Scholarlink

<p>Pharmacophores are widely used to describe protein-ligand interactions. In this work, we propose a hybrid framework for binding affinity prediction that combines pharmacophoric maps of the protein binding site with a graph-based representation of the ligand. Our method achieves performance comparable to state-of-the-art models while offering interpretability through attribution methods, thereby demonstrating the potential of pharmacophoric representations in deep learning.</p><p><b>Scientific contribution</b></p><p>We investigate whether a purely pharmacophoric representation of the protein pocket is sufficient to train a deep learning model for affinity prediction. For this purpose, we devise a hybrid model architecture from simple building blocks for affinity prediction. To enhance interpretability, we apply integrated gradients to attribute predictions to individual pharmacophoric features. Source code and model weights are available at <a href="https://github.com/molinfo-vienna/GRIPHIN">https://github.com/molinfo-vienna/GRIPHIN</a>.</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

GRIPHIN: grids of pharmacophore interaction fields for affinity prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月7日

查看全文
  • Daniel Rose,
  • Thomas Seidel,
  • Thierry Langer

摘要

Pharmacophores are widely used to describe protein-ligand interactions. In this work, we propose a hybrid framework for binding affinity prediction that combines pharmacophoric maps of the protein binding site with a graph-based representation of the ligand. Our method achieves performance comparable to state-of-the-art models while offering interpretability through attribution methods, thereby demonstrating the potential of pharmacophoric representations in deep learning.

Scientific contribution

We investigate whether a purely pharmacophoric representation of the protein pocket is sufficient to train a deep learning model for affinity prediction. For this purpose, we devise a hybrid model architecture from simple building blocks for affinity prediction. To enhance interpretability, we apply integrated gradients to attribute predictions to individual pharmacophoric features. Source code and model weights are available at https://github.com/molinfo-vienna/GRIPHIN.