Memorization Bias Impacts Modeling of Alternative Conformational States of Symmetric Solute Carrier Membrane Proteins...

Conformational memorization impacts the performance of AlphaFold in modeling the dynamic structures of proteins. The Solute Carrier (SLC) superfamily of integral membrane proteins transport a wide array of small molecules across plasma and organelle membranes, and function as important drug transporters and as viral receptors. They populate different conformational states during the solute transport process, including outward-open, intermediate (occluded), and inward-open conformational states. For some SLC proteins this structural "flipping" corresponds to swapping between conformations of their N-terminal and C-terminal symmetry-related sub-structures. Conventional AlphaFold2, AlphaFold3, or Evolutionary Scale Modeling methods typically generate models for only one of these multiple conformational states of SLC proteins. While several AI-based protocols for modeling multiple conformational states of proteins have been described recently, these methods are often impacted by "memorization" of one of the alternative conformational states, and do not always provide both the inward- and outward-open conformations of SLC proteins. Here we assess the impact of memorization in modeling SLC proteins with AlphaFold, and describe a combined ESM - template-based-modeling process, based on a previously described template-based modeling method that relies on the internal pseudo-symmetry of many SLC proteins, to consistently model the alternate conformational states of SLC proteins. We also demonstrate how the resulting multi-state models can be validated experimentally by comparison with sequence-based evolutionary co-variance data (ECs) that encode information about contacts present in the various conformational states adopted by the protein. This simple, rapid, and robust approach for modeling conformational landscapes of pseudo-symmetric SLC proteins is demonstrated for several integral membrane protein transporters, including SLC35F2 the receptor of a feline leukemia virus envelope protein required for viral entry into eukaryotic cells.