Efficient drug discovery hinges on the accurate prediction of interactions between potential drugs and target proteins. Deep learning models have shown promise in this domain; however, their adoption can be challenging for individuals not well-versed in both computer science and cheminformatics. In response to this challenge, we present DeepPurpose, an extensive and user-friendly deep learning library tailored for drug-target interaction (DTI) prediction. DeepPurpose offers a range of features, including the ability to customize interaction types through chemical and protein encoders, as well as access to over 50 neural architectures. As the effectiveness of existing aseptic medications diminishes, the identification of viable DTIs becomes pivotal in the drug development process. DeepPurpose employs an encoder-decoder structure to model interactions, taking compound SMILES strings and pairs of protein amino acid sequences as inputs. The system generates a binding affinity score for the given compound-protein pair. To achieve this, DeepPurpose encodes input proteins and compounds using multiple deep learning encoders, combining their deep embeddings and passing them through a deep neural network decoder to determine binding propensity. DeepPurpose represents a valuable tool in the field of drug discovery, providing researchers with accessible and effective means to predict and explore potential drug-target interactions. Its user-friendly design and comprehensive functionality aim to bridge the gap between deep learning and DTI prediction for a wider audience of researchers and practitioners.