Conditional domain adversarial learning presents a promising approach for enhancing the generalizability of deep learning-based methods. Inspired by the efficacy of conditional domain adversarial networks, Bai and colleagues introduced DrugBAN, a methodology designed to explicitly learn pairwise local interactions between drugs and targets. DrugBAN leverages drug molecular graphs and target protein sequences, employing conditional domain adversarial networks to improve the ability to adapt to out-of-distribution data and thereby ensuring superior prediction accuracy for new drug–target pairs. Here we examine the reusability of DrugBAN and extend the evaluation of its generalizability across a wider range of biomedical contexts beyond the original datasets. Various clustering-based strategies are implemented to resplit the source and target domains to assess the robustness of DrugBAN. We also apply this cross-domain adaptation technique to the prediction of cell line–drug responses and mutation–drug associations. The analysis serves as a stepping-off point to better understand and establish a general template applicable to link prediction tasks in biomedical bipartite networks.

条件域对抗性学习为增强基于深度学习的方法的通用性提供了一种有前途的方法。受到条件域对抗网络功效的启发，Bai 和同事推出了 DrugBAN，这是一种旨在明确学习药物和靶点之间成对局部相互作用的方法。 DrugBAN 利用药物分子图和靶蛋白序列，采用条件域对抗网络来提高适应分布外数据的能力，从而确保新药物-靶点对的卓越预测准确性。在这里，我们检查了 DrugBAN 的可重用性，并将对其普遍性的评估扩展到原始数据集之外的更广泛的生物医学环境中。实施各种基于聚类的策略来重新划分源域和目标域，以评估 DrugBAN 的稳健性。我们还将这种跨域适应技术应用于细胞系药物反应和突变药物关联的预测。该分析作为更好地理解和建立适用于生物医学二分网络中链接预测任务的通用模板的起点。