Learning constructive models of emergent systems

Abstract

Emergent systems - systems with multiscale interactions - arise through iteration than forward design, leaving principles for building them under-explored. Current artificial intelligence architectures, while useful for generation, provide no logic for construction. Inspired by statistical phylogenetics, we show that inferring scales of system entropy then constraining information from low to high entropic scales yields stepwise constructive models. We term this architecture the Layer-Restricted Boltzmann Machine (LRBM). Applied identically to digit images, natural language, and enzyme sequences, LRBMs follow a common hierarchical logic: lower layers encode global structure, higher layers fine-grained features. As a stringent test, we assayed 160 synthetic chorismate mutase (CM) constructive trajectories alongside 1,130 natural homologs in vivo. Designed CMs functioned up to 53% divergent from nearest natural homolog. Fold emerged at intermediate layers while function required all layers, illustrating that fold was necessary but insufficient for function. Our results demonstrate a shared, learnable logic for constructing emergent systems.

Supplemental Table pertaining to the chorismate mutase assay and experimental results can be found in the associated github repository mentioned in the paper