Summary
About 100,000 datapoints are required to train an accurate ddG predictor with Spearman correlation of 0.85 (1).
See also
1.
Pak MA, Dovidchenko NV, Sharma SM, Ivankov DN. New mega dataset combined with deep neural network makes a progress in predicting impact of mutation on protein stability. openRxiv; 2023. Available from: https://doi.org/10.1101/2022.12.31.522396