I will present the phase separation behavior of different sequences of a coarse-grained model for intrinsically disordered proteins or sequence defined block copolymers. I will discuss results from unsupervised manifold learning (UMAP) to classify the different aggregate types and what we can learn from machine learning. This method provides insight into the structure of these disordered, dilute aggregates, which has proven difficult to understand using collective variables manually derived from expert knowledge [Statt et al., J. Chem. Phys., 2020, 152, 075101]. In contrast to such conventional order parameters, we are able to classify the global aggregate structure directly using descriptions of the local environments. The resulting characterization provides a deeper understanding of the range of possible self-assembled structures and their relationships to each other. We also provide analysis of the effects of finite system size, stochasticity, and kinetics of these aggregates based on the learned collective variables. These results demonstrate the insight which can be gained by applying unsupervised machine learning to soft matter systems, especially when suitable order parameters are not known. Additionally, we accurately predict the morphology of aggregates via supervised machine learning, using a bidirectional-Gated Recurrent Units-based Neural Network (RNN). We find that regression models with implicit representation learning perform significantly better than those based on engineered features such as k-mer counting, and a recurrent-neural-network-based regressor performs the best out of nine model architectures we tested. Furthermore, we demonstrate the high-throughput screening of monomer sequences using the regression model to identify candidates for self-assembly into selected morphologies.
