Soluble protein analog selection engine (SPASE): An automated AI-powered server to improve protein engineering...

Area of Science:

• Biotechnology
• Protein Engineering
• Computational Biology

Background:

• Designing proteins with high solubility and low aggregation is vital for biotechnology.
• Current deep learning methods like ProteinMPNN may not always yield proteins with optimal biophysical properties.

Purpose of the Study:

• To present SPASE (Soluble Protein Analog Selection Engine), an automated webserver for designing soluble proteins.
• To integrate ProteinMPNN with solubility and aggregation prediction tools to enhance protein design.

Main Methods:

• SPASE integrates ProteinMPNN, Protein-Sol, Aggrescan3D, and ESMFold.
• It generates protein variants, predicts solubility and aggregation, models structures, and scores candidates.
• The workflow prioritizes designs based on predicted solubility, aggregation, and folding confidence.

Main Results:

• SPASE enriches for protein analogs with higher predicted solubility and lower aggregation propensity compared to standard ProteinMPNN output.
• Benchmarking demonstrates the server's effectiveness in identifying improved protein candidates.

Conclusions:

• SPASE provides a practical and accessible platform for prioritizing protein engineering candidates.
• Integrated computational approaches are valuable for optimizing protein designs across multiple biophysical properties.