Centre for Drug Discovery and Molecular Pharmacology, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylor's, 47500, Subang Jaya, Selangor, Malaysia.
School of Pharmacy, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylors, 47500, Subang Jaya, Selangor, Malaysia.
J Comput Aided Mol Des. 2022 Jun;36(6):427-441. doi: 10.1007/s10822-022-00456-3. Epub 2022 May 18.
The recent availability of large numbers of GPCR crystal structures has provided an unprecedented opportunity to evaluate their performance in virtual screening protocols using established benchmarking datasets. In this study, we evaluated the ability of MM/GBSA in consensus scoring-based virtual screening enrichment together with nine classical scoring functions, using the GPCR-Bench dataset consisting of 24 GPCR crystal structures and 254,646 actives and decoys. While the performance of consensus scoring was modest overall, combinations which included MM/GBSA performed relatively well compared to combinations of classical scoring functions. Combinations of MM/GBSA and good-performing scoring functions provided the highest proportion of improvements, with improvements observed in 32% and 19% of all combinations across all targets at the EF and EF levels respectively. Combinations of MM/GBSA and poor-performing scoring functions still outperformed classical scoring functions, with improvements observed in 26% and 17% of all combinations at the EF and EF levels. In comparison, only 14-22% and 6-11% of combinations of classical scoring functions produced improvements at EF and EF respectively. Efforts to improve performance by increasing the number of scoring functions in consensus scoring to three were mostly ineffective. We also observed that consensus scoring performed better for individual scoring functions possessing initially low enrichment factors, potentially implying their benefits are more relevant in such scenarios. Overall, this study demonstrated the first implementation of MM/GBSA in consensus scoring using the GPCR-Bench dataset and could provide a valuable benchmark of the performance of MM/GBSA in comparison to classical scoring functions in consensus scoring for GPCRs.
最近大量的 GPCR 晶体结构的出现为使用已建立的基准数据集评估其在虚拟筛选协议中的性能提供了前所未有的机会。在这项研究中，我们使用由 24 个 GPCR 晶体结构和 254646 个配体和非配体组成的 GPCR-Bench 数据集，评估了基于 MM/GBSA 的共识评分虚拟筛选富集与 9 种经典评分函数相结合的能力。虽然共识评分的性能总体上是适度的，但与经典评分函数的组合相比，包括 MM/GBSA 的组合表现相对较好。包含 MM/GBSA 和表现良好的评分函数的组合提供了最高比例的改进，在所有目标的 EF 和 EF 水平上，分别有 32%和 19%的组合得到了改进。包含 MM/GBSA 和表现不佳的评分函数的组合仍然优于经典评分函数，在 EF 和 EF 水平上，所有组合的改进比例分别为 26%和 17%。相比之下，经典评分函数的组合在 EF 和 EF 水平上分别只有 14-22%和 6-11%的组合得到了改进。通过将共识评分中的评分函数数量增加到三个来提高性能的努力大多是无效的。我们还观察到，共识评分对于初始富集因子较低的单个评分函数表现更好，这可能意味着在这种情况下它们的好处更为相关。总体而言，本研究首次在 GPCR-Bench 数据集中实现了基于 MM/GBSA 的共识评分，并且可以为 MM/GBSA 在 GPCR 共识评分中的性能与经典评分函数进行比较提供有价值的基准。
