immuneKG: An Immune-Cell-Aware Knowledge Graph Framework for Target Discovery in Immune-Mediated Diseases

Abstract

Biomedical knowledge graphs have emerged as foundational infrastructure for AI-driven drug discovery, yet their translational impact on novel target identification in immune-mediated diseases remains limited. Here we present immuneKG, a multimodal knowledge graph centred on autoimmune diseases, constructed through biologically meaningful feature reprogramming of disease nodes to enable deep mechanistic modelling of immune-related disorders. immuneKG introduces a new entity class immune_cell and four original directed relation types, together adding 9,105 novel triples absent from all existing biomedical KG schemas. Disease nodes are endowed with three novel modal feature sets quantifying immune homeostatic imbalance: autoantibody profiles, cytokine signatures, and HLA genotypes, complemented by systemic involvement scores and genetic features. The graph encompasses over 407,000 training triples across 7,287 entities and 32 relation types. Applied to inflammatory bowel disease (IBD), immuneKG combined with a HeteroPNA-Attn graph neural network achieves a Hits@100 of 0.99 against a Clarivate Phase II+ clinical pipeline, while a novelty-penalised scoring function surfaces high-potential dark targets. The framework shifts from conventional candidate-space screening to a development-oriented decision-support paradigm, providing actionable and interpretable guidance for downstream drug discovery. The immuneKG project is publicly available on GitHub at https://github.com/YaowenYe/immuneKG. HighlightsO_LIWe propose ImmuneKG, introducing novel immune_cell node types, four original immune-cell relation types, and a gold feature set for autoimmune disease nodes, while pruning redundant nodes to enhance feature depth and distribution balance. C_LIO_LIWe develop HeteroPNA-Attn, a dedicated heterogeneous graph attention network that mitigates uneven feature distribution density across node modalities. Multi-head mutual attention balances cross-modal weights, yielding steady downstream performance gains as modalities are added. C_LIO_LIOur novelty-driven scoring module prioritises de novo target discovery over retrospective data fitting. Optimising Hits@1 rather than reporting successes from large candidate pools eliminates selection bias and demonstrates authentic predictive power in real-world R&D scenarios. C_LIO_LIInterpretability analysis confirms that immune cell nodes play a pivotal role in complex multi-hop graph reasoning; visualisation of path-level attention weights reveals that immuneKG routes predictions through biologically coherent immune-cell intermediaries. C_LI