DDA-BERT is an end-to-end rescoring tool tailored for data-dependent acquisition (DDA) proteomics. Leveraging a deep learning model based on the Transformer architecture, it refines initially identified peptide-spectrum matches (PSMs) to improve identification accuracy and sensitivity. Trained on a large-scale dataset of 3,701 DDA-MS files and approximately 82 million high-confidence PSMs, DDA-BERT effectively captures complex relationships between peptide sequences and MS/MS spectra. The model delivers robust and consistent performance across a wide range of biological systems, including animal, plant, and microbial proteomes. It also demonstrates high sensitivity in low-input conditions, such as trace-level and single-cell proteomics, making it well-suited for diverse experimental contexts. Results are exported in structured CSV format, providing clear, interpretable summary tables to support downstream biological insights. Fully open-source, DDA-BERT integrates seamlessly into experimental and computational workflows. Its modular architecture enables easy customization and extension, offering a scalable, high-performance solution for enhancing peptide identification depth and reliability.

This software is currently under development, and we welcome you to try it out. If you have any feedback or suggestions, please let us know.
Email address: guotiannan@westlake.edu.cn.