Solubility-Weighted Index: fast and accurate prediction of protein solubility

Bikash K. Bhandari; Paul P. Gardner; Chun Shen Lim

Prediction accuracy of solubility prediction tools using the above cross-validation sets (Fig 2A) . For SWI, the test AUC scores were calculated from a 10-fold cross-validation (i.e., a boxplot representation of Fig 2B) . For other tools, the test AUC scores were calculated directly from the individual subsets used for cross-validation. No cross-validations were done. CamSol and ccSOL omics are only available as web servers (no fill colors). (B) Wall time of protein solubility prediction tools per sequence (log scale). All command line tools were run three times using 10 sequences selected from the PSI:Biology and eSOL datasets. Related data is available as Supplementary To demonstrate a use case for SWI, we developed the Soluble Domain for Protein Expression (SoDoPE) web server (see Methods and https://tisigner.com/sodope ). Upon sequence submission, the SoDoPE web server enables users to navigate the protein sequence and its domains for predicting and maximising protein expression and solubility.