Combined application of cheminformatics- and physical force field-based scoring functions improves binding affinity prediction for CSAR data sets.
Combined application of cheminformatics- and physical force field-based scoring functions improves binding affinity prediction for CSAR data sets.
复制标题
DOI：
10.1021/ci200146e
复制
发表时间：
2011-09-26
影响因子：
5.6
通讯作者：
Tropsha A
中科院分区：
文献类型：
--
作者：
Hsieh JH;Yin S;Liu S;Sedykh A;Dokholyan NV;Tropsha A
策划的CSAR-NRC基准集为测试或比较现有和新颖评分功能的性能提供了有价值的机会。我们应用了两种不同的评分函数，分别独立和组合，来预测CSAR-NRC数据集中配体的结合亲和力。一种是本文首次报道的，利用蛋白质-配体界面的多种化学-几何描述符来建立定量结构-结合亲和关系（QSBAR）模型；然后使用这些模型来预测外部数据集中配体的结合亲和力。第二个是基于物理力场的评分功能，MedusaScore。结果表明，两种评分函数的预测精度均具有统计学意义，QSBAR模型的实际与预测结合亲和力的平方相关系数（R2）为0.44/0.53 (Set1/Set2)， MedusaScore模型的相关系数为0.34/0.47 （Set1/Set2）。重要的是，我们发现将QSBAR模型和MedusaScore组合成共识评分函数的预测精度比任何贡献方法都高，R2为0.45/0.58 （Set1/Set2）。此外，我们确定了几种化学特征和非共价相互作用，这些特征和非共价相互作用可能导致本研究中使用的评分函数不准确地预测了几种配体的结合亲和力。
The curated CSAR-NRC benchmark sets provide valuable opportunity for testing or comparing the performance of both existing and novel scoring functions. We apply two different scoring functions, both independently and in combination, to predict binding affinity of ligands in the CSAR-NRC datasets. One, reported here for the first time, employs multiple chemical-geometrical descriptors of the protein-ligand interface to develop Quantitative Structure – Binding Affinity Relationships (QSBAR) models; these models are then used to predict binding affinity of ligands in the external dataset. Second is a physical force field-based scoring function, MedusaScore. We show that both individual scoring functions achieve statistically significant prediction accuracies with the squared correlation coefficient (R2) between actual and predicted binding affinity of 0.44/0.53 (Set1/Set2) with QSBAR models and 0.34/0.47 (Set1/Set2) with MedusaScore. Importantly, we find that the combination of QSBAR models and MedusaScore into consensus scoring function affords higher prediction accuracy than any of the contributing methods achieving R2 of 0.45/0.58 (Set1/Set2). Furthermore, we identify several chemical features and non-covalent interactions that may be responsible for the inaccurate prediction of binding affinity for several ligands by the scoring functions employed in this study.