AFsample2 predicts multiple conformations and ensembles with AlphaFold2.

ABSTRACT: Understanding protein dynamics and conformational states is crucial for insights into biological processes and disease mechanisms, which can aid drug development. Recently, several methods have been devised to broaden the conformational predictions made by AlphaFold2 (AF2). We introduce AFsample2, a method using random MSA column masking to reduce co-evolutionary signals, enhancing structural diversity in AF2-generated models. AFsample2 effectively predicts alternative states for various proteins, producing high-quality end states and diverse conformational ensembles. In the OC23 dataset, alternate state models improved (ΔTM>0.05) in 9 out of 23 cases without affecting preferred state generation. Similar results were seen in 16 membrane protein transporters, with 11 out of 16 targets showi

SUBMITTER: Kalakoti Y 

PROVIDER: S-EPMC11882827 | biostudies-literature | 2025 Mar

REPOSITORIES: biostudies-literature