Summary
Randomly masking residues prior to running ESMFold allows false positive folders to be identified (1). This partially overcomes the limitation of ESMFold to fold everything. It also leads to marginal improvements in Spearman correlation between pLDDT and experimental stability ().
See also
1.
Hermosilla AM, Berner C, Ovchinnikov S, Vorobieva AA. Validation of de novo designed water-soluble and transmembrane proteins by in silico folding and melting. openRxiv; 2023. Available from: https://doi.org/10.1101/2023.06.06.543955