Background: HIV-1 Integrase (IN) is an important target for the development of the new anti-AIDS drugs. HIV-1 LEDGF/p75 inhibitors, which block the integrase and LEDGF/p75 interaction, have been validated for reduction in HIV-1 viral replicative capacity.

Methods: In this work, computational Quantitative Structure-Activity Relationship (QSAR) models were developed for predicting the bioactivity of HIV-1 integrase LEDGF/p75 inhibitors. We collected 190 inhibitors and their bioactivities in this study and divided the inhibitors into nine scaffolds by the method of T-distributed Stochastic Neighbor Embedding (TSNE). These 190 inhibitors were split into a training set and a test set according to the result of a Kohonen’s self-organizing map (SOM) or randomly. Multiple Linear Regression (MLR) models, support vector machine (SVM) models and two consensus models were built based on the training sets by 20 selected CORINA Symphony descriptors.

Results: All the models showed a good prediction of pIC50. The correlation coefficients of all the models were more than 0.7 on the test set. For the training set of consensus Model C1, which performed better than other models, the correlation coefficient(r) achieved 0.909 on the training set, and 0.804 on the test set.

Conclusion: The selected molecular descriptors show that hydrogen bond acceptor, atom charges and electronegativities (especially π atom) were important in predicting the activity of HIV-1 integrase LEDGF/p75-IN inhibitors.

背景：HIV-1整合酶（IN）是开发新型抗艾滋病药物的重要靶点。阻断整合酶和 LEDGF/p75 相互作用的 HIV-1 LEDGF/p75 抑制剂已被证实可降低 HIV-1 病毒的复制能力。

方法：在这项工作中，开发了计算定量结构-活性关系 (QSAR) 模型来预测 HIV-1 整合酶 LEDGF/p75 抑制剂的生物活性。我们在本研究中收集了 190 种抑制剂及其生物活性，并通过 T 分布随机邻域嵌入 (TSNE) 的方法将抑制剂分为 9 个支架。根据 Kohonen 自组织图 (SOM) 的结果或随机将这 190 个抑制剂分成训练集和测试集。多重线性回归 (MLR) 模型、支持向量机 (SVM) 模型和两个共识模型是基于 20 个选定的 CORINA Symphony 描述符的训练集构建的。

结果：所有模型都显示出对 pIC50 的良好预测。所有模型在测试集上的相关系数均大于0.7。对于性能优于其他模型的共识模型 C1 的训练集，相关系数 (r) 在训练集上达到 0.909，在测试集上达到 0.804。

结论：选定的分子描述符表明氢键受体、原子电荷和电负性（尤其是 π 原子）对于预测 HIV-1 整合酶 LEDGF/p75-IN 抑制剂的活性很重要。