Plant vacuoles, as important multifunctional organelles within cells, play a crucial role in maintaining cellular stability, adapting to environmental changes, and responding to external pressures. In order to more accurately identify vacuole proteins, this study developed a new predictive model PEL-PVP.
Model Introduction
PEL-PVP based on ESM-2. It utilizes Transformer structure and self attention mechanism to calculate pairwise relationships between residues in the sequence, capturing the interdependence and interaction relationships between amino acid residues at different positions. And by utilizing the massive pre training parameters of ESM-2, adaptive fine-tuning of vacuolar proteins was performed to efficiently extract features. LoRA technology was used to effectively reduce the number of parameters and computational complexity during the fine-tuning process.