{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:01:11Z","timestamp":1785416471598,"version":"3.56.0"},"reference-count":32,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014989","name":"Chan Zuckerberg Initiative","doi-asserted-by":"publisher","award":["253558"],"award-info":[{"award-number":["253558"]}],"id":[{"id":"10.13039\/100014989","id-type":"DOI","asserted-by":"publisher"}]},{"award":["253558"],"award-info":[{"award-number":["253558"]}],"id":[{"id":"https:\/\/ror.org\/02qenvm24","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["3R35GM152245-25"],"award-info":[{"award-number":["3R35GM152245-25"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"award":["3R35GM152245-25"],"award-info":[{"award-number":["3R35GM152245-25"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Background: Mechanistic reporting from large-scale biomedical knowledge graphs remains challenging, particularly when integrating structured graph evidence with large language model (LLM)\u2013based explanation in a reproducible and auditable manner. Existing approaches either rely on manual synthesis of graph-derived results or generate unconstrained narratives that lack traceability to underlying evidence. Methods: We present SemNet Explorer, an evidence-grounded knowledge graph\u2013LLM unified framework for automated mechanistic reporting across biomedical domains using SemNet 2.0, a PubMed-scale heterogeneous knowledge graph. Given a set of target concepts and a selected semantic layer, the framework organizes graph-derived evidence into structured regions and generates two complementary report types: global reports for process-level mechanisms and anchor-centric reports for localized mediator-based explanations. A central methodological contribution is an ablation-derived adaptive grounding policy: we systematically compare alternative evidence-integration strategies across report types, semantic layers, and region structures, and use the resulting preferences to guide prompt selection in the deployed system. Results: SemNet Explorer produces stable region decompositions and interpretable report scaffolds across molecular (AAPP), disease-level (DSYN), and pharmacologic (PHSU) representations. For global reports, explicit evidence grounding improves expression quality more consistently than content accuracy, with benefits dependent on evidence density and semantic abstraction. In contrast, anchor-centric reports show consistent improvements in both content and expression under stronger, mediator-constrained prompting. These findings are supported by both pairwise ablation comparisons and absolute score analyses. Conclusions: SemNet Explorer establishes a generalizable unified framework and interactive platform for transforming knowledge graph evidence into reproducible mechanistic narratives across biomedical domains, including multimorbidity analysis, comparative pathophysiology, drug repurposing, and adverse event discovery. The results demonstrate that effective knowledge graph\u2013LLM integration requires adaptive, context-dependent evidence grounding rather than fixed prompting strategies.<\/jats:p>","DOI":"10.3390\/bdcc10060171","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T14:10:22Z","timestamp":1779718222000},"page":"171","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SemNet Explorer: An Evidence-Grounded Knowledge Graph\u2013LLM Framework for Multi-Scale Mechanistic Reporting Across Biomedical Domains"],"prefix":"10.3390","volume":"10","author":[{"given":"Xin","family":"He","sequence":"first","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Camacho","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"},{"name":"Department of Mathematics, Brigham Young University, Provo, UT 84602, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lama","family":"Moukheiber","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meghna","family":"Iyer","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3039-3235","authenticated-orcid":false,"given":"Benjamin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christophe","family":"Ye","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Batuhan","family":"Nursal","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-6327","authenticated-orcid":false,"given":"Albert J. B.","family":"Lee","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5472-6355","authenticated-orcid":false,"given":"Cassie S.","family":"Mitchell","sequence":"additional","affiliation":[{"name":"Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA"},{"name":"Center for Machine Learning at Georgia Tech, Georgia Institute of Technology, Atlanta, GA 30332, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1016\/S0140-6736(20)32205-4","article-title":"Alzheimer\u2019s disease","volume":"397","author":"Scheltens","year":"2021","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"17085","DOI":"10.1038\/nrdp.2017.85","article-title":"Amyotrophic lateral sclerosis","volume":"3","author":"Hardiman","year":"2017","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1672","DOI":"10.1016\/S0140-6736(15)00461-4","article-title":"Frontotemporal dementia","volume":"386","author":"Bang","year":"2015","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1146\/annurev.neuro.24.1.1121","article-title":"Neurodegenerative tauopathies","volume":"24","author":"Lee","year":"2001","journal-title":"Annu. Rev. Neurosci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1007\/s00415-009-5069-7","article-title":"Amyotrophic lateral sclerosis, frontotemporal dementia and beyond: The TDP-43 diseases","volume":"256","author":"Geser","year":"2009","journal-title":"J. Neurol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1016\/S1474-4422(10)70195-2","article-title":"TDP-43 and FUS in amyotrophic lateral sclerosis and frontotemporal dementia","volume":"9","author":"Mackenzie","year":"2010","journal-title":"Lancet Neurol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1126\/science.1134108","article-title":"Ubiquitinated TDP-43 in frontotemporal lobar degeneration and amyotrophic lateral sclerosis","volume":"314","author":"Neumann","year":"2006","journal-title":"Science"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.bbrc.2006.10.093","article-title":"TDP-43 is a component of ubiquitin-positive tau-negative inclusions in frontotemporal lobar degeneration and amyotrophic lateral sclerosis","volume":"351","author":"Arai","year":"2006","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.neuron.2011.09.010","article-title":"A hexanucleotide repeat expansion in C9ORF72 is the cause of chromosome 9p21-linked ALS-FTD","volume":"72","author":"Renton","year":"2011","journal-title":"Neuron"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2011.09.011","article-title":"Expanded GGGGCC hexanucleotide repeat in noncoding region of C9ORF72 causes chromosome 9p-linked FTD and ALS","volume":"72","author":"Mackenzie","year":"2011","journal-title":"Neuron"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wei, Z., Iyer, M.R., Zhao, B., Deng, J., and Mitchell, C.S. (2024). Artificial Intelligence-Assisted Comparative Analysis of the Overlapping Molecular Pathophysiology of Alzheimer\u2019s Disease, Amyotrophic Lateral Sclerosis, and Frontotemporal Dementia. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms252413450"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Iyer, M.R., Zhao, B., He, X., Camacho, D., Wei, Z., Deng, J., and Mitchell, C.S. (2026). An Artificial Intelligence-Driven Multimorbidity Framework Reveals a Shared Metabolic and Immune Core Across Alzheimer\u2019s Disease, Amyotrophic Lateral Sclerosis, and Frontotemporal Dementia. Biomedicines, 14.","DOI":"10.3390\/biomedicines14020444"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1353\/pbm.1986.0087","article-title":"Fish oil, Raynaud\u2019s syndrome, and undiscovered public knowledge","volume":"30","author":"Swanson","year":"1986","journal-title":"Perspect. Biol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sedler, A.R., and Mitchell, C.S. (2019). SemNet: Using local features to navigate the biomedical concept graph. Front. Bioeng. Biotechnol., 7.","DOI":"10.3389\/fbioe.2019.00156"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kirkpatrick, A., Onyeze, C., Kartchner, D., Allegri, S., Nakajima An, D., McCoy, K., Davalbhakta, E., and Mitchell, C.S. (2022). Optimizations for Computing Relatedness in Biomedical Heterogeneous Information Networks: SemNet 2.0. Big Data Cogn. Comput., 6.","DOI":"10.3390\/bdcc6010027"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e26726","DOI":"10.7554\/eLife.26726","article-title":"Systematic integration of biomedical knowledge prioritizes drugs for repurposing","volume":"6","author":"Himmelstein","year":"2017","journal-title":"eLife"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1016\/j.csbj.2020.05.017","article-title":"Constructing knowledge graphs and their biomedical applications","volume":"18","author":"Nicholson","year":"2020","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2724","DOI":"10.1109\/TKDE.2017.2754499","article-title":"Knowledge graph embedding: A survey of approaches and applications","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Patidar, K., Deng, J.H., Mitchell, C.S., and Ford Versypt, A.N. (2024). Cross-Domain Text Mining of Pathophysiological Processes Associated with Diabetic Kidney Disease. Int. J. Mol. Sci., 25.","DOI":"10.1101\/2024.01.10.575096"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"McCoy, K., Gudapati, S., He, L., Horlander, E., Kartchner, D., Kulkarni, S., Mehra, N., Prakash, J., Thenot, H., and Vanga, S.V. (2021). Biomedical Text Link Prediction for Drug Discovery: A Case Study with COVID-19. Pharmaceutics, 13.","DOI":"10.3390\/pharmaceutics13060794"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mehra, N., Varmeziar, A., Chen, X., Kronick, O., Fisher, R., Kota, V., and Mitchell, C.S. (2022). Cross-domain text mining to predict adverse events from tyrosine kinase inhibitors for chronic myeloid leukemia. Cancers, 14.","DOI":"10.3390\/cancers14194686"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tandra, G., Yoone, A., Mathew, R., Wang, M., Hales, C.M., and Mitchell, C.S. (2023). Literature-based discovery predicts antihistamines are a promising repurposed adjuvant therapy for Parkinson\u2019s disease. Int. J. Mol. Sci., 24.","DOI":"10.3390\/ijms241512339"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kartchner, D., McCoy, K., Dubey, J., Zhang, D., Zheng, K., Umrani, R., Kim, J.J., and Mitchell, C.S. (2023). Literature-Based Discovery to Elucidate the Biological Links between Resistant Hypertension and COVID-19. Biology, 12.","DOI":"10.3390\/biology12091269"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s44387-025-00047-1","article-title":"Large language models in biomedicine and healthcare","volume":"1","author":"Zhou","year":"2025","journal-title":"npj Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Amugongo, L.M., Mascheroni, P., Brooks, S., Doering, S., and Seidel, J. (2025). Retrieval augmented generation for large language models in healthcare: A systematic review. PLoS Digit. Health, 4.","DOI":"10.1371\/journal.pdig.0000877"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xiong, G., Jin, Q., Lu, Z., and Zhang, A. (2024). Benchmarking Retrieval-Augmented Generation for Medicine. Findings of the Association for Computational Linguistics: ACL 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-acl.372"},{"key":"ref_28","unstructured":"Peng, B., Zhu, Y., Liu, Y., Bo, X., Shi, H., Hong, C., Zhang, Y., and Tang, S. (2024). Graph Retrieval-Augmented Generation: A Survey. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wu, J., Zhu, J., Qi, Y., Chen, J., Xu, M., Menolascina, F., Jin, Y., and Grau, V. (2025). Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"key":"ref_30","unstructured":"Xiong, G., Xie, E., Shariatmadari, A.H., Guo, S., Bekiranov, S., and Zhang, A. (2024). Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models. arXiv."},{"key":"ref_31","unstructured":"Edge, D., Trinh, H., Cheng, B., and Bradley, A. (2024). From local to global: A graph retrieval augmented generation approach. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2479","DOI":"10.1109\/TKDE.2013.2297920","article-title":"HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks","volume":"26","author":"Shi","year":"2014","journal-title":"IEEE Trans. Knowl. Data Eng."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/6\/171\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:11:11Z","timestamp":1780459871000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/6\/171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":32,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["bdcc10060171"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10060171","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,25]]}}}