Unifying structural descriptors for biological and bioinspired nanoscale complexes

Biomimetic nanoparticles are known to serve as nanoscale adjuvants, enzyme mimics and amyloid fibrillation inhibitors. Their further development requires better understanding of their interactions with proteins. The abundant knowledge about protein–protein can a guide for designing protein–nanoparticle assemblies, but the chemical biological inputs used in computational packages not applicable inorganic nanoparticles. Analysing chemical, geometrical graph-theoretical descriptors protein complexes, we found that uniformly nanostructures predict interaction sites pairs accuracy >80% classification probability ~90%. We extended machine-learning algorithms trained on nearly exact match between experimental predicted These findings be other organic assemblies biomolecules structures forming lock-and-key complexes. Unified structural features developed, allowing complexes utilized formation pairs.