Conditional diffusion with locality-aware modal alignment for generating diverse protein conformational ensembles

Recent advances in artificial intelligence have enabled accurate prediction of a protein’s stable structure solely based on its amino acid sequence. However, capturing the complete conformational landscape of a protein and its dynamic flexibility remains challenging. Here we developed modal-aligned conditional diffusion (Mac-Diff), a score-based diffusion model for generating the conformational ensembles for unseen proteins. Central to Mac-Diff is an attention module that enforces a delicate, locality-aware alignment between the conditional view (protein sequence) and the target view (residue pair geometry) to compute highly contextualized features for effective structural denoising and generation. Furthermore, Mac-Diff leverages semantically rich sequence embedding from protein language models such as ESM-2 in enforcing the protein sequence condition that captures evolutionary, structural and functional information. Mac-Diff showed promising results in generating realistic and diverse protein structures. It successfully recovered conformational distributions of fast-folding proteins, captured multiple meta-stable conformations that were observed only in long MD simulation trajectories and efficiently predicted alternative conformations for allosteric proteins. We believe that Mac-Diff offers a useful tool to improve understanding of protein dynamics and structural variability, with broad implications for structural biology, structure-based drug design and protein engineering.