Plastic polymers are widely used in agriculture, industry, and our daily life because of their convenient and economic properties. However, pollution caused by plastic polymers, especially polyethylene (PE), affects both animal and human health when they aggregate in the environment, as they are not easily degraded under natural conditions. In this study, Enterobacter sp. D1 was isolated from the guts of wax moth (Galleria mellonella). Microbial colonies formed around a PE film after 14 days of cultivation with D1. Roughness, depressions, and cracks were detected on the surface of the PE film by scanning electron microscopy (SEM) and atomic force microscopy (AFM). Fourier transform infrared spectroscopy (FTIR) showed the presence of carbonyl functional groups and ether groups on the PE film that was treated with D1. Liquid chromatography-tandem mass spectrometry (LC-MS) also revealed that the contents of certain alcohols, esters, and acids were increased as a result of the D1 treatment, indicating that oxidation reaction occurred on the surface of the PE film treated with D1 bacteria. These observations confirmed that D1 bacteria has an ability to degrade PE.
• Gene sequence is the major factor contributing expression. • MPEPE is a mutation predictor for enhancing protein expression. • Identified mutations in enzymes increased its expression levels in E. coli.
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. This approach enables the generation of peptide sequences with potential bioactivities. Using the SHapley Additive exPlanations (SHAP) method, we quantify the contribution of each amino acid in multifunctional peptides with potential antibacterial, antifungal, and antioxidant activities. Key feature fragments (KFFs) with the highest average contributions are extracted and classified into four subfamilies based on amino acid frequency. These high-frequency amino acids are systematically arranged to generate a plausible sequence subspace for candidate peptides, from which 16 representative sequences were selected for experimental validation. The results show that 75% (12/16) of the sequences exhibited at least two types of activity. Notably, D1 exhibits broad-spectrum antimicrobial activity, including efficacy against multidrug-resistant clinical pathogenic isolates both in vitro and in vivo. This proof-of-concept study underscores the potential of the DLFea4AMPGen platform for efficient design and screening of bioactive peptides, showcasing its value in AMP research.