-
Notifications
You must be signed in to change notification settings - Fork 506
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
mapping performance improvement #773
base: master
Are you sure you want to change the base?
Conversation
* [stitchWindowAligns()] used to create a new [Transcript] instance irregardless of if it will be successfully stitched to the transcript. Early check allows to check for most common reasons to reject the alignment. * To ease reading, `WA[iA]` is aliased as `align`. * minor formatting
Hi Alexey, thanks a lot for this very interesting PR (and the previous as well). Cheers |
Does anybody knows whether using a gtf annotation + Star + human genome I could improve alignment speed? If yes, how many times I can speed up the alignment? |
Hi @rherai using annotations increases accuracy but not the speed. Cheers |
During mapping,
stitchWindowAligns
uses recursive callsiA
The call 1) is performed only if
stitchAlignToTranscript
does not return a bad score.Since
stitchAlignToTranscript
modifies theTranscript
object, an additional copy is created, which is expansive.This pull request attempts to address this performance overhead:
additional cheaper check is performed, which allows to avoid copy-creation of a new
Transcript
object if it will not be used in the recursion.The changes comprise of
Progress output with and without the PR code on a test subset: