticancer drug synergy. Bioinformatics, 36(16), 4483\u20134489.","journal-title":"Bioinformatics"},{"key":"2416_CR30","doi-asserted-by":"crossref","unstructured":"Balazevic, I., Allen, C., & Hospedales, T. (2019). TuckER: Tensor Factorization for Knowledge Graph Completion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1522"},{"key":"2416_CR31","unstructured":"Sun, Z., Deng, Z. H., Nie, J. Y., & Tang, J. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In International Conference on Learning Representations."},{"key":"2416_CR32","doi-asserted-by":"crossref","unstructured":"Lee, J. E., Yu, S. H., Kim, S. R., Ahn, K. J., Song, K. H., Lee, I. K., \u2026 Lee, M.K. (2024). Efficacy and safety of metformin and atorvastatin combination therapy vs.Monotherapy with either drug in type 2 diabetes mellitus and dyslipidemia patients(ATOMIC): double-blinded randomized controlled trial. Diabetes & Metabolism Journal,48(4), 730\u2013739.","DOI":"10.4093\/dmj.2023.0077"},{"key":"2416_CR33","doi-asserted-by":"crossref","unstructured":"McGuinness, J. E., Crew, K. D., Trivedi, M. S., Accordino, M. K., Lee, S. M., Guo,H., \u2026 Kalinsky, K. (2023). Abstract P3-07-22: Presurgical Trial of Metformin plus Atorvastatin in Women with Operable Breast Cancer. Cancer Research, 83(5_Supplement),P3-07.","DOI":"10.1158\/1538-7445.SABCS22-P3-07-22"},{"key":"2416_CR34","doi-asserted-by":"crossref","unstructured":"Jia, W., Bai, T., Zeng, J., Niu, Z., Fan, D., Xu, X., \u2026 Dai, X. (2021). Combined administration of metformin and atorvastatin attenuates diabetic cardiomyopathy by inhibiting inflammation, apoptosis, and oxidative stress in type 2 diabetic mice.Frontiers in cell and developmental biology, 9, 634900.","DOI":"10.3389\/fcell.2021.634900"},{"key":"2416_CR35","doi-asserted-by":"crossref","unstructured":"Luo, F., Guo, Y., Ruan, G. Y., Long, J. K., Zheng, X. L., Xia, Q., \u2026 Li, X. P. (2017).Combined use of metformin and atorvastatin attenuates atherosclerosis in rabbits fed a high-cholesterol diet. Scientific Reports, 7(1), 2169.","DOI":"10.1038\/s41598-017-02080-w"},{"key":"2416_CR36","doi-asserted-by":"crossref","unstructured":"Dizon, D. S., Blessing, J. A., Penson, R. T., Drake, R. D., Walker, J. L., Johnston,C. M., \u2026 Fader, A. N. (2012). A phase II evaluation of belinostat and carboplatin in the treatment of recurrent or persistent platinum-resistant ovarian, fallopian tube, or primary peritoneal carcinoma: a Gynecologic Oncology Group study. Gynecologic oncology, 125(2), 367\u2013371.","DOI":"10.1016\/j.ygyno.2012.02.019"},{"key":"2416_CR37","doi-asserted-by":"crossref","unstructured":"Gerds, A. T., Scott, B. L., Greenberg, P., Lin, T. L., Pollyea, D. A., Verma, A.,\u2026 Donnellan, W. (2022). Atezolizumab alone or in combination did not demonstrate a favorable risk-benefit profile in myelodysplastic syndrome. Blood Advances, 6(4), 1152\u20131161.","DOI":"10.1182\/bloodadvances.2021005240"},{"issue":"3","key":"2416_CR38","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s11192-011-0494-7","volume":"90","author":"D Fanelli","year":"2012","unstructured":"Fanelli, D. (2012). Negative results are disappearing from most disciplines and countries. Scientometrics, 90(3), 891\u2013904.","journal-title":"Scientometrics"},{"issue":"1","key":"2416_CR39","doi-asserted-by":"publisher","first-page":"vbaf263","DOI":"10.1093\/bioadv\/vbaf263","volume":"5","author":"R Masumshah","year":"2025","unstructured":"Masumshah, R., & Eslahchi, C. (2025). PSO-FeatureFusion: a general framework for fusing heterogeneous features via particle swarm optimization. Bioinformatics Advances, 5(1), vbaf263.","journal-title":"Bioinformatics Advances"},{"key":"2416_CR40","doi-asserted-by":"crossref","unstructured":"Soman, K., Nelson, C. A., Cerono, G., & Baranzini, S. E. (2022). Time-aware embeddings of clinical data using a knowledge graph. In Pacific Symposium on Biocomputing 2023: Kohala Coast, Hawaii, USA, 3\u20137 January 2023 (pp. 97\u2013108).","DOI":"10.1142\/9789811270611_0010"}],"container-title":["Journal of Medical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02416-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10916-026-02416-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02416-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T07:31:47Z","timestamp":1779953507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10916-026-02416-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2416"],"URL":"https:\/\/doi.org\/10.1007\/s10916-026-02416-y","relation":{},"ISSN":["1573-689X"],"issn-type":[{"value":"1573-689X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"10 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethicsal Approval and Consent to Participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"88"}}