Structural computer-aided design of drugs is an effective modern way of creating targeted drugs. The essence of the method is to use intermolecular docking programs to select a ligand with a high affinity for the target protein. In the present study, we used the example of the search for ligands for the nonselective cationic channel TRPM8 to propose a two-step strategy based on deep neural networks and further verification by intermolecular docking. The strategy consists of using a neural network to screen out potential drug candidates and thereby reduce the list of candidate ligands for verification by intermolecular AutoDock program, which allows assessing the protein's affinity for the ligand by the minimum binding energy and identifying possible ligand conformations upon binding to certain centers of the protein, namely Y745 (Tyr 745 - critical center for TRPM8), R1008 (Phe 1008), and L1009 (Ala 1009). 8 from the ten potential ligands predicted by the neural network revealed minimum binding energy and a greater number of conformations in comparison to the classic TRPM8 ligand, menthol when verified by the AutoDock program. 2 ligands failed to dock, which may be due to insufficient allocated memory of the compute for successful docking or other technical problems. The proposed strategy is universal and will accelerate the search for ligands for various proteins.