Fig. 4: Simulation of recombinant protein production.

a Overview of protein features for eight recombinant proteins produced by S. cerevisiae. See Supplementary Data 7 for detailed information. Abbr. abbreviation. b Simulation of maximum specific recombinant protein production rate as a function of specific growth rate. c Feature importance analysis towards recombinant protein production. NG N-glycosylation site, OG O-glycosylation site, DSB disulfide bond number, Trans transmembrane domain, single letters stand for specific amino acids, SHAP value SHapley Additive exPlanations value. Fivefold cross validation was performed to validate the result (Supplementary Fig. 7). Source data are provided as a Source Data file.