Scholarlink

<p>Accurate drug-target interaction (DTI) prediction is vital to modern discovery workflows, yet models trained in one setting often underperform when chemotypes, protein families, or assay conditions shift. MoleProLink-RL addresses this challenge as a model-first solution that couples chemically faithful representations with geometry-aware alignment and stability-aware decision making. The system combines graph-transformer drug encoders and residual protein embeddings with an unsupervised distribution alignment layer that respects molecular similarity through a DTI-aware transport distance complemented by kernel mean embeddings, while a lightweight reinforcement-learning objective regulates ranking stability across latent sub-environments under a small trust region to a supervised reference. Unlike pipelines that bolt adaptation onto frozen features or tune policies post hoc, MoleProLink-RL trains representation, alignment, and decisions end-to-end so that what the model learns to represent directly improves how it prioritizes candidates under shift. We provide a Fisher–Wasserstein view that clarifies why joint updates are safe in parameter space and effective on distribution space, and we validate the approach on Human, <i>C. elegans</i>, and Davis benchmarks with realistic class imbalance, comprehensive ablations, and diagnostics for calibration and interpretability. The result is a practical, data-efficient DTI model that maintains top-of-list precision when conditions change, narrowing the gap between benchmark performance and laboratory impact.</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

MoleProLink-RL: geometric transport for domain-policy reinforcement learning in drug-target interaction prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月24日

查看全文
  • Donghao Xu,
  • Bibo Wang,
  • Dexing Zhu,
  • Chenzhi Zheng,
  • Haitao Wu,
  • Ruhan Wang,
  • Jinxing Sun,
  • Mingchen Xie,
  • Xu Li,
  • Liang Wu,
  • Chao Zhang

摘要

Accurate drug-target interaction (DTI) prediction is vital to modern discovery workflows, yet models trained in one setting often underperform when chemotypes, protein families, or assay conditions shift. MoleProLink-RL addresses this challenge as a model-first solution that couples chemically faithful representations with geometry-aware alignment and stability-aware decision making. The system combines graph-transformer drug encoders and residual protein embeddings with an unsupervised distribution alignment layer that respects molecular similarity through a DTI-aware transport distance complemented by kernel mean embeddings, while a lightweight reinforcement-learning objective regulates ranking stability across latent sub-environments under a small trust region to a supervised reference. Unlike pipelines that bolt adaptation onto frozen features or tune policies post hoc, MoleProLink-RL trains representation, alignment, and decisions end-to-end so that what the model learns to represent directly improves how it prioritizes candidates under shift. We provide a Fisher–Wasserstein view that clarifies why joint updates are safe in parameter space and effective on distribution space, and we validate the approach on Human, C. elegans, and Davis benchmarks with realistic class imbalance, comprehensive ablations, and diagnostics for calibration and interpretability. The result is a practical, data-efficient DTI model that maintains top-of-list precision when conditions change, narrowing the gap between benchmark performance and laboratory impact.