Machine learned designs of functional colloidal foldamers
Abstract
A protein's function follows from the structure it adopts, and in some cases which structure that is depends on the pathway taken. In programmable matter the target is fixed before assembly, and whatever else forms is treated as error. Here we show that pathways themselves form a design space. Using reinforcement learning, we fold model DNA-coated droplet chains into rigid two-dimensional geometries, uncovering two classes of pathways: downhill, in which bonds are only added, and detour, in which bonds are broken and remade before the target is reached: for some the only route that exists. Coarse-graining pathways by interactions gives experimentally realizable protocols. Some produce one geometry, others several: structures sharing a detour route can be cycled between, while those that coexist assemble into superstructures inaccessible to a uniform product. Function emerges from the pathways rather than being designed. Designing the process instead of the components could give colloidal materials that reconfigure on demand.
Related
- Capturing the Effect of Exact Exchange in Thio-Michael Additions with a Machine-Learned Functional at Meta-GGA Cost
- All-electron machine-learned orbital-free density functional for periodic CHNO systems
- Molecular Implementation of the Machine-Learned Skala Exchange-Correlation Functional in CP2K through GauXC
- Native implementation of the machine-learned Skala exchange-correlation functional in CP2K: Unified one-centre reconstruction for molecular and condensed-phase calculations
- Application of Machine Learning for the Identification of 2D Colloidal Assemblies: A Case Study on Particles of Distinct Shapes
BibTeX
@misc{mastrigt2026machine,
title = {{Machine learned designs of functional colloidal foldamers}},
author = {Ryan van Mastrigt and Zorana Zeravcic},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.28554},
eprint = {2608.28554},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28554},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Machine learned designs of functional colloidal foldamers
AU - Ryan van Mastrigt
AU - Zorana Zeravcic
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2608.28554
UR - https://arxiv.org/abs/2608.28554
AB - A protein's function follows from the structure it adopts, and in some cases which structure that is depends on the pathway taken. In programmable matter the target is fixed before assembly, and whatever else forms is treated as error. Here we show that pathways themselves form a design space. Using reinforcement learning, we fold model DNA-coated droplet chains into rigid two-dimensional geometries, uncovering two classes of pathways: downhill, in which bonds are only added, and detour, in which bonds are broken and remade before the target is reached: for some the only route that exists. Coarse-graining pathways by interactions gives experimentally realizable protocols. Some produce one geometry, others several: structures sharing a detour route can be cycled between, while those that coexist assemble into superstructures inaccessible to a uniform product. Function emerges from the pathways rather than being designed. Designing the process instead of the components could give colloidal materials that reconfigure on demand.
ER -