Machine-Learning-Assisted Approach for Discovering Novel Inhibitors Targeting Bromodomain-Containing Protein 4

Bromodomain-containing protein 4 (BRD4) is implicated in the pathogenesis of a number of different cancers, inflammatory diseases and heart failure. Much effort has been dedicated toward discovering novel scaffold BRD4 inhibitors (BRD4is) with different selectivity profiles and potential antiresistance properties. Structure-based drug design (SBDD) and virtual screening (VS) are the most frequently used approaches. Here, we demonstrate a novel, structure-based VS approach that uses machine-learning algorithms trained on the priori structure and activity knowledge to predict the likelihood that a compound is a BRD4i based on its binding pattern with BRD4. In addition to positive experimental data, such as X-ray structures of BRD4–ligand complexes and BRD4 inhibitory potencies, negative data such as false positives (FPs) identified from our earlier ligand screening results were incorporated into our knowledge base. We used the resulting data to train a machine-learning model named BRD4LGR to predict the BRD4i-likeness of a compound. BRD4LGR achieved a 20–30% higher AUC-ROC than that of Glide using the same test set. When conducting in vitro experiments against a library of previously untested, commercially available organic compounds, the second round of VS using BRD4LGR generated 15 new BRD4is. Moreover, inverting the machine-learning model provided easy access to structure–activity relationship (SAR) interpretation for hit-to-lead optimization.含溴结构域蛋白4（Bromodomain-containing protein 4, BRD4）参与多种癌症、炎症性疾病及心力衰竭的发病机制。学界已投入大量精力开发具备差异化选择性谱与潜在抗耐药特性的新型骨架型BRD4抑制剂（BRD4is）。基于结构的药物设计（Structure-based drug design, SBDD）与虚拟筛选（Virtual screening, VS）是目前最常用的研发策略。本研究提出一种新型基于结构的虚拟筛选方法，该方法依托先验结构与活性知识训练机器学习算法，通过化合物与BRD4的结合模式预测其成为BRD4抑制剂的可能性。除BRD4-配体复合物X射线晶体结构、BRD4抑制活性等阳性实验数据外，本研究还将早期配体筛选结果中鉴定出的假阳性（False positives, FPs）等阴性数据纳入知识库。利用上述数据集训练得到命名为BRD4LGR的机器学习模型，用于预测化合物的BRD4抑制剂类药性。在同一测试集上，BRD4LGR的受试者工作特征曲线下面积（AUC-ROC）较Glide高出20%~30%。针对此前未经过测试的商用有机化合物库开展体外实验时，采用BRD4LGR进行的第二轮虚拟筛选共获得15种新型BRD4抑制剂。此外，对该机器学习模型进行逆向解析，可便捷实现构效关系（Structure–activity relationship, SAR）解读，用于指导从命中化合物到先导化合物的优化工作。