An Integrated Machine Learning Approach Delineates Entropy-mediated Conformational Modulation of α-synuclein by Small Molecule

Abstract

The mis-folding and aggregation of intrinsically disordered proteins (IDPs) such as α -synuclein ( α S) underlie the pathogenesis of various neurodegenerative disorders. However, targeting α S with small molecules faces challenges due to its lack of defined ligand-binding pockets in its disordered structure. Here, we implement a deep artificial neural network based machine learning approach, which is able to statistically distinguish fuzzy ensemble of conformational substates of α S in neat water from those in aqueous fasudil (small molecule of interest) solution. In particular, the presence of fasudil in milieu either modulates pre-existing states of α S or gives rise to new conformational states of α S, akin to an ensemble-expansion mechanism. The ensembles display strong conformation-dependence in residue-wise interaction with the small molecule. A thermodynamic analysis indicates that small-molecule modulates the structural repertoire of α S via tuning protein backbone entropy, however keeping entropic ordering of surrounding solvent unperturbed. Together, this study sheds light on the intricate interplay between small molecules and IDPs, offering insights into entropic modulation and ensemble expansion as key biophysical mechanisms driving potential therapeutics.