The DeepDDG server predicts the stability change of protein point mutations using neural networks.
The dataset used to train the network can be downloaded here.
For a quick demo, use the T4 lysozyme structure and the predicted result is like this.

Protein Structure (Please make sure the uploaded structure does not contain short peptides):
Select PDB file to upload:
Or download PDB ID:

Network model:
DeepDDG (non-integrated model)
iDeepDDG (integrated model, uses user-provided ΔΔG values from mCSM, SDM, and DUET as additional inputs)

Mutation list:
All possible mutations
Selected mutations ( You may submit multiple mutations in one job )
Mutation list (format):
  • Each line contains one mutation, multiple lines can be submitted in one job :
    Chain WTResidueName ResidueID MutantResidueName
    e.g., A W 32 G
  • If the iDeepDDG network is used, put the ΔΔG values from mCSM, SDM, and DUET at the end of each mutation (order is important):
    e.g., A W 32 G -1.23 -2.04 -0.59
  • The mCSM, SDM, and DUET ΔΔG values can be obtained from the DUET server

Your email (optional, results will be sent to this email if provided):

Submitting job...

H. Cao, J. Wang, L. He, Y. Qi*, and J. Z. Zhang*. (2019). DeepDDG: Predicting the Stability Change of Protein Point Mutations Using Neural Networks. J. Chem. Inf. Model.