School of life sciences, Northeast Agricultural University, Harbin, PR China; Department of Data and Computing, Northeast Agricultural University, Harbin, PR China.
Department of Data and Computing, Northeast Agricultural University, Harbin, PR China; School of Engineering, Northeast Agricultural University, Harbin, PR China.
Comput Methods Programs Biomed. 2024 Feb;244:108003. doi: 10.1016/j.cmpb.2023.108003. Epub 2023 Dec 31.
Recent studies have emphasized the significance of computational in silico drug-target binding affinity (DTA) prediction in the field of drug discovery and drug repurposing. However, existing DTA prediction approaches suffer from two major deficiencies that impede their progress. Firstly, while most methods primarily focus on the feature representations of drug-target binding affinity pairs, they fail to consider the long-distance relationships of proteins. Furthermore, many deep learning-based DTA predictors simply model the interaction of drug-target pairs through concatenation, which hampers the ability to enhance prediction performance.
To address these issues, this study proposes a novel framework named TransVAE-DTA, which combines the transformer and variational autoencoder (VAE). Inspired by the early success of VAEs, we aim to further investigate the feasibility of VAEs for drug structure encoding, while utilizing the transformer architecture for target feature representation. Additionally, an adaptive attention pooling (AAP) module is designed to fuse the drug and target encoded features. Notably, TransVAE-DTA is proven to maximize the lower bound of the joint likelihood of drug, target, and their DTAs.
Experimental results demonstrate the superiority of TransVAE-DTA in drug-target binding affinity prediction assignments on two public Davis and KIBA datasets.
In this research, the developed TransVAE-DTA opens a new avenue for engineering drug-target interactions.
最近的研究强调了计算药物靶标结合亲和力（DTA）预测在药物发现和药物再利用领域的重要性。然而，现有的 DTA 预测方法存在两个主要缺陷，阻碍了它们的发展。首先，虽然大多数方法主要关注药物靶标结合亲和力对的特征表示，但它们没有考虑蛋白质的远距离关系。此外，许多基于深度学习的 DTA 预测器只是通过串联来模拟药物靶标对的相互作用，这阻碍了提高预测性能的能力。
为了解决这些问题，本研究提出了一种名为 TransVAE-DTA 的新框架，它结合了转换器和变分自动编码器（VAE）。受 VAEs 早期成功的启发，我们旨在进一步研究 VAEs 用于药物结构编码的可行性，同时利用转换器架构进行目标特征表示。此外，设计了自适应注意池（AAP）模块来融合药物和目标编码特征。值得注意的是，TransVAE-DTA 被证明可以最大化药物、靶标及其 DTA 的联合似然的下界。
实验结果表明，在两个公共的 Davis 和 KIBA 数据集上，TransVAE-DTA 在药物靶标结合亲和力预测任务中具有优越性。
在这项研究中，开发的 TransVAE-DTA 为工程药物靶标相互作用开辟了新途径。
