Skip to content

Question about handling different peak sets in cross-organ prediction #9

@yuequnwang

Description

@yuequnwang

Thank you for developing scButterfly and making the code available. I'm particularly interested in the cross-organ prediction experiment described in Figure 4g of your paper.

I have a technical question about how different peak sets were handled in the cross-organ prediction experiments. Since different organs (e.g., UP_stomach, UP_pancreas, and UP_spleen) naturally have different sets of accessible chromatin regions with different genomic coordinates, I'm curious about:

(1) Peak unification strategy: How did you handle the different peak sets when training on one organ (e.g., UP_stomach) and testing on another (e.g., UP_pancreas)?

(2) Could you point to the specific part of the code that handles this aspect of the cross-organ prediction? I've looked through the repository but couldn't find the exact implementation for this particular challenge.

Thank you for your time!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions