bago 1.0.0

Fully automated LC gradient optimization of optimal compound separation in nontargeted metabolomics

BAGO

BAGO is a Bayesian optimization strategy for LC gradient optimization for MS-based small molecule analysis. Check out our YouTube video

BAGO enables

Highly efficient gradient optimization

• Find an optimal gradient for your LC-MS/MS analysis within 10 runs.
• Wonder why BAGO is efficient? Read more about acquisition functions.

Omics-scale evaluation on compound separation

• Separation efficiency was defined to evaluate the performance of a gradient.
• Wonder how omics-scale evaluation is achieved? Read more about encodings.

Broader discovery of chemical space

• Expand your discovery of chemical space by improving identification and quantification.
• Wonder how BAGO can help you? Read more about applications.

   

BAGO Windows Software

BAGO Windows software is freely available from the GitHub release page. A user manual in .pdf format is included with the software.

The software is designed to be simple, clear, and intuitive. BAGO has a graphical user interface as shown below.

   

bago Python package

bago is a Python package for supporting the proposed Bayesian Optimization framework of LC gradient optimization.

bago covers the proposed features needed in creating a gradient optimization workflow based on Bayesian optimization. Depending on your use case, bago can be used in different ways:

• Perform LC gradient optimization in programmtic envrionment
• Model LC-MS experiment to evaluate compound separation performance
• Optimize the default pipeline to adpat a special gradient optimization scenario
• Further development of the proposed Bayesian optimization strategy
• Extend the corrent stategy to other LC-based analytical platforms

   

Accessibility

• Documentation: https://bago.readthedocs.io/en/latest/
• Source code: https://github.com/huaxuyu/bago
• Bug reports: https://github.com/huaxuyu/bago/issues

   

Please cite

Yu, H., Biswas, P., Rideout, E., Cao, Y., & Huan, T. (2023). Bayesian optimization of separation gradients to maximize the performance of untargeted LC-MS. bioRxiv, 2023-09.

BAGO manuscript