Open access
Aug 2026
PMPNN-DDG: an accurate machine learning-based ΔΔG prediction pipeline trained on a novel interpretable feature set extracted from ProteinMPNN
PMPNN-DDG, a Random Forest-based DDG prediction model, trained on a novel set of interpretable features extracted from the recently proposed message-passing neural network-based fixed backbone protein design model, ProteinMPNN, is proposed.
Sajid Ahmed, Md. Rafsan Jani
· bioRxiv · 0 citations