Di-n-butyl phthalate (DBP) is an extensively used plasticizer. Most investigations on DBP have been concentrated on its environmental distribution and toxicity to humans. However, information on the effects of plasticizers on algal species is scarce. This study verified the impacts of endocrine disruptor di-n-butyl phthalate ester on microalga Chlorella vulgaris by approaches of proteomics and gene ontology. The algal acute biotoxicity results showed that the 24h-EC50 of DBP for C. vulgaris was 4.95 mg L⁻¹, which caused a decrease in the chlorophyll a content and an increase in the DBP concentration of C. vulgaris. Proteomic analysis led to the identification of 1257 C. vulgaris proteins. Sixty-one more proteins showed increased expression, compared to proteins with decreased expression. This result illustrates that exposure to DBP generally enhances protein expression in C. vulgaris. GO annotation showed that both acetolactate synthase (ALS) and GDP-L-fucose synthase 2 (GER2) decreased more than 1.5-fold after exposure to DBP. These effects could inhibit both the valine biosynthetic process and the nucleotide-sugar metabolic process in C. vulgaris. The results of this study demonstrate that DBP could inhibit growth and cause significant changes to the biosynthesis-relevant proteins in C. vulgaris.

The fermentation of Lactiplantibacillus plantarum is a complex bioprocess due to the nonlinear and dynamic nature of microbial growth. Traditional monitoring methods often fail to provide early and actionable insights into fermentation outcomes. This study proposes a deep learning-based predictive system using convolutional neural networks (CNNs) to classify fermentation trajectories and anticipate final cell counts based on the first 24 h of process data. A total of 52 fermentation runs were conducted, during which real-time parameters, including pH, temperature, and dissolved oxygen, were continuously recorded and transformed into time-series feature vectors. After rigorous preprocessing and feature selection, the CNN was trained to classify fermentation outcomes into three categories: successful, semi-successful, and failed batches. The model achieved a classification accuracy of 97.87%, outperforming benchmark models such as LSTM and XGBoost. Validation experiments demonstrated the model’s practical utility: early predictions enabled timely manual interventions that effectively prevented batch failures or improved suboptimal fermentations. These findings suggest that deep learning provides a robust and scalable framework for real-time fermentation control, with significant implications for enhancing efficiency and reducing costs in industrial probiotic production.