EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SemNet Explorer: An Evidence-Grounded Knowledge Graph–LLM Framework for Multi-Scale Mechanistic Reporting Across Biomedical Domains

Xin He, David Camacho, Lama Moukheiber, Meghna Iyer, Benjamin Zhao iD, Christophe Ye, Batuhan Nursal, Xinyu Guo, Albert J B Lee iD, Cassie S Mitchell iD

Big Data and Cognitive Computing · 25.05.2026 · 10 (6) · 171

DOI: 10.3390/bdcc10060171 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 25.05.2026. Verfasst von Xin He und 9 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIGMS NIH HHS, Chan Zuckerberg Initiative.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Mechanistic reporting from large-scale biomedical knowledge graphs remains challenging, particularly when integrating structured graph evidence with large language model (LLM)–based 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–LLM 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–LLM integration requires adaptive, context-dependent evidence grounding rather than fixed prompting strategies.

Schlagwörter

Stichwörter der Autor:innen

SemNet 2.0Venn decompositionadaptive promptingadverse event analysiscomparative pathophysiologydrug repurposingevidence groundinggraph-based reasoningknowledge graphlarge language modelsmechanistic reportingmultimorbidityprocess enrichment

Autor:innen und Institutionen

  • Laboratory for Pathology Dynamics, Georgia Institute of Technology, Emory University School of Medicine, Atlanta, GA 30332, USA.
  • Department of Mathematics, Brigham Young University, Provo, UT 84602, USA.
  • Center for Machine Learning at Georgia Tech, Georgia Institute of Technology, Atlanta, GA 30332, USA.

ORCID-Profile: Benjamin Zhao, Albert J B Lee, Cassie S Mitchell

Förderung

  • NIA NIH HHS
  • NIGMS NIH HHS
  • Chan Zuckerberg Initiative
  • National Institutes of Health

Zitieren

APA

He, X., Camacho, D., Moukheiber, L., Iyer, M., Zhao, B., Ye, C., Nursal, B., Guo, X., Lee, A. J. B., & Mitchell, C. S. (2026). SemNet Explorer: An Evidence-Grounded Knowledge Graph–LLM Framework for Multi-Scale Mechanistic Reporting Across Biomedical Domains. Big Data and Cognitive Computing, 10(6), 171. https://doi.org/10.3390/bdcc10060171

Vancouver

He X, Camacho D, Moukheiber L, Iyer M, Zhao B, Ye C, et al. SemNet Explorer: An Evidence-Grounded Knowledge Graph–LLM Framework for Multi-Scale Mechanistic Reporting Across Biomedical Domains. Big Data and Cognitive Computing. 2026;10(6):171. doi:10.3390/bdcc10060171

BibTeX
@article{He2026,
  author = {He, Xin and Camacho, David and Moukheiber, Lama and Iyer, Meghna and Zhao, Benjamin and Ye, Christophe and Nursal, Batuhan and Guo, Xinyu and Lee, Albert J B and Mitchell, Cassie S},
  title = {SemNet Explorer: An Evidence-Grounded Knowledge Graph–LLM Framework for Multi-Scale Mechanistic Reporting Across Biomedical Domains},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {6},
  pages = {171},
  doi = {10.3390/bdcc10060171}
}
Kostenlos starten →