Laboratory of Chemoinformatics, UMR 7177 University of Strasbourg/CNRS, 4 rue B. Pascal, 67000 Strasbourg, France.
J Chem Inf Model. 2013 Apr 22;53(4):763-72. doi: 10.1021/ci300200r. Epub 2013 Mar 29.
We herewith present a novel approach to predict protein-ligand binding modes from the single two-dimensional structure of the ligand. Known protein-ligand X-ray structures were converted into binary bit strings encoding protein-ligand interactions. An artificial neural network was then set up to first learn and then predict protein-ligand interaction fingerprints from simple ligand descriptors. Specific models were constructed for three targets (CDK2, p38-α, HSP90-α) and 146 ligands for which protein-ligand X-ray structures are available. These models were able to predict protein-ligand interaction fingerprints and to discriminate important features from minor interactions. Predicted interaction fingerprints were successfully used as descriptors to discriminate true ligands from decoys by virtual screening. In some but not all cases, the predicted interaction fingerprints furthermore enable to efficiently rerank cross-docking poses and prioritize the best possible docking solutions.
我们在此提出了一种新的方法，可从配体的单个二维结构预测蛋白质-配体的结合模式。已知的蛋白质-配体 X 射线结构被转换为编码蛋白质-配体相互作用的二进制位串。然后建立一个人工神经网络，首先从简单的配体描述符中学习，然后预测蛋白质-配体相互作用指纹。为三个靶标（CDK2、p38-α、HSP90-α）和 146 个具有蛋白质-配体 X 射线结构的配体构建了特定的模型。这些模型能够预测蛋白质-配体相互作用指纹，并区分重要特征和次要相互作用。预测的相互作用指纹成功地用作描述符，通过虚拟筛选从诱饵中区分真正的配体。在某些情况下（但不是所有情况），预测的相互作用指纹还能够有效地重新排列对接构象，并优先考虑最佳的对接解决方案。
