Virtual screening (VS) aids in prioritizing unknown bio-interactions between compounds and protein targets for empirical drug discovery. In standard VS exercise, roughly 10% of top-ranked molecules exhibit activity when examined in biochemical assays, which accounts for many false positive hits, making it an arduous task. Attempts for conquering false-hit rates were developed through either ligand-based or structure-based VS separately; however, nonetheless performed remarkably well. Here, we present an advanced VS framework—automated hit identification and optimization tool (A-HIOT)—comprises chemical space-driven stacked ensemble for identification and protein space-driven deep learning architectures for optimization of an array of specific hits for fixed protein receptors. A-HIOT implements numerous open-source algorithms intending to integrate chemical and protein space leading to a high-quality prediction. The optimized hits are the selective molecules which we retrieve after extreme refinement implying chemical space and protein space modules of A-HIOT. Using CXC chemokine receptor 4, we demonstrated the superior performance of A-HIOT for hit molecule identification and optimization with tenfold cross-validation accuracies of 94.8% and 81.9%, respectively. In comparison with other machine learning algorithms, A-HIOT achieved higher accuracies of 96.2% for hit identification and 89.9% for hit optimization on independent benchmark datasets for CXCR4 and 86.8% for hit identification and 90.2% for hit optimization on independent test dataset for androgen receptor (AR), thus, shows its generalizability and robustness. In conclusion, advantageous features impeded in A-HIOT is making a reliable approach for bridging the long-standing gap between ligand-based and structure-based VS in finding the optimized hits for the desired receptor. The complete resource (framework) code is available at https://gitlab.com/neeraj-24/A-HIOT .

中文翻译：

---

用于优化虚拟筛选中的命中选择的机器智能驱动框架

虚拟筛选 (VS) 有助于优先考虑化合物和蛋白质靶标之间的未知生物相互作用，以进行经验性药物发现。在标准的 VS 练习中，大约 10% 的排名靠前的分子在生化分析中表现出活性，这导致了许多假阳性命中，使其成为一项艰巨的任务。通过基于配体或基于结构的 VS 分别开发了克服错误命中率的尝试；然而，仍然表现得非常好。在这里，我们提出了一个先进的 VS 框架——自动命中识别和优化工具 (A-HIOT)——包括用于识别的化学空间驱动的堆叠集成和用于优化固定蛋白质受体的一系列特定命中的蛋白质空间驱动的深度学习架构. A-HIOT 实施了许多旨在整合化学和蛋白质空间的开源算法，从而实现高质量的预测。优化的命中是我们在极端细化后检索到的选择性分子，这意味着 A-HIOT 的化学空间和蛋白质空间模块。使用 CXC 趋化因子受体 4，我们展示了 A-HIOT 在命中分子识别和优化方面的卓越性能，其交叉验证准确度分别为 94.8% 和 81.9%。与其他机器学习算法相比，A-HIOT 在 CXCR4 的独立基准数据集上实现了更高的命中识别准确率和命中优化 89.9%，在雄激素独立测试数据集上命中识别和命中优化分别达到 86.8% 和 90.2%因此，受体（AR）显示出其普遍性和鲁棒性。总之，A-HIOT 中阻碍的优势特征正在为弥合基于配体和基于结构的 VS 之间长期存在的差距以寻找所需受体的优化命中提供一种可靠的方法。完整的资源（框架）代码可在 https://gitlab.com/neeraj-24/A-HIOT 获得。