search

JinmiaoChenLab / SpatialGlue

SpatialGlue is a novel deep learning methods for spatial multi-omics data integration.
GNU Affero General Public License v3.0
35 stars 5 forks source link

Questions about the dataset. #8

Open KID-KK opened 3 months ago

KID-KK commented 3 months ago

Hello, I have a few questions I would like to ask you:

  1. Do the suffixes in the dataset names have any specific meanings? For example:

    • In Dataset11_Human_Lymph_Node_A1 and Dataset11_Human_Lymph_Node_D1, what do A1 and D1 signify?
    • Similarly, in Dataset1_Mouse_Spleen1 and Dataset1_Mouse_Spleen2, do the suffixes indicate something specific?

    Do these suffixes suggest that an originally complete dataset has been divided into several sub-datasets?

  2. How are the training and testing datasets divided? Which data is used for training? I noticed that the link you provided (https://zenodo.org/records/10362607) describes datasets used for testing. Could you provide more details on this?

Thank you!

longyahui commented 3 months ago

Hi,

Thank you for your questions.

A1: The suffixes mean the identity of samples. Each sample is separate.

A2: SpatialGlue does not involve data division. Each dataset included in the Zenodo depository is both a training and testing dataset. The model takes one sample as input for model training and testing each time. Hope it helps.

Best regards,
Yahui