Machine Learning-Guided Adaptive Parametrization for Coupling Terms in a Mixed United-Atom/Coarse-Grained Model for Diphenylalanine Self-Assembly in Aqueous Ionic Liquids

Abstract

Precise regulation of the peptide self-assembly into ordered nanostructures with intriguing properties has attracted intense attention. However, predicting peptide assembly at atomic resolution is a challenge due to both the structural flexibility of peptides and the associated huge computational costs. A machine learning-guided adaptive parametrization method was proposed for developing a mixed atomic and coarse-grained (CG) model through a multiobjective optimization strategy. Our model incorporates the united-atom (UA) model for diphenylalanine (P) and the polarizable electrostatic-variable coarse-grained (VaCG) model for aqueous ionic liquid [BMIM]+[BF4]− solution. In this mixed model, the coupling van der Waals (vdW) interaction is addressed by introducing virtual sites (VS) in the UA model to interact with solvent CG beads. The coupling parameters, including the electrostatic parameter and vdW parameters, are automatically optimized through ML-guided adaptive parametrization. The performance of this model was tested by some microstructural properties, e.g., the average number of P–P intermolecular hydrogen bonds (HBs) and radius distribution functions (RDFs) between P and different fragments of IL, in comparison with all-atom (AA) simulations. The computational cost is significantly reduced using such a parametrization scheme, which could search tens of thousands of force-field parameter sets, while needing only a small fraction of them to be assessed with molecular dynamics (MD) simulations. We used such a mixed resolution model to investigate the self-assembly in IL–water mixtures with variants of IL concentration (X). The long-range-ordered fibril structure is formed in a pure water system (X = 0). With an increase of IL concentrations, the formation of an ordered self-assembly nanostructure is prohibited, instead forming branched fibril at X = 2 mol % or amorphous aggregates when X > 10 mol %, resulting from the interplay between π-stacking and HB interactions between P and IL. The qualitative agreement between the simulated structures and the observed morphologies in experiments indicates the applicability of ML-guided parametrization strategy in the study of complex systems, such as polymers, lipid bilayers, and polysaccharides.

Simulations of Functional Motions of Super Large Biomolecules with a Mixed-Resolution Model

“…Incidentally, as was found by Sokkar et al, the coupling scheme proposed by Rzepiela et al may result in too strong AA-CG interactions that cause unfolding of AA proteins in simulations. A systematic reparametrization of the interactions involving virtual sites is thus necessary and may be attainable, as was shown by Ge et al in their recent model development for peptide self-assembly using machine learning techniques …”

“…A systematic reparametrization of the interactions involving virtual sites is thus necessary and may be attainable, as was shown by Ge et al in their recent model development for peptide self-assembly using machine learning techniques. 29 In a different type of approaches, AA protein sites were allowed to interact with polarizable CG water sites through electrostatic and van der Waals (vdW) interactions. The parameters for these interactions were generated from those of the AA and CG sites using a set of combining rules 30,31 but could be rescaled 32,33 or even systematically optimized 34,35 to reproduce solvation free energies of small molecules or their association free energy profiles.…”

“…A systematic reparametrization of the interactions involving virtual sites is thus necessary and may be attainable, as was shown by Ge et al in their recent model development for peptide self-assembly using machine learning techniques. 29 …”

Computation-Driven Rational Design of Self-Assembled Short Peptides for Catalytic Hydrogen Production

“…In recent years, several works have focused on the theoretical investigation of peptide aggregation behavior. For instance, coarse-grained molecular dynamics (MD) simulation predictions of short-peptide aggregation behavior − and the integration of machine learning to expand the search space − have been reported. Coarse-grained approaches, on the one hand, often lack atomic-scale details, making them less suitable for guiding catalytic design.…”

A Robust Induced Fit Docking Approach with the Combination of the Hybrid All-Atom/United-Atom/Coarse-Grained Model and Simulated Annealing

“…In the hybrid model, all nonbonded interactions are systematically matched using a bottom-up coarse-graining approach called the Lennard-Jones Static Potential Matching (LJSPM). , The LJSPM method demonstrates transferability by accurately reproducing the static Lennard-Jones (LJ) potential energy surface from the higher-level reference (AA model), consistently producing geometric-combining-rule-based force field parameters for all inter- and intra-residue nonbonded interactions between AA, UA, and CG models. The hybrid model − not only accelerates simulation speed but also preserves the accuracy associated with ligand binding and its interactions with the protein environment. To fully sample the conformational space of the receptor–ligand complexes, simulated annealing (SA) and an Elastic Network Model (ENM) for the CG region are incorporated into the model.…”