DIA-BERT is user-friendly Graphical User Interface (GUI) that leverages a transformer based pre-trained artificial intelligence (AI) model for the analysis of data-independent acquisition (DIA) proteomics. Over 276 million of high-quality training samples from real MS files were used for identification model and 34 million of training samples from synthetic MS files were used for quantification model. The tool is well-suited for multi-species datasets, particularly human proteomes. The output of DIA-BERT is provided as summarized tables in CSV format.
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: liuzhiwei@westlake.edu.cn; guotiannan@westlake.edu.cn.
Frequently asked questions: https://github.com/guomics-lab/DIA-BERT
You can also create an issue on the GitHub page: https://github.com/guomics-lab/DIA-BERT/issues
Core Features
AI driven
Adopting advanced transformer models to provide accurate proteomic analysis results
High quality data
Based on massive real and simulated mass spectrometry data training, ensure the reliability of analysis results
Friendly interface
Intuitive graphical user interface makes complex analysis processes simple and easy to use
Technical specifications
Training sample size
Over 276 million real samples
Quantitative sample
Over 34 million synthetic samples
Format output
CSV format summary table
Application scenarios
Multi species dataset analysis
Start using DIA-BERT
Download and experience the new generation of intelligent proteomics analysis tools now
Downloading the latest version