Minimization

The minimization is crucial for the quality of the outcome. The better the structure is energetically minimized, the more reliable the results will be.
We continuously pre-minimize structures from the PDB using the commandline described below. If you specify a PDB ID that is contained in our database, the pre-minimized structure is used.
Otherwise we offer two modes of side-chain minimization, a short and a long one. The short one should take a few minutes, depending on the size of the protein. The long one may take some hours for large proteins.

RaSP model

RaSP is a deep-learning-based tool that rapidly estimates protein stability changes. With RaSP, Mutation Explorer presents the user with a quick initial estimation of a mutation's (de)stabilizing effect, without their having to wait for the longer full minimization process. The RaSP tool consists of two linearly linked networks. A self-supervised 3D convolutional neural network that has learned representations of protein structures is followed by a fully connected neural network that maps these internal representations to Rosetta protein stability changes. RaSP is optimised for accuracy in the range [-1,7] kcal/mol.

This command will create a RaSP model for each chain of the structure. This can take up to 10 minutes per chain.

Once this option is selected, it will be applied in all subsequent steps accordingly.