Does Sequence Clustering Confound AlphaFold2?

Predicting multiple conformational states of proteins represents a significant open challenge in structural biology. Increasingly many methods have been reported for perturbing and sampling AlphaFold2 (AF2) (Jumper et al., 2021) to achieve multiple conformational states. However, if multiple methods achieve similar results, that does not in itself invalidate any method, nor does it answer why these methods work. Interpreting why deep learning models give the results they do is a critically important endeavor for future model development and appropriate usage. To help the field continue to try to answer these questions, this work addresses misunderstandings and inaccurate conclusions in Porter et al. (2023), Chakravarty et al. (2023), Chakravarty et al. (2024), Schafer et al. (2024), and Schafer et al. (2025). Deep learning methods development moves quickly, and by no means did we think that the implementation of AF-Cluster in Wayment-Steele et al. (2024) would be the final word on how to sample multiple conformations. However, Porter et al.'s primary critique, that AF-Cluster does not use local evolutionary couplings in its MSA clusters, is incorrect. We report here further analysis that underscores our original finding that local evolutionary couplings do indeed play an important role in AF-Cluster predictions, and refute all false claims made against (Wayment-Steele et al., 2024).