This tool is an inverse folding protein design model retrained on the ProteinMPNN architecture specifically for the computational redesign of salt-tolerant proteins and halophilic enzymes. The model was trained on a high-quality proteome dataset from "salt-in" extreme halophilic archaea. While preserving the input protein backbone, it shifts sequence features of ordinary non-halophilic proteins toward those of natural halophilic proteins: lowering the isoelectric point, increasing the fraction of negatively charged residues on the protein surface, and reducing the proportion of bulky hydrophobic residues on both the surface and in the core, thereby recapitulating the characteristic amino acid substitution preferences of halophilic proteins. It is suitable for blue biotechnology and enzyme engineering under high-salt industrial conditions.
This is a computational design tool, and the output sequences still require wet-lab validation for actual salt tolerance. Users only need to upload the backbone structure of the target protein to obtain salt-optimized candidate sequences and accelerate their R&D work.
Upload a protein structure file in PDB or mmCIF format, and the system will automatically parse chain information. After selecting chains to design and setting parameters, the model will generate multiple optimized amino acid sequences, with scores (score = -log_prob, lower is better) and sequence recovery rates for each.