A Deep-Learning-Based Server SecEff-Pred for Predicting Signal Peptide Secretion Efficiency to Improve Protein Production in <i>Bacillus subtilis</i>

In <i>Bacillus</i> species, the signal peptide (SP) efficiently guiding the protein secretion is crucial for production, yet there is still a lack of reliable computational tools to accurately predict its efficiency. Therefore, we developed SecEff-Pred, a novel web server that leverages an ESM-2-based predictor. Enhanced by an innovative data simulation strategy and a multitask learning framework, SecEff-Pred accurately predicted the secretion efficiency of signal peptides in <i>Bacillus subtilis</i>. The server demonstrated exceptional performance, achieving prediction accuracies of 85.59% for α-amylase, 81.58% for alkaline xylanase, and 74.68% for cutinase. SecEff-Pred was further validated using phospholipase D (PLD) as a reporter protein, demonstrating high prediction accuracy for signal peptide efficiency (overall 72%), with an accuracy of 80% for "efficient" SPs (corresponding to a maximum PLD activity of 929 U/mL) and 62.50% for "inefficient" SPs. These results confirm the SecEff-Pred is a powerful tool for guiding protein secretion in <i>B. subtilis</i>.