We present a complete dataset of self-assembled structures of sequence-defined polyethylene oxide (PEO), polybutadiene (PBD) copolymers in water with a fixed degree of polymerization. The dataset was acquired from coarse-grained molecular dynamics simulations parameterized using the Martini 3 force field. We simulated all (16,512) unique macromolecular sequences of 15 two-monomer repeat units (corresponding to 30 chemical monomers) across the full composition range from homopolymers to 50:50 copolymers. Each dataset entry consists of a simulation of 500 identical polymer chains in solution, equilibrated from random initial conditions and integrated for 200 nanoseconds to form stable, self-assembled aggregates. The simulation procedure is as follows. Chains are initialized as random walks. The box is filled with Martini water beads. We then used the Fast Inertial Relaxation Engine (FIRE) energy minimization method to remove any particle overlaps. The temperature and density are equilibrated through successive constant volume (NVT) and constant pressure (NPT) simulation. Production runs are then performed in a constant volume (NVT) ensemble. All simulations were performed using HOOMD-Blue version 4.8.2 on the Roar cluster. There are two dataset folders: * peo_pbd_martini_dataset contains all the information that was generated. This includes init, with the initial configuration, fire, with the configuration after the FIRE energy minimization, cv, with the configuration after the NVT equilibration step, cp, with the configuration after the NPT equilibration step, and traj, with the configuration at the end of the production run. * peo_pbd_no_water_dataset includes only the gsd files traj_no_water, which contain the configuration of only the polymer beads at the end of the production run. Within both dataset folders, there are 258 "chunks", each containing 64 of the 16,512 sequence simulations. Each of these chunks contains a data folder with subfolders containing the individual simulation results. Each subfolder is named with a binary sequence corresponding to the 30 monomers in the chains used for the simulation within, with 0 corresponding to a PEO monomer and 1 corresponding to a PBD monomer. The output files, varying depending on which dataset folder (martini or no_water), are housed within these subfolders. Output configuration files are in the form of .gsd's, the native binary file of HOOMD. Both dataset folders contain README files with more detailed descriptions of their individual file structures. An example script to access data from the dataset is provided in trajectory_access.py. Example simulation scripts can be found in a GitHub repository (https://github.com/stattlab/sequence_martini), or in chunk 0000 of peo_pbd_martini_dataset.