Following identification of a target protein, hit identification, which finds small organic molecules that bind to the target, is an important first step of a structure-based drug design project. In this study, we demonstrate a target-specific drug design method that can autonomously generate a series of target-favorable compounds. This method utilizes the seq2seq model based on a deep learning algorithm and a water pharmacophore. Water pharmacophore models are used to screen compounds that are favorable to a given target in a large compound database, and seq2seq compound generators are used to train the screened compounds and generate entirely new compounds based on the training model. Our method was tested through binding energy calculation studies of six pharmaceutically relevant targets in the directory of useful decoys (DUD) set with docking. The compounds generated by our method had lower average binding energies than decoy compounds in five out of six cases and included a number of compounds that had lower binding energies than the average binding energies of the active compounds in four cases. The generated compound lists for these four cases featured compounds with lower binding energies than even the most active compounds.