结合电势信息可显著提升蛋白质表面形状检索效果。
SHREC 2025: Protein surface shape retrieval including electrostatic potential
- 融合分子表面形状与静电势的检索方法表现最优。
- 在11,555个蛋白表面数据上，综合指标达到最高。
- 尤其对小样本类别有效，适合结构生物学家使用。
本次SHREC 2025蛋白质表面形状检索赛道共有9支队伍参与。我们在包含11,555个蛋白质表面的大规模数据集上评估了15种方法的检索性能，该数据集包含计算得到的静电势（关键分子表面描述符）。通过准确率、平衡准确率、F1分数、精确率和召回率等指标进行评估，结果显示：结合静电势与分子表面形状的方法取得了最佳检索性能。该结论在数据量有限的类别中同样成立，凸显了引入额外分子表面描述符的重要性。
原文摘要 · Abstract (English)
This SHREC 2025 track dedicated to protein surface shape retrieval involved 9 participating teams. We evaluated the performance in retrieval of 15 proposed methods on a large dataset of 11,555 protein surfaces with calculated electrostatic potential (a key molecular surface descriptor). The performance in retrieval of the proposed methods was evaluated through different metrics (Accuracy, Balanced accuracy, F1 score, Precision and Recall). The best retrieval performance was achieved by the proposed methods that used the electrostatic potential complementary to molecular surface shape. This observation was also valid for classes with limited data which highlights the importance of taking into account additional molecular surface descriptors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。