School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055, China.
Department of Computing, The Hong Kong Polytechnic University, Hong Kong 810005, China.
Int J Mol Sci. 2019 Jul 12;20(14):3425. doi: 10.3390/ijms20143425.
Transcription factor binding sites (TFBSs) play an important role in gene expression regulation. Many computational methods for TFBS prediction need sufficient labeled data. However, many transcription factors (TFs) lack labeled data in cell types. We propose a novel method, referred to as DANN_TF, for TFBS prediction. DANN_TF consists of a feature extractor, a label predictor, and a domain classifier. The feature extractor and the domain classifier constitute an Adversarial Network, which ensures that learned features are common features across different cell types. DANN_TF is evaluated on five TFs in five cell types with a total of 25 cell-type TF pairs and compared to a baseline method which does not use Adversarial Network. For both data augmentation and cross-cell-type prediction, DANN_TF performs better than the baseline method on most cell-type TF pairs. DANN_TF is further evaluated by an additional 13 TFs in the five cell types with a total of 65 cell-type TF pairs. Results show that DANN_TF achieves significantly higher AUC than the baseline method on 96.9% pairs of the 65 cell-type TF pairs. This is a strong indication that DANN_TF can indeed learn common features for cross-cell-type TFBS prediction.
转录因子结合位点 (TFBSs) 在基因表达调控中起着重要作用。许多用于 TFBS 预测的计算方法都需要充足的标记数据。然而，许多转录因子 (TFs) 在细胞类型中缺乏标记数据。我们提出了一种新的方法，称为 DANN_TF，用于 TFBS 预测。DANN_TF 由特征提取器、标签预测器和域分类器组成。特征提取器和域分类器构成了一个对抗网络，确保学习到的特征是不同细胞类型共有的特征。在五种细胞类型中的五个 TF 上评估了 DANN_TF，共有 25 对细胞类型 TF，与不使用对抗网络的基线方法进行了比较。对于数据增强和跨细胞类型预测，DANN_TF 在大多数细胞类型 TF 对中都优于基线方法。DANN_TF 还在五种细胞类型中的另外 13 个 TF 上进行了评估，共有 65 对细胞类型 TF。结果表明，在 65 对细胞类型 TF 对中，DANN_TF 在 96.9%的对上的 AUC 显著高于基线方法。这强烈表明 DANN_TF 确实可以学习跨细胞类型 TFBS 预测的共同特征。
