Discriminations of active from inactive HDAC8 inhibitors Part II: Bayesian classification study to find molecular fingerprints

In continuation of our earlier work (Doi: 10.1080/07391102.2019.1661876), a statistically validated and robust Bayesian model was developed on a large diverse set of HDAC8 inhibitors. The training set comprised of 676 small molecules and 293 compounds were considered as test set molecules. The findings of this analysis will help to explore some major directions regarding the HDAC8 inhibitor designing approach. Acrylamide (G1-G3, G9), <i>N</i>-substituted 2-phenylimidazole (G4-G8, G9, G12-G13, G16-G19), benzimidazole (G10-G11), piperidine substituted pyrrole (G13-G14) groups, alkyl/aryl amide (G15) and aryloxy carboxamide (G20) fingerprints were found to play a crucial role in HDAC8 inhibitory activity whereas -CH-N=CH- (B1, B4-B6, B14) motif, benzamide (B2-B3, B9-B13, B16-B17) groups and heptazepine (B7-B8, B15, B18-B20) group were found to influence negatively the HDAC8 inhibitory activity. The importance of such fingerprints was further validated by the HDAC8 enzyme and related inhibitor interactions at the receptor level. These results are in close agreement with those of our previous work that validate each other. Moreover, this comparative learning may enrich future endeavours regarding the designing strategy of HDAC8 inhibitors.

本研究延续了我们此前的工作（DOI: 10.1080/07391102.2019.1661876），针对大型多样化的组蛋白去乙酰化酶8（HDAC8）抑制剂数据集，构建了经统计学验证的稳健贝叶斯模型。训练集包含676个小分子化合物，293个化合物被用作测试集。本分析所得结果可为HDAC8抑制剂的设计思路探索重要方向。研究发现，丙烯酰胺（G1~G3、G9）、N-取代2-苯基咪唑（G4~G8、G9、G12~G13、G16~G19）、苯并咪唑（G10~G11）、哌啶取代吡咯（G13~G14）基团、烷基/芳基酰胺（G15）以及芳氧基甲酰胺（G20）等分子指纹特征，对HDAC8抑制活性具有关键促进作用；而-CH-N=CH-（B1、B4~B6、B14）结构基序、苯甲酰胺（B2~B3、B9~B13、B16~B17）基团以及七元氮杂卓（B7~B8、B15、B18~B20）基团，则会对HDAC8抑制活性产生负面影响。此类分子指纹特征的重要性，进一步通过受体水平下HDAC8酶与对应抑制剂的相互作用实验得到验证。本研究结果与此前工作的结论高度吻合，二者可相互佐证。此外，本次对比学习研究可为未来HDAC8抑制剂的设计策略研究提供更多有益参考。