UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning

• URL: http://arxiv.org/abs/2606.01394v1
• Date: Sun, 31 May 2026 18:36:41 GMT
• Title: UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning
• Abstract summary: We introduce UniD$3$, a unified framework that integrates Large Language Models with Knowledge Graph-enhanced Retrieval-Augmented Generation (KG-RAG)<n>UniD$3$ processes 157,849 PubMed articles with Llama 3.3-70B and constructs knowledge graphs via a dual-stage strategy.<n>These graphs support KG-RAG-based generation of structured datasets, evaluated through external benchmarks, fuzzy matching with curated resources, and clinician review.
• Score: 10.616744261460376
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Systematic characterization of drug-disease relationships is essential for drug discovery and repurposing, yet is hindered by the heterogeneity and rapid growth of biomedical literature. Existing datasets rely on labor-intensive curation and are often incomplete, while LLM-only approaches suffer from hallucination and weak evidence grounding. We introduce UniD$^3$, a unified framework that integrates Large Language Models with Knowledge Graph-enhanced Retrieval-Augmented Generation (KG-RAG) to extract, organize, and validate drug-disease knowledge across Drug-Disease Matching (DDM), Drug Effectiveness Assessment (DEA), and Drug-Target Analysis (DTA). UniD$^3$ processes 157,849 PubMed articles with Llama 3.3-70B and constructs knowledge graphs via a dual-stage strategy combining paper-level extraction with KG-level consolidation centered on drug and disease entities. These graphs support KG-RAG-based generation of structured datasets, evaluated through external benchmarks, fuzzy matching with curated resources, and clinician review. UniD$^3$ produces six knowledge graphs and large-scale datasets, including 28,915 DDM, 15,042 DEA, and over 4,000 DTA QA pairs. External validation shows strong performance (F1: 0.85-0.87 for DDM/DEA; 0.82 for DTA), with clinician review confirming high reliability (AUROC = 0.90). KG-RAG-augmented models outperform standalone LLMs, and the UniD$^3$ chatbot enables interpretable, citation-supported exploration of drug-disease relationships. UniD$^3$ provides a scalable, extensible framework for transforming unstructured biomedical literature into high-quality, structured drug-disease knowledge, supporting AI-driven discovery, repurposing, and precision medicine.

Related papers

• DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing [55.45112712244231]
  DrugReason is a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing.<n> Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines.
  arXiv  Detail & Related papers  (2026-09-06T18:54:26Z)
• Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach [62.0906177191353]
  Existing approaches distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL)<n>We propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework.<n>Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions.<n>We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled data, followed by supervised RL on the human-annotated real data
  arXiv  Detail & Related papers  (2026-04-13T14:37:38Z)
• SIDEKICK: A Semantically Integrated Resource for Drug Effects, Indications, and Contraindications [11.439066289590878]
  Sidekick is a knowledge graph that standardizes drug indications, contraindications, and adverse reactions from FDA Structured Product Labels.<n>We processed over 50,000 drug labels and mapped terms to the Human Phenotype Ontology (HPO), the MONDO Disease Ontology, and RxNorm.<n>Sidekick enables automated safety-based similarity analysis for drug repurposing.
  arXiv  Detail & Related papers  (2025-12-06T17:35:07Z)
• MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning [4.579424650757833]
  Supervised Fine-Tuning (SFT) on existing datasets often leads to poor generalization on unseen modalities and tasks.<n>We introduce Generative Reward Learning for Medical Reasoning (MedGR$2$), a novel framework that creates a self-improving virtuous cycle.<n>Our experiments demonstrate that SFT with MedGR$2$-produced data already surpasses baselines trained on large-scale, human-curated datasets.
  arXiv  Detail & Related papers  (2025-08-28T08:41:32Z)
• MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph [57.54231831309079]
  We introduce MedKGent, a framework for constructing temporally evolving medical Knowledge Graphs.<n>We simulate the emergence of biomedical knowledge via a fine-grained daily time series.<n>The resulting KG contains 156,275 entities and 2,971,384 relational triples.
  arXiv  Detail & Related papers  (2025-08-17T15:14:03Z)
• Retrieval Augmented Large Language Model System for Comprehensive Drug Contraindications [0.0]
  The versatility of large language models (LLMs) has been explored across various sectors, but their application in healthcare poses challenges.<n>This study enhances the capability of LLMs to address contraindications effectively by implementing a Retrieval Augmented Generation (RAG) pipeline.
  arXiv  Detail & Related papers  (2025-08-08T09:09:03Z)
• RAG-based Architectures for Drug Side Effect Retrieval in LLMs [0.0]
  Large Language Models (LLMs) offer promising conversational interfaces, but their inherent limitations hinder their reliability in specialized fields like pharmacovigilance.<n>We propose two architectures: Retrieval-Augmented Generation (RAG) and GraphRAG, which integrate comprehensive drug side effect knowledge into a Llama 3 8B language model.
  arXiv  Detail & Related papers  (2025-07-18T11:20:52Z)
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery [54.79763887844838]
  Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
  arXiv  Detail & Related papers  (2025-05-20T05:18:15Z)
• Boosting drug-disease association prediction for drug repositioning via dual-feature extraction and cross-dual-domain decoding [9.721502993958193]
  We propose a new model called Dual-Feature Drug Repurposing Neural Network (DFDRNN)<n> DFDRNN allows the mining of two features (similarity and association) from the drug-disease biomedical networks to encode drugs and diseases.<n>Our proposed DFDRNN model outperforms six state-of-the-art methods on four benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-16T15:02:18Z)
• Drug Synergistic Combinations Predictions via Large-Scale Pre-Training and Graph Structure Learning [82.93806087715507]
  Drug combination therapy is a well-established strategy for disease treatment with better effectiveness and less safety degradation. Deep learning models have emerged as an efficient way to discover synergistic combinations. Our framework achieves state-of-the-art results in comparison with other deep learning-based methods.
  arXiv  Detail & Related papers  (2023-01-14T15:07:43Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.