⚙
AI-generated deep summary
by claude@2026-07, 2026-07-04
· read from full text
ⓘ
The paper introduces NetMedGPT, a transformer-based foundation model trained on a large-scale biomedical knowledge graph via masked token prediction to mine disease mechanisms and support drug repurposing in a unified, task-agnostic way. Across five drug discovery tasks (drug–indication, target, adverse reaction, contraindication, and off-label use association), it reports consistent performance gains over specialized baselines, with area under the precision-recall curve improvements ranging from 2.2% to 26%, and it performs better than baselines on external datasets including an expert-curated clinical indications set and drug-disease pair prioritization aligned with ClinicalTrials.gov. It also claims that its generative capability can construct mechanistically plausible subnetworks for biological insight. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.
Abstract
Network medicine leverages large biomedical knowledge graphs (KGs) to model disease mechanisms and identify therapeutic opportunities. However, most deep learning approaches that use KGs in biomedicine remain task-specific, limiting their ability to generalize across diverse applications within a unified framework. Here, we introduce NetMedGPT, a transformer-based foundation model trained on a large-scale biomedical KG using masked token prediction. By learning contextualized representations of biomedical nodes, NetMedGPT enables unified, zero-shot inference across different drug discovery tasks. Specifically, in five tasks, i.e., predicting the association of drugs with indications, targets, adverse drug reactions, contraindications, and off-label uses, NetMedGPT consistently outperforms all specialized baselines, achieving area under the precision-recall curve gains of between 2.2% and 26%. When evaluated on independent external datasets, NetMedGPT outperformed baseline on an expert-curated clinical indications set and also preferentially prioritized clinically relevant drug-disease pairs in ClinicalTrials.gov . NetMedGPT’s generative capability further supports the construction of mechanistically plausible subnetworks offering biological insights. NetMedGPT provides a unified foundation model for network medicine that supports scalable hypothesis generation and provides potential to accelerate drug repurposing. We further provided an interactive interface ( https://prototypes.cosy.bio/chatnetmedgpt/ ) that allows users to obtain model inferences through natural-language queries.
Full text
1,692 characters
· extracted from
oa-doi-fallback
· click to expand
Abstract
Network medicine leverages large biomedical knowledge graphs (KGs) to model disease mechanisms and identify therapeutic opportunities. However, most deep learning approaches that use KGs in biomedicine remain task-specific, limiting their ability to generalize across diverse applications within a unified framework. Here, we introduce NetMedGPT, a transformer-based foundation model trained on a large-scale biomedical KG using masked token prediction. By learning contextualized representations of biomedical nodes, NetMedGPT enables unified, zero-shot inference across different drug discovery tasks. Specifically, in five tasks, i.e., predicting the association of drugs with indications, targets, adverse drug reactions, contraindications, and off-label uses, NetMedGPT consistently outperforms all specialized baselines, achieving area under the precision-recall curve gains of between 2.2% and 26%. When evaluated on independent external datasets, NetMedGPT outperformed baseline on an expert-curated clinical indications set and also preferentially prioritized clinically relevant drug-disease pairs in ClinicalTrials.gov. NetMedGPT’s generative capability further supports the construction of mechanistically plausible subnetworks offering biological insights. NetMedGPT provides a unified foundation model for network medicine that supports scalable hypothesis generation and provides potential to accelerate drug repurposing. We further provided an interactive interface (https://prototypes.cosy.bio/chatnetmedgpt/) that allows users to obtain model inferences through natural-language queries.
Competing Interest Statement
The authors have declared no competing interest.
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.