In silico target prediction of compounds plays an important role in drug discovery. The chemical similarity ensemble approach (SEA) is a promising method, which has been successfully applied in many drug-related studies. There are various models available analogous to SEA, because this approach is based on different types of molecular fingerprints. To investigate the influence of training data selection and the complementarity of different models, several SEA models were constructed and tested. When we used a test set of 37,138 positive and 42,928 negative ligand-target interactions, among the five tested molecular fingerprint methods, at significance level 0.05, Topological-based model yielded the best precision rate (83.7 %) and $${F_{0.25}{\text{-}}Measure}$$ (0.784) while Atom pair-based model yielded the best $$F_{0.5}{\text{-}}Measure$$ (0.694). By employing an election system to combine the five models, a flexible prediction scheme was achieved with precision range from 71 to 90.6 %, $$F_{0.5}{\text{-}}Measure$$ range from 0.663 to 0.684 and $$F_{0.25}{\text{-}}Measure$$ range from 0.696 to 0.817. The overall effectiveness of all of the five models could be ranked in decreasing order as follows: Atom pair $$\approx$$ Topological > Morgan > MACCS > Pharmacophore. Combining multiple SEA models, which takes advantages of different models, could be used to improve the success rates of the models. Another possibility of improving the model could be using target-specific classes or more active compounds.

中文翻译：

---

改进目标预测中的化学相似性集成方法。


化合物的计算机靶点预测在药物发现中发挥着重要作用。化学相似性集成方法（SEA）是一种很有前景的方法，已成功应用于许多药物相关研究。有多种类似于 SEA 的模型可用，因为这种方法基于不同类型的分子指纹。为了研究训练数据选择的影响和不同模型的互补性，构建并测试了几个 SEA 模型。当我们使用包含 37,138 个正配体-靶标相互作用和 42,928 个负配体-靶标相互作用的测试集时，在五种测试的分子指纹方法中，显着性水平为 0.05，基于拓扑的模型产生了最佳的精确率 (83.7 %) 和 $${F_{0.25 }{\text{-}}Measure}$$ (0.784)，而基于原子对的模型产生了最佳的$$F_{0.5}{\text{-}}Measure$$ (0.694)。通过采用选举系统结合五个模型，实现了灵活的预测方案，精度范围为 71% 至 90.6%，$$F_{0.5}{\text{-}}Measure$$ 范围为 0.663 至 0.684，$$ F_{0.25}{\text{-}}测量$$范围从 0.696 到 0.817。所有五个模型的整体有效性可以按降序排列如下： 原子对 $$\approx$$ 拓扑 > 摩根 > MACCS > 药效团。结合多个SEA模型，发挥不同模型的优点，可以提高模型的成功率。改进模型的另一种可能性是使用特定目标类别或更活性的化合物。