Clifton, B. R. | bioRxiv Science

bioRxiv2026

Benchmarking AI-generated structural ensembles of membrane proteins against physics-based modelling

Proteins dynamically switch between a continuum of interconverting conformational states, and understanding these structural dynamics is important for understanding protein function and for developing therapeutics. Molecular dynamics (MD) simulations can provide insight into protein conformational ensembles, but sampling rare conformational states can require substantial computational resources. The recent development of AI-based approaches for generating protein conformational ensembles, such as the Biomolecular Emulator (BioEmu), offers a potential alternative, although it remains unclear whether these approaches can accurately capture the conformational landscapes, especially for special cases such as membrane proteins. Here, we assess the ability of BioEmu to model the conformational dynamics of a model membrane protein, the bacterial rhomboid intramembrane proteases GlpG. We find that BioEmu generates a range of conformations corresponding to both open and closed states of the rhomboid lateral gate, including states associated with different stages of the catalytic cycle. These conformations broadly correspond to states sampled during microsecond-timescale MD simulations, although BioEmu does not reproduce the full conformational landscape observed using MD. BioEmu also samples substantial conformational heterogeneity within the soluble domains of rhomboids, which are highly flexible and poorly represented in experimental structures. Overall, our findings demonstrate that BioEmu can generate plausible conformational ensembles for relatively large, six-and seven-pass membrane proteins, sampling rare states at a fraction of the computational cost of conventional MD simulations. These results suggest that AI-based ensemble generation could provide an accessible approach for exploring membrane protein dynamics and complement conventional molecular modelling approaches.

biophysics↗

bioRxiv2025

Structural and energetic insights into human rhomboid proteases reveal a unique lateral gating mechanism for orphan family members

Rhomboid proteases play fundamental roles in human biology and disease by cleaving substrate transmembrane domains. However, the absence of structural data and the inability to identify substrates for orphan human rhomboids limit mechanistic understanding. Lateral gating is considered the primary route by which transmembrane substrates access the rhomboid active site, although this has been demonstrated directly only for the bacterial rhomboid GlpG. To address this, we characterised the structures, conformational ensembles, and energy landscapes of human rhomboid proteases using AI-based structural models and molecular dynamics simulations, benchmarked by simulations seeded with GlpG crystal structures and models. We find that while some human rhomboids readily transition to open conformations compatible with transmembrane substrate access, orphan rhomboids possess unusually narrow lateral gates that require substantially higher energy to open. Our results reveal unexpected diversity in substrate engagement mechanisms among human rhomboids, and provide a rationale for the orphan status of recently evolved family members.

biochemistry↗