Scholarlink

<p>Predicting drug-disease associations (DDA) is severely hindered by extreme data sparsity and the positive-unlabeled (PU) nature of biomedical datasets, where unobserved pairs are often misidentified as true negatives. To prevent negative label contamination and information leakage commonly observed in end-to-end models, we propose a two-stage framework that decouples representation learning from link verification. The first stage performs offline contrastive representation learning on a heterogeneous graph via a dual-view graph attention mechanism and node-level InfoNCE loss, learning discriminative embeddings without adjacency reconstruction or premature negative assumptions. The second stage applies subgraph embedding-based link prediction (SEAL) verification by extracting k-hop enclosing subgraphs with target-edge removal. By combining a negative sampling strategy under the PU setting that integrates easy and hard negatives, the framework enables robust training under open-world settings. Experimental results under ten-fold cross-validation demonstrate that the proposed method achieves an AUC of 0.9406 and an AUPR of 0.9461 on the benchmark Cdataset, outperforming several competitive baselines and confirming its effectiveness under extreme sparsity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A two-stage framework with contrastive representation learning for drug-disease association prediction under positive-unlabeled learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Thi Huong Lan Nguyen,
  • Tho Hoan Pham,
  • Van Tinh Nguyen,
  • Dang Hung Tran

摘要

Predicting drug-disease associations (DDA) is severely hindered by extreme data sparsity and the positive-unlabeled (PU) nature of biomedical datasets, where unobserved pairs are often misidentified as true negatives. To prevent negative label contamination and information leakage commonly observed in end-to-end models, we propose a two-stage framework that decouples representation learning from link verification. The first stage performs offline contrastive representation learning on a heterogeneous graph via a dual-view graph attention mechanism and node-level InfoNCE loss, learning discriminative embeddings without adjacency reconstruction or premature negative assumptions. The second stage applies subgraph embedding-based link prediction (SEAL) verification by extracting k-hop enclosing subgraphs with target-edge removal. By combining a negative sampling strategy under the PU setting that integrates easy and hard negatives, the framework enables robust training under open-world settings. Experimental results under ten-fold cross-validation demonstrate that the proposed method achieves an AUC of 0.9406 and an AUPR of 0.9461 on the benchmark Cdataset, outperforming several competitive baselines and confirming its effectiveness under extreme sparsity.