FunCLAN: A novel and generalisable method for categorising protein complex conformations, measuring their similarities, and solving the chain equivalence problem

We present FunCLAN, a novel method for finding, categorising, and measuring conformational relationships between protein complexes, as well as for finding corresponding chain pairs between them. Its purpose is to provide a general tool, applicable to a broad range of complexes. As such, it only utilises sequence similarity and superposition transformations to compare rigid bodies (chains), and how they transform with relation to each other. This lets us clusterise transformations, which lets us identify sets of similar and dissimilar transformations across the dataset. We use this information to classify conformations according to how the transformations relate to each other at chain and complex level. We have also included two data, and scale agnostic methods that can make informed predictions as to the number of clusters (conformers) present in the dataset. We also present a way to superpose entire complexes using the alignment and chain correspondence data for visualisation purposes. The entire process can be generalised to domains and even single chains, but this requires bespoke/specialised preprocessing of the data as well as prior knowledge of the structures to be analysed. This is out of the scope of this paper, but we outline a method to do so in the supplementary information.