solublempnn

To design solubility-optimized protein sequences, provide a backbone structure and constraints to the soluble design workflow to obtain solubility-enhanced sequences. This process uses SolubleMPNN to improve expression yield and reduce aggregation.

Yes, you can perform ligand-aware solubility improvement tasks using the LigandMPNN workflow. This generates designed sequences and design-ready outputs suitable for structure validation and downstream QC workflows.

Running a SolubleMPNN workflow requires Python 3.8+, CUDA 11+, and the soluble model. You must also provide input data such as the backbone, constraints, and design targets to generate the designed sequences.

Yes, this approach supports E. coli expression planning and aggregation reduction. Solubility-biased sequence design enhances expression in bacterial systems and reduces aggregation during protein engineering workflows.

Standard soluble protein design uses ProteinMPNN, while ligand-aware design uses LigandMPNN. Both generate solubility-optimized sequences to improve expression yield and reduce aggregation in protein engineering workflows.