Accurate determination of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a two-staged graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. We first describe an unsupervised graph-autoencoder to learn meaningful protein pocket representations. Two Graph-CNNs are then trained to automatically extract features from pocket graphs and 2D molecular graphs, respectively. We demonstrate that graph-autoencoders can learn meaningful fixed-size representation for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand co-complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark datasets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks recognize meaningful interactions between pockets and ligands.