BACKGROUND Toll-like receptor 9 is a key innate immune receptor involved in detecting infectious diseases and cancer. TLR9 activates the innate immune system following the recognition of single-stranded DNA oligonucleotides (ODN) containing unmethylated cytosine-guanine (CpG) motifs. Due to the considerable number of rotatable bonds in ODNs, high-throughput in silico screening for potential TLR9 activity via traditional structure-based virtual screening approaches of CpG ODNs is challenging. In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We employed an in-house experimentally validated dataset of 396 single-stranded synthetic ODNs, to compare the results of five machine learning algorithms. Since the dataset was highly imbalanced, we used an ensemble learning approach based on repeated random down-sampling. RESULTS Using in-house experimental TLR9 activity data we found that random forest algorithm outperformed other algorithms for our dataset for TLR9 activity prediction. Therefore, we developed a cross-validated ensemble classifier of 20 random forest models. The average Matthews correlation coefficient and balanced accuracy of our ensemble classifier in test samples was 0.61 and 80.0%, respectively, with the maximum balanced accuracy and Matthews correlation coefficient of 87.0% and 0.75, respectively. We confirmed common sequence motifs including 'CC', 'GG','AG', 'CCCG' and 'CGGC' were overrepresented in mTLR9 agonists. Predictions on 6000 randomly generated ODNs were ranked and the top 100 ODNs were synthesized and experimentally tested for activity in a mTLR9 reporter cell assay, with 91 of the 100 selected ODNs showing high activity, confirming the accuracy of the model in predicting mTLR9 activity. CONCLUSION We combined repeated random down-sampling with random forest to overcome the class imbalance problem and achieved promising results. Overall, we showed that the random forest algorithm outperformed other machine learning algorithms including support vector machines, shrinkage discriminant analysis, gradient boosting machine and neural networks. Due to its predictive performance and simplicity, the random forest technique is a useful method for prediction of mTLR9 ODN agonists.

中文翻译：

---

使用随机森林方法预测新型小鼠 TLR9 激动剂。

背景技术Toll样受体9是参与检测传染病和癌症的关键先天免疫受体。TLR9 在识别含有未甲基化胞嘧啶鸟嘌呤 (CpG) 基序的单链 DNA 寡核苷酸 (ODN) 后激活先天免疫系统。由于 ODN 中存在大量可旋转键，通过传统的基于结构的 CpG ODN 虚拟筛选方法对潜在 TLR9 活性进行高通量计算机筛选具有挑战性。在当前的研究中，我们提出了一种基于机器学习的方法，用于预测新型小鼠 TLR9 (mTLR9) 激动剂，该方法基于基序的计数和位置、基序之间的距离以及图形衍生的特征（例如回转半径和惯性矩） 。我们采用了经过内部实验验证的 396 个单链合成 ODN 数据集，来比较五种机器学习算法的结果。由于数据集高度不平衡，我们使用基于重复随机下采样的集成学习方法。结果使用内部实验 TLR9 活动数据，我们发现随机森林算法在 TLR9 活动预测数据集上优于其他算法。因此，我们开发了 20 个随机森林模型的交叉验证集成分类器。我们的集成分类器在测试样本中的平均马修斯相关系数和平衡精度分别为 0.61 和 80.0%，最大平衡精度和马修斯相关系数分别为 87.0% 和 0.75。我们确认了常见的序列基序，包括“CC”、“GG”、“AG”、“CCCG”和“CGGC”，在 mTLR9 激动剂中出现过多。对 6000 个随机生成的 ODN 进行了预测，合成了前 100 个 ODN，并在 mTLR9 报告细胞测定中对其活性进行了实验测试，100 个选定的 ODN 中有 91 个显示出高活性，证实了模型预测 mTLR9 活性的准确性。结论我们将重复随机下采样与随机森林相结合来克服类别不平衡问题并取得了可喜的结果。总体而言，我们表明随机森林算法优于其他机器学习算法，包括支持向量机、收缩判别分析、梯度提升机和神经网络。由于其预测性能和简单性，随机森林技术是预测 mTLR9 ODN 激动剂的有用方法。