Huiying Luo

Conflicts of Interest The authors declare no conflicts of interest. Data Availability Statement The data that support the findings of this study are available from the corresponding author upon reasonable request. Supporting Information Filename Description crat70152-sup-0001-SuppMat.docx19.3 KB Supporting File: crat70152-sup-0001-SuppMat.docx. References 1, , and , “Special Issue Paper.

1 Introduction The yeast Komagataella pastoris is among the most widely used microbial hosts for recombinant protein production, with more than 4000 heterologous proteins successfully expressed in this host to date (Claes et al. 2024; Vijayakumar and Venkataraman 2024). With recent progress in synthetic biology and metabolic engineering, K. pastoris is also increasingly employed as a chassis organism for the synthesis of high-value bioactive compounds (Gao et al. 2023; Fang et al. 2025).

Abstract Deep learning models show promise in accelerating the design and optimization of antimicrobial peptides (AMPs), but current methods face challenges, such as low success rates, or large virtual library scales. In this study, we introduce DLFea4AMPGen, a bioactive peptide design strategy that leverages deep learning models to identify and extract key features associated with antimicrobial peptide activity.