KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
arXiv:2606.26179v1 Announce Type: new Abstract: While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pathways. We present KG-TRACE, a novel neuro-symbolic framework that integrates the WHO mutation knowledge graph (KG) as a structured biological constraint on a neural genomic model. Unlike existing methods that learn statistical patterns in isolation, KG-TRACE fuses genomic features and RotatE-based KG embeddings through a learned epistemic trust gate, dynamically weighting neural evidence against sym
The increasing sophistication of AI models and the critical need for explainability in sensitive domains like medicine are driving the development of neuro-symbolic AI for applications like antimicrobial resistance prediction.
This development addresses a key limitation of current AI in healthcare by providing mechanistic grounding, which is crucial for trust, regulatory adoption, and effective intervention against public health threats like AMR.
The ability to integrate established biological knowledge into neural networks changes how AI models can be validated and applied in medical contexts, moving beyond mere statistical correlation to explainable causation.
- · AI in healthcare
- · Synthetic biology researchers
- · Pharmaceutical companies
- · Public health organizations
- · Purely black-box AI models in medicine
- · Antibiotic-resistant pathogens
KG-TRACE improves the accuracy and interpretability of antimicrobial resistance prediction by integrating biological knowledge.
Enhanced AMR prediction could lead to more targeted antibiotic treatments, slowing the development of new resistant strains and improving patient outcomes.
The neuro-symbolic framework could be adapted to accelerate drug discovery, personalized medicine, and other complex biological problems, leveraging AI with biological causality.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG