Background/Objectives: Alzheimer’s disease (AD), amyotrophic lateral sclerosis (ALS), and frontotemporal dementia (FTD) share molecular features yet differ clinically, suggesting underlying systems-level commonalities. We aimed to characterize shared and disease-specific multimorbidity architectures across AD, ALS, and FTD using an artificial intelligence–driven literature-based semantic network. Methods: We applied SemNet 2.0, constructed from over 35 million PubMed abstracts, to analyze disease and syndrome (DSYN) and pharmacological substance (PHSU) nodes. Nodes were ranked using HeteSim and mapped to a harmonized 13-category mechanistic ontology. We quantified pairwise disease intersections, ontology-level enrichment, rank similarity, and intersection–disease alignment, and constructed an integrated multimorbidity priority landscape integrating disease-specific and intersection-level hierarchies. Results: Across AD, ALS, and FTD, a convergent multimorbidity architecture centered on a shared metabolic and immune core was identified, accompanied by prominent neurobehavioral processes and intermediate systems including gastrointestinal, endocrine, hematological, hepatic, and sensory pathways. Disease-specific signatures shaped distinct vulnerability profiles within this shared structure, including cardiovascular enrichment in AD, neuromuscular and toxin-related pathways in ALS, and coupled neurobehavioral–metabolic features in FTD. PHSU patterns reinforced these findings, with centrally positioned compounds predominantly targeting inflammatory, metabolic, or neuromodulatory processes. Conclusions: These findings position AD, ALS, and FTD within a unified, AI-derived multimorbidity framework. This ontology-guided approach provides a computational, hypothesis-generating foundation for multimorbidity-aware biomarker discovery, risk stratification, and cross-disease therapeutic exploration in neurodegenerative disease.

Background/Objectives: Literature-derived knowledge graphs are attractive for drug repurposing because every edge retains its supporting publications. Their predicates, however, record which relation a sentence asserted, not whether the evidence supports a therapeutic direction. We asked whether reading those publications can align such a graph with the repurposing task. Methods: EviAlign re-interprets each edge of disease-centered SemMedDB subgraphs. A large language model (LLM) judge reads the supporting publications sentence by sentence, assigns a therapeutic direction or withdraws the edge, and weights each edge by evidence strength rather than publication count. Signed edges compose along drug–mediator–disease paths. Six diseases and 68,689 edges were evaluated against the original predicates read through a fixed mapping and trimmed to the same size, using curated drug–disease benchmarks, an internal sign-consistency test, and blinded rating by three domain experts. Results: EviAlign increased average precision by 63% over the size-matched fixed-mapping baseline. For candidates with no direct disease literature, Precision@10 increased approximately threefold (0.050 versus 0.018). Direct and mediator-derived signs agreed in 75.0% of evaluable cases, 16 percentage points above a shuffled-label control; the fixed mapping stayed at the level of its own control. Experts confirmed the re-interpreted direction in 34 of 36 reversal ratings and judged 80% of top-ranked mediator-only candidates worth investigating, versus 53% of low-ranked controls. Conclusions: Reading the evidence behind each edge aligns literature-derived knowledge graphs with drug repurposing and yields interpretable, mechanism-grounded hypotheses for further investigation.

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.