Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Tuning MS2 by low-quality fragment matches on all DIA PSMs at apex_rt resulted in low-quality MS2 prediction #124

Open
jalew188 opened this issue Dec 31, 2023 · 1 comment

Comments

@jalew188
Copy link
Collaborator

jalew188 commented Dec 31, 2023

  1. Using DIA PSMs identified by DIA search engine to refine MS2 model may result in low-quality MS2 prediction due to low-quality precursor matches;
  2. Using spectral library tsv to refine the MS2 model may also result in low-quality MS2 prediction. It depends on how many low-quality matches are there in spectral library;
@jalew188
Copy link
Collaborator Author

jalew188 commented Jan 3, 2024

It turns out that this is not “catastrophic forgetting”, this is due to low matching quality of DIA data.

@jalew188 jalew188 changed the title “catastrophic forgetting” after transfer learning on MS2 Tuning by low quality fragment matches on DIA data resulted in low quality MS2 prediction Jan 3, 2024
@jalew188 jalew188 reopened this Jan 9, 2024
@jalew188 jalew188 changed the title Tuning by low quality fragment matches on DIA data resulted in low quality MS2 prediction Tuning MS2 by low-quality fragment matches on all DIA PSMs at apex_rt resulted in low-quality MS2 prediction Jan 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant