DiffDock实际表现不如传统方法，依赖近似数据表检索。
Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows
- 用自动流程构建公平基线，对比DiffDock与传统对接方法
- 已知结合位点下Surflex-Dock成功率68%/81%，远超DiffDock的45%/51%
- 模型实为近似数据查找，无法应对无训练近邻的新情况
扩散学习方法DiffDock用于小分子配体对接蛋白结合位点，近期声称性能优于传统方法。本文采用全自动流程使用Surflex-Dock生成传统方法的公平基线。在已知结合位点条件下，Surflex-Dock在2.0埃RMSD下的命中率（Top-1/Top-5）分别为68%/81%，显著高于DiffDock的45%/51%；Glide表现类似（67%/73%），AutoDock Vina与Gnina也呈此趋势。在未知结合位点条件下，通过自动识别多个结合口袋，Surflex-Dock仍优于DiffDock，但差距缩小。DiffDock基于约17,000个共结晶结构（98% PDBBind 2020 pre-2019）训练，测试集为363例（2% PDBBind 2020 2019年后数据）。其性能在超过一半测试案例中依赖训练集中近似相同的蛋白-配体复合物。存在近邻训练案例时，成功率比无近邻者高40个百分点（占测试集三分之二）。表明DiffDock实际编码了类似查表机制，限制其泛化能力，且未达到现代高效对接工作流的竞争力。
原文摘要 · Abstract (English)
The diffusion learning method, DiffDock, for docking small-molecule ligands into protein binding sites was recently introduced. Results included comparisons to more conventional docking approaches, with DiffDock showing superior performance. Here, we employ a fully automatic workflow using the Surflex-Dock methods to generate a fair baseline for conventional docking approaches. Results were generated for the common and expected situation where a binding site location is known and also for the condition of an unknown binding site. For the known binding site condition, Surflex-Dock success rates at 2.0 Angstroms RMSD far exceeded those for DiffDock (Top-1/Top-5 success rates, respectively, were 68/81% compared with 45/51%). Glide performed with similar success rates (67/73%) to Surflex-Dock for the known binding site condition, and results for AutoDock Vina and Gnina followed this pattern. For the unknown binding site condition, using an automated method to identify multiple binding pockets, Surflex-Dock success rates again exceeded those of DiffDock, but by a somewhat lesser margin. DiffDock made use of roughly 17,000 co-crystal structures for learning (98% of PDBBind version 2020, pre-2019 structures) for a training set in order to predict on 363 test cases (2% of PDBBind 2020) from 2019 forward. DiffDock's performance was inextricably linked with the presence of near-neighbor cases of close to identical protein-ligand complexes in the training set for over half of the test set cases. DiffDock exhibited a 40 percentage point difference on near-neighbor cases (two-thirds of all test cases) compared with cases with no near-neighbor training case. DiffDock has apparently encoded a type of table-lookup during its learning process, rendering meaningful applications beyond its reach. Further, it does not perform even close to competitively with a competently run modern docking workflow.
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。