PulseAugur
实时 12:24:15
English(EN) Benchmarking Single-Pose Docking, Consensus Rescoring, and Supervised ML on the LIT-PCBA Library: A Critical Evaluation of DiffDock, AutoDock-GPU, GNINA, and DiffDock-NMDN

AI和ML方法在虚拟筛选基准测试中显示出适度收益

一篇新论文批判性地评估了包括DiffDock和GNINA在内的几种基于AI的对接工具在LIT-PCBA库上的表现。研究发现,AutoDock-GPU结合GNINA重评分在单一方法中表现最佳。然而,监督式机器学习重新排序带来了最显著的改进,将最佳单一评分器的性能提升了110%。 AI

影响 强调即使是先进的AI对接工具在现实基准测试中也只提供适度的富集,突出了混合经典+ML工作流程的价值。

排序理由 这是一篇评估特定基准上现有AI模型的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

AI和ML方法在虚拟筛选基准测试中显示出适度收益

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Youssef Abo-Dahab, Xiaoiang Xiang, Xiaoiang Xiang, Xiaoiang Xiang ·

    Benchmarking Single-Pose Docking, Consensus Rescoring, and Supervised ML on the LIT-PCBA Library: A Critical Evaluation of DiffDock, AutoDock-GPU, GNINA, and DiffDock-NMDN

    arXiv:2605.01681v1 Announce Type: new Abstract: Virtual screening performance depends heavily on the chosen docking and scoring methods. Recent AI-based tools such as DiffDock and NMDN have reported strong benchmark results, but their practical utility on realistic, experimentall…